JP6832498B2 - System and evaluation device and evaluation method - Google Patents

Description

Disclosure embodiments relate to systems and evaluation devices and evaluation methods.

Patent Document 1 describes a technique for automatically adjusting the gain in the position controller of the motor control device based on the acceleration of the motor rotor.

Japanese Unexamined Patent Publication No. 2011-176907

The above-mentioned prior art adjusts the control for the motor based on the behavior of the motor as an industrial device, and is tuned so that the control is correct when the evaluation criteria for whether the control is correct is predetermined. (So-called auto-tuning). However, if the evaluation criteria were not set, adjustments could not be made and control could not be optimized.

The present invention has been made in view of such problems, and a system and evaluation capable of optimizing control even when an evaluation standard for the current control content for industrial equipment is not defined. It is an object of the present invention to provide an apparatus and an evaluation method.

In order to solve the above problems, according to one aspect of the present invention, a control device for controlling an industrial device and an evaluation device for controlling the industrial device and evaluating at least one of the operations of the industrial device are provided. The evaluation device is an information acquisition unit that acquires at least one of control information that is information about control of the industrial equipment and operation information that is information about the operation of the industrial equipment, and the industry. Acquire at least one of the pre-control information which is the information about the control for the industrial equipment before the control for the equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Based on the prior information acquisition unit and at least one of the prior control information and the prior operation information, an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment is determined. Evaluation that performs control on the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on the evaluation standard generation unit to be generated, at least one of the control information and the operation information, and the evaluation standard. A system is applied that includes a unit and an output unit that outputs evaluation information that is information related to the evaluation.

Further, according to another aspect of the present invention, an information acquisition unit that acquires at least one of control information that is information on control of an industrial device and operation information that is information on the operation of the industrial device, and the industry. Acquire at least one of pre-control information which is information about control for the industrial equipment prior to control for the device and pre-operation information which is information about the operation of the industrial equipment before the operation of the industrial equipment. Based on the prior information acquisition unit and at least one of the prior control information and the prior operation information, an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment is determined. Evaluation that performs control on the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on the evaluation standard generation unit to be generated, at least one of the control information and the operation information, and the evaluation standard. An evaluation device characterized by including a unit and an output unit that outputs evaluation information that is information related to the evaluation is applied.

Further, according to still another viewpoint of the present invention, an information acquisition unit that acquires at least one of control information that is information on control of an industrial device and operation information that is information on the operation of the industrial device, and the above-mentioned information acquisition unit. Information on control of other industrial equipment other than the industrial equipment prior to control of the industrial equipment Other device pre-control information and information on the operation of the other industrial equipment prior to the operation of the industrial equipment. Control of the industrial equipment and the industry based on the advance information acquisition unit that acquires at least one of the equipment pre-operation information, and at least one of the other equipment pre-control information and the other equipment pre-operation information. Control and control of the industrial equipment based on the evaluation criteria generator that generates the evaluation criteria used for the evaluation of at least one of the operations of the equipment, and the control information and at least one of the operation information and the evaluation criteria. An evaluation device including an evaluation unit that evaluates at least one of the operations of the industrial equipment and an output unit that outputs evaluation information that is information related to the evaluation is applied.

Further, according to still another viewpoint of the present invention, it is an evaluation method of an evaluation device for evaluating an industrial device, which is control information which is information about control for the industrial device and information about operation of the industrial device. Acquisition of at least one of the operation information, pre-control information which is information on control of the industrial device prior to control of the industrial device, and operation of the industrial device prior to the operation of the industrial device. Control of the industrial equipment and control of the industrial equipment based on the acquisition of at least one of the pre-operation information which is information about the above, and at least one of the pre-control information and the pre-operation information. Control over the industrial equipment and operation of the industrial equipment based on generating an evaluation criterion used for evaluation of at least one of the operations and based on the control information and at least one of the operation information and the evaluation criterion. An evaluation method characterized by performing at least one of the evaluations and outputting evaluation information which is information on the evaluation is applied.

According to the present invention, even when the evaluation criteria for the current control contents for the industrial equipment are not defined, the control can be optimized.

It is a figure which shows an example of the schematic structure of the machine control system of an embodiment. It is a control block diagram which schematically shows the outline of the control parameter adjustment method in a motor control device, and the outline of the evaluation method by the evaluation device of the adjusted control parameter. It is a figure which shows an example of the transmission / reception relation of each information between a feedback control system including a feedback control part, and an adjustment part by a control block of a transfer function form. It is a graph which represented each state quantity data at the time of executing the same sequence operation for adjustment by time series pattern data. It is a figure which shows an example of the schematic model structure of the neural network of the adjustment part when deep learning is applied. It is explanatory drawing which illustrates the data set for learning of the adjustment part corresponding to various sequence operations. It is a graph which shows the time-series pattern of the detection position when the control accuracy is not good. It is a graph which shows the time-series pattern of a torque command when the control accuracy is not good. It is a block diagram which shows an example of the functional structure of the evaluation apparatus. It is a figure which shows an example of the schematic model structure of the neural network of the evaluation standard generation part when deep learning is applied. It is explanatory drawing which illustrates the data set for evaluation standard generation part learning corresponding to various sequence operations. It is a flowchart which shows the processing procedure when the machine learning process is executed in the evaluation standard generation part by data learning. It is a flowchart which shows the detail of the data set creation procedure of FIG. It is a flowchart which shows the processing procedure when the evaluation value determination process is performed in the evaluation part. It is explanatory drawing which shows another method of evaluation value determination processing. It is a system block diagram which shows the hardware composition of the evaluation apparatus.

Hereinafter, embodiments will be described with reference to the drawings.

<Outline configuration of machine control system>
FIG. 1 shows an example of a schematic system block configuration of a machine control system including the evaluation device of the present embodiment. This mechanical control system is a system that controls the linear movement of the slider by controlling the drive of the rotary motor. In FIG. 1, the machine control system 1 includes an upper control device 2, a motor control device 3, a rotary motor 4, a drive machine 5, and an evaluation device 6. The rotary motor 4 and the drive machine 5 correspond to the industrial equipment described in each claim.

The host control device 2 is composed of, for example, a general-purpose personal computer including a CPU, ROM, RAM, an operation unit, a display unit, and the like (not shown). The host control device 2 generates a position command for the slider of the drive machine 5 described later based on various settings and commands input from the operator via the operation unit, and inputs the position command to the motor control device 3.

The motor control device 3 generates a torque command based on the position command input from the upper control device 2 and inputs it to the rotary motor 4. At this time, the motor control device 3 performs feedback control of the position of the rotary motor 4 based on the detection position output from the encoder 41a described later included in the rotary motor 4. The motor control device 3 corresponds to the control device according to each claim.

Further, the motor control device 3 has a feedback control unit 31 and an adjustment unit 32. The feedback control unit 31 is a calculation unit that generates the torque command based on the position command and the detection position. The functional configuration of the feedback control unit 31 will be described in detail with reference to the functional block diagram shown in FIG. 3 below.

The adjusting unit 32 is a processing unit that adjusts control parameters (described later) used in the calculation processing of the torque command in the feedback control unit 31 based on the position command, the detection position, and the torque command in an appropriate situation. is there. The processing content of the adjusting unit 32 will also be described in detail later.

The rotary motor 4 is, for example, a synchronous three-phase AC motor. The rotary motor 4 integrally includes an encoder 41a that outputs the rotational position of the output shaft of the rotary motor 4 as the detection position.

In the illustrated example, the drive machine 5 is an actuator having a coupling 53, a feed screw 51, and a slider 52. The feed screw 51 is connected to the output shaft of the rotary motor 4 via the coupling 53. The slider 52 is a pedestal on which an object can be placed, and the feed screw 51 is screwed into the lower portion thereof. As a result, the rotary motor 4 reverses forward and reverse, so that the slider 52 is fed by the feed screw 51 and moves straight along the direction corresponding to the rotation direction of the rotary motor 4 (left-right direction in the drawing). Driven to do. That is, the drive machine 5 converts the rotational position, which is the shaft output of the rotary motor 4, into the translational position of the slider 52 via the feed screw 51.

The evaluation device 6 will be described later.

<Characteristics of this embodiment>
In the above configuration, as described above, the feedback control unit 31 of the motor control device 3 is a rotary motor so that the position of the slider 52 follows the position command based on the detection position output from the encoder 41a. Position feedback control is performed to control the torque command input to 4. At this time, the feedback control unit 31 outputs the torque command by arithmetic processing using a large number of the control parameters. Therefore, the adjusting unit 32 appropriately sets the control parameters in response to the mechanical constants of the rotary motor 4 and the drive machine 5, the disturbance that can be added, and the like.

At this time, in the present embodiment, as the greatest feature, it is verified whether or not the setting of the control parameter by the adjustment unit 32 as described above is really appropriate. That is, the machine control system 1 is provided with the evaluation device 6, and the evaluation device 6 controls the motors / drive machines 4 and 5 by the motor control device 3 based on the detection position and the torque command, and At least one of the operations of the motor / drive machine 4 and 5 (specifically, the control parameter adjusted by the adjusting unit 32) is evaluated.

<Outline of control parameter adjustment and evaluation method>
FIG. 2 shows a control block diagram schematically showing an outline of a control parameter adjustment method in the motor control device 3 and an outline of an evaluation method by the adjusted control parameter evaluation device 6.

In FIG. 2, between the command information r input from the outside and the operation information y output by the industrial equipment (the rotary motor 4 and the drive machine 5. Here, simply shown as “industrial equipment 4 and 5”). The deviation of is input to the feedback control unit 31. The feedback control unit 31 outputs control information u by arithmetic processing based on the control parameter ρ, and the industrial devices 4 and 5 are controlled by the control information u. The command information r referred to here corresponds to the position command, the control information u corresponds to the torque command, and the operation information y corresponds to the detection position.

In the feedback control system as described above, since the feedback control unit 31 is a predetermined calculation model using the variable control parameter ρ, it can be said that its characteristics and behavior are completely known. On the other hand, regarding industrial equipment 4 and 5, even if a rough model based on design values is known, individual differences (part manufacturing error, assembly error, etc.) and operating conditions of the industrial equipment 4 and 5 themselves, It can be said that its substantive and detailed characteristics and behavior are unknown due to changes in aging deterioration and usage environment. That is, the control parameter ρ needs to be adjusted so as to adapt to specific mechanical constants and disturbances in the actually applied industrial equipments 4 and 5.

Here, it is considered that the unknown mechanical constants and disturbance factors in the industrial devices 4 and 5 have a great influence on the correlation between the command information r and the operation information y. Therefore, in the present embodiment, the command information r, control information u, operation information y, and other operation conditions c at the time of various sequence operations or disturbance addition are associated with the control parameter ρ set at that time. The adjustment unit learning data set (see FIG. 6 described later) is recorded and saved in the database DB (see FIG. 3 described later). Then, the adjusting unit 32 executes a machine learning process based on the adjusting unit learning data set, so that the industrial equipment 4 estimated from the correspondence relationship with the command information r, the control information u, and the operation information y. _{Appropriate control parameter ρ NEW} is set according to the mechanical constant of 5 and the disturbance.

On the other hand, the evaluation device 6 also refers to command information r, control information u, operation information y, and other operation conditions c at the time of various sequence operations and disturbance addition, and control parameters set at that time. A data set for learning of the evaluation standard generation unit (see FIG. 11 described later) associated with the evaluation value is separately recorded and saved. Then, the evaluation device 6 executes a machine learning process (separate from the machine learning process executed by the adjusting unit 32) based on the evaluation standard generation unit learning data set, so that the control information u and the operation information y are executed. From the correspondence with, it is possible to output the evaluation information estimated for the _{control parameter ρ NEW set at that time.} If the control parameter setting by the adjustment unit 32 is not appropriate, a warning is issued to the operator, the control parameter is readjusted by the adjustment unit, the rotary motor 4 or the drive machine 5 is stopped, and the like. Appropriate measures can be taken.

<Specific configuration>
Hereinafter, a specific configuration for executing the above method will be described step by step.

<Feedback control unit 31 and adjustment unit 32>
FIG. 3 shows an example of the transmission / reception relationship of each information between the feedback control system including the feedback control unit 31 and the adjustment unit 32 by a transfer function type control block. As shown in FIG. 3, the feedback control system includes the feedback control unit 31, the rotary motor 4 and the drive machine 5 (hereinafter, appropriately simply referred to as “motor / drive machine 4, 5”), and the above. A coordinating unit 32 and a database DB are provided.

The feedback control unit 31 includes a subtractor 34, a gain multiplier 38, a subtractor 35, an integrator 39, an adder 36, a gain multiplier 38, a gain multiplier 40, and a speed calculator 37.

The subtractor 34 subtracts the detected positions detected by the motors / drive machines 4 and 5 from the position commands input from the upper control device 2, and outputs the position deviation between them to the gain multiplier 38. To do. Then, the gain multiplier 38 multiplies the position deviation by the position loop gain Kp, generates a speed command, and outputs the speed command to the subtractor 35. In the present embodiment, the gain multiplier 38 functions as a feedback control portion for position control, and performs so-called position proportional control.

The speed calculator 37 generates a detection speed (output speed of the rotary motor 4) based on the detection positions detected from the motors / drive machines 4 and 5, and outputs the detection speed (output speed of the rotary motor 4) to the subtractor 35. Specifically, the speed calculator 37 is composed of a differentiator (abbreviated as “s” in the figure).

The subtractor 35 subtracts the detection speed output from the speed calculator 37 from the speed command output from the gain multiplier 38, and outputs a speed deviation between them. The integrator 39 performs an integral operation based on the integrator T of the integrator loop for the output velocity deviation (abbreviated as "1 / T · s" in the figure), and the adder 36 is the integrator 39. And the speed deviation from the subtractor 35 are added and output to the gain multiplier 40. The gain multiplier 40 generates and outputs the torque command by multiplying this added output by the speed loop gain Kv. In the present embodiment, the integrator 39 and the gain multiplier 40 function as a feedback control portion for speed control, and perform so-called speed integral proportional control.

The motors / drive machines 4 and 5 (corresponding to the industrial devices 4 and 5 in FIG. 2 above) are the entire movable mechanism in which the rotor of the rotary motor 4 and the movable portion of the drive machine 5 are connected in FIG. It is represented by a mathematical model based on the moment of inertia J (abbreviated as "1 / J · s" and "1 / s" in the figure).

As described above, the feedback control system of the present embodiment composed of the feedback control unit 31 and the motors / drive machines 4 and 5 has a double loop configuration of a feedback loop of the position proportional control system and a feedback loop of the speed integration proportional control system. (So-called P-IP control).

<Data acquisition phase and subsequent machine learning>
In the above feedback control system, when the above-mentioned adjustment unit learning data set is acquired, the above position loop gain Kp, the above speed loop integration time constant T, and the above speed loop gain Kv corresponding to the control parameter ρ are obtained. A position command (in command information r) when a predetermined adjustment sequence operation is executed with each value of (hereinafter, these are collectively referred to as "control parameters Kp, T, Kv" as appropriate) temporarily set as appropriate. (Equivalent), torque command (corresponding to control information u), and detection position (corresponding to operation information y) are recorded in the database DB.

That is, in the present embodiment, the position command, the torque command, and the detection position (hereinafter, appropriately collectively referred to as “state quantity data”) are shown in FIGS. 4 (a), 4 (c), and 4 respectively. As shown in (d), it is recorded as time-series pattern data in which instantaneous values are sequentially recorded in the same time-series when the adjustment sequence operation is executed. In the examples shown in FIGS. 4 (a), 4 (c), and 4 (d), when the sequence operation is executed by the positioning operation in which the position command is increased from 0 to a predetermined position by so-called locus control, each of them. The time series pattern data (thick solid line waveform data) of the state quantity is shown. The sequence operation may be executed by the speed command control or the torque command control, not limited to the case where the position command control is performed. For example, as shown in FIG. 4B, a speed command is input in a trapezoidal time-series pattern in which there is a section in which the acceleration during acceleration / deceleration is constant and the steady speed remains constant, and the sequence operation is executed. You may let me. Alternatively, input a speed command expressed by a polynomial, trigonometric function, exponential function, etc. that guarantees the continuity of acceleration at the switching part between acceleration / deceleration and constant speed in such a time series pattern, and perform sequence operation. You may let it run.

At this time, for each of the various adjustment sequence operations, the time-series pattern data of each state quantity data (position command, torque command, and detection position) and the control parameters Kp, T, tentatively set during the adjustment sequence operation, One adjustment unit learning data set is created in association with Kv and saved in the database DB (= data acquisition phase. See the broken line arrow in FIG. 3). The database DB may be configured by an appropriate storage device provided inside the motor control device 3, or may be configured by an appropriate external storage device connected to the motor control device 3 so as to be able to send and receive information. It may be (not shown in FIG. 1 above). After a sufficient number of adjustment unit learning data sets have been acquired in the database DB in this way, the adjustment unit 32 performs machine learning using these adjustment unit learning data sets (= learning phase, which will be described later). See also FIGS. 5 and 6).

<Parameter setting phase>
After the machine learning is performed as described above, when the actual operation sequence operation of the machine control system 1 is executed, the adjustment unit 32 is based on the above learning content (in a form reflecting the learning content). However, each control parameter Kp, T, Kv is set (= parameter setting phase. See the dotted arrow in FIG. 3). That is, the time-series pattern data of each state amount data (position command, torque command, and detection position) when the actual operation sequence operation of the machine control system 1 is executed with each control parameter temporarily set is the adjustment unit. When input to 32, the adjusting unit 32 outputs the optimum control parameters Kp, T, Kv reflecting the learning content to the feedback control unit 31. Then, by setting these output control parameters Kp, T, and Kv in the feedback control unit 31, it is possible to ensure good control accuracy in the feedback control system during the actual operation.

<Example of machine learning method of adjustment unit 32>
In the machine learning executed by the adjusting unit 32, various known learning methods can be applied. Hereinafter, as an example, an example in which deep learning is applied to the machine learning algorithm will be described. FIG. 5 shows an example of a schematic model configuration of the neural network of the adjustment unit 32 when deep learning is applied.

In FIG. 5, the neural network of the adjustment unit 32 has these state quantities with respect to the position command, the torque command, and the time series pattern data of the detection position, which are the state quantity data input from each unit. 9 control parameters Kp, T, Kv that are estimated from the correspondence between the data (particularly the correspondence between the position command and the detection position) (for example, the 9 control parameters Kp, T, Kv that appropriately correspond to the mechanical constants of the motor / drive machine 4 and 5). It is designed to output. In the schematic model configuration example of the neural network shown in FIG. 5, the values and signals corresponding to the above mechanical constants (for example, the values and signals representing the characteristics) are not shown. There is.

As shown in FIG. 5, instantaneous values (sampled in the same predetermined sampling cycle) of each state quantity data, which is time series pattern data, are input to each input node of the adjustment unit 32 arranged in chronological order. Then, each output node outputs control parameters Kp, T, and Kv by multi-value output (continuous value) by regression problem processing. The setting process of these control parameters Kp, T, Kv is based on the learning content in the machine learning process of the adjusting unit 32 in the learning phase described above. That is, in the neural network of the adjusting unit 32, feature quantities representing the correlation between the state quantity data and the appropriate control parameters Kp, T, Kv are learned.

In the machine learning process of the adjustment unit 32, after the multi-layer neural network designed as described above is implemented in the motor control device 3 in terms of software (or hardware), a large number of adjustment units for learning are stored in the database DB. It can be learned by so-called supervised learning using a database.

As shown in FIG. 6, for example, the adjustment unit learning data set includes each state quantity data (time series pattern data) when various adjustment sequence operations are executed, its responsiveness evaluation value, and at that time. This is a data set associated with the temporarily set control parameters Kp, T, and Kv. In the illustrated example, the responsiveness evaluation value is an index indicating the evaluation of responsiveness in the sequence operation of the feedback control system to which the control parameters Kp, T, Kv of the corresponding data set are applied.

The responsiveness evaluation values include, for example, position deviation, vibration amplitude during overshoot or undershoot, settling time until the end of the transition period, rise time until the operation information follows the command, and torque command. It may be comprehensively obtained based on the state quantity data of the data set, such as the magnitude of the ripple of the value, the power consumption value that can be estimated from the torque command value and the speed. Further, a torque command in which a plurality of sine waves are combined may be input, and the values of the phase margin, the gain margin, and the sensitivity function calculated from the response may be used as an index. In the figure, this evaluation value is represented by an index of two stages of "high" and "low", but it may be expressed by an index of three or more stages or a numerical value.

Then, in the present embodiment, (the relationship between the input layer and the output layer of the neural network of the adjustment unit 32 is established by using the teacher data of the combination in which the state quantity data is the input data and the control parameter is the output data. (Adjust the weighting coefficient of each edge connecting each node) so-called backpropagation processing or the like can be used for learning. In this backpropagation processing, only the data set having a particularly high responsiveness evaluation value may be extracted from a large number of data sets, and only this data set may be used as the teacher data to adjust the weighting coefficient of each edge. Alternatively, all the data sets may be used as teacher data, and the weighting coefficient of each edge may be adjusted to be strengthened or weakened according to the respective responsiveness evaluation values. Not limited to such backpropagation, processing accuracy can be improved by using various known learning methods such as so-called autoencoder, restricted Boltzmann machine, dropout, noise addition, and sparse regularization. Good.

The machine learning process by data learning processing in offline learning (batch learning) as described above may be performed before the start of operation of the machine control system 1, or the rotary motor 4 and the drive machine 5 are deteriorated over time. It may be performed when necessary after the start of operation for the purpose of improving control accuracy according to changes in the situation and usage environment. Further, by performing the data learning by online learning, it is possible to always set appropriate control parameters in response to changes in the aged deterioration state and the usage environment state during the operation of the machine control system 1. Environmental data (ambient temperature, posture, etc. of the drive machine 5) that may affect the control accuracy in the sequence operation of the motor / drive machine 4 and 5 is detected by a separate sensor and included in the adjustment unit learning data set. The coordinating unit 32 may learn.

Further, as described above, the adjusting unit 32 of the motor control device 3 is not limited to executing machine learning by itself in the learning phase (using the data set obtained in the data face). That is, the learning content in the machine learning executed in the same manner as above using other industrial equipment, which is the same industrial equipment as the rotary motor 4 (in the above method, the combination of the weighting coefficients of each edge, etc.) ) May be acquired by the adjusting unit 32, and the control parameters Kp, T, and Kv may be set using this in the parameter setting phase.

Further, as described above, the machine learning algorithm executed by the adjustment unit 32 is not limited to the one based on the illustrated deep learning, and other machine learning algorithms using, for example, a support vector machine or a Bayesian network (not shown in particular). May be applied. Even in that case, the basic configuration of outputting the control parameters appropriately corresponding to the input state quantity data is the same.

<Evaluation device 6>
Next, the evaluation of the control parameters by the evaluation device 6 will be described in detail.

<Background where evaluation of control parameters is particularly effective>
For example, even when the adjusting unit 32 sets the control parameters based on the machine learning as described above, the control accuracy in the feedback control system is not always the best in the actual operation.

For example, as shown in FIG. 7 corresponding to FIG. 4 (d), even when the position command (see the dotted line in the figure) is increased from 0 to a predetermined position by so-called locus control, the actual motor / drive machine The behavior of changes in the detection positions (see the thick solid line in the figure) in 4 and 5 may differ (does not accurately follow the position commands). As an index for evaluation regarding controllability at this time, for example, an overshoot amount, a settling time, and a maximum position deviation can be used as shown in the figure. The overshoot amount corresponds to the vibration amplitude amount of the detection positions (operating positions of the motors / drive machines 4 and 5) after positioning when the fluctuation of the position command has stopped. The settling time corresponds to the elapsed time from after the positioning until the vibration of the detection position converges (converges within the coin width region based on the positioned position command). The maximum position deviation corresponds to the maximum deviation between the position command and the detection position. Further, as shown in FIG. 8 corresponding to FIG. 4 (c), vibration ripple may occur where the torque command in a constant speed region should be stable at a constant value. The index related to controllability at this time is the amplitude of the vibration of the torque command.

In addition to the above, although not particularly shown, there are also evaluation indexes such as acceleration, torque, noise, and power consumption in the operation information of the motor / drive machine 4 and 5. When the control parameter setting is not appropriate, one of these evaluation indexes may show a value (= abnormal value) different from the case where the control parameter setting is appropriate.

<Functional configuration of evaluation device-Part 1>
Based on the above background, in the present embodiment, it is evaluated and verified whether or not the current control content (specifically, the control parameter currently set in this example) by the adjustment unit 32 is really appropriate. The evaluation device 6 is provided for this purpose. FIG. 9 is a block diagram showing the functional configuration of the evaluation device 6. In FIG. 9, the evaluation device 6 includes an abnormality information acquisition unit 61, a prior information acquisition unit 65, an information acquisition unit 70, a consumption degree information acquisition unit 68, an evaluation standard generation unit 71, and an evaluation unit 62. A determination unit 63, a parameter identification unit 64, and an output unit 67 are functionally provided.

The evaluation device 6 has a learning phase in which machine learning is performed, which will be described later, and an operation phase in which the above-mentioned current control parameters are evaluated based on the learning results in the learning phase after the learning phase is executed (. In other words, the learning phase is executed before the operational phase). The above-mentioned abnormality information acquisition unit 61, the advance information acquisition unit 65, and the evaluation standard generation unit 71 mainly function in the above-mentioned learning phase. The evaluation unit 62 functions in both the learning phase and the operation phase.

That is, in the learning phase, the advance information acquisition unit 65 acquires advance control information (in this example, the torque command; the same applies hereinafter) which is information related to control of the motors / drive machines 4 and 5 from the motor control device 3. , Preliminary operation information (in this example, the detection position in the rotary motor 4; the same applies hereinafter), which is information on the operation of the motors / drive machines 4 and 5, is acquired from the encoder 41a. The advance information acquisition unit 65 may acquire only one of the above-mentioned advance control information and advance operation information. In that case, each process described thereafter can be performed by the information of either one.

The abnormality information acquisition unit 61 is used as the teacher data of the evaluation standard generation unit learning data set used at the time of machine learning execution (described later) of the evaluation standard generation unit 71 in the learning phase, and is used as control abnormality information and operation. Acquire anomaly information (either one of them may be used). The control abnormality information and the operation abnormality information are information accompanying the state quantity data included in the evaluation standard generation unit learning data set, and are input to the evaluation device 6 based on, for example, an appropriate operation input of the operator. The control abnormality information indicates that the control for the motors / drive machines 4 and 5 is abnormal, and the operation abnormality information indicates that the operations of the motors / drive machines 4 and 5 are abnormal (see also FIG. 11 described later). These control abnormality information and operation abnormality information are output to the evaluation unit 62 and the evaluation standard generation unit 71.

The evaluation standard generation unit 71 is based on the advance control information and the advance operation information acquired by the advance information acquisition unit 65, and the control abnormality information and the operation abnormality information acquired by the abnormality information acquisition unit 61. In the operation phase, the evaluation unit 62 generates an evaluation standard to be used when performing evaluation (details will be described later). In particular, the evaluation standard generation unit 71 includes an item-specific evaluation standard generation unit 71A that generates the above-mentioned evaluation standard as an item-specific evaluation standard for each of a plurality of predetermined evaluation items. That is, the itemized evaluation standard generation unit 71A is based on the prior control information and the prior operation information (which may be any one of them) acquired by the prior information acquisition unit 65, and the prior control information (torque command). ) And the above itemized evaluation criteria for at least one of the above prior operation information (detection position). This itemized evaluation standard is generated for each of the plurality of evaluation items (for example, the overshoot amount, the settling time, the maximum position deviation, the amplitude of the torque command, the acceleration, the torque, the noise, and the power consumption described above). The evaluation standard generation unit 71 may generate the evaluation standard in response to the control information and the operation information (details will be described later) acquired by the information acquisition unit 70 in the operation phase.

The generation of the evaluation criteria for each item is performed by machine learning by the evaluation criteria generation unit 71 (specifically, the evaluation criteria generation unit 71A for each item) in the learning phase prior to the operation phase.

<Example of machine learning method of evaluation standard generation unit 71>
In the machine learning executed by the evaluation standard generation unit 71, various known machine learning methods can be applied. Hereinafter, as an example, an example in which deep learning is applied to the machine learning algorithm as in the case of machine learning in the adjustment unit 32 described above will be described. FIG. 10 shows an example of a schematic model configuration of the neural network of the evaluation standard generation unit 71 when deep learning is applied.

In FIG. 10, the neural network of the evaluation standard generation unit 71 is at each time of the torque command (corresponding to the pre-control information) and the detection position (corresponding to the pre-operation information) which are the state quantity data input from each unit. Values related to the above-mentioned plurality of evaluation items (overshoot amount, settling time, maximum position deviation, torque command amplitude, acceleration, etc., estimated from the correspondence between these state quantity data with respect to the series pattern data. It is designed to output torque, noise, power consumption, etc. (hereinafter referred to as "evaluation item values"), the control abnormality information, and the operation abnormality information (not shown). At this time, the evaluation item values are designed in advance so that each item is clustered into two groups, a "group with a large value" and a "group with a small value", and output (not limited to the two). It may be clustered into three or more groups according to the value of the item value). Therefore, in the illustrated example, the output side is "large overshoot amount", "small overshoot amount", "large settling time", "small settling time", "large maximum position deviation", "small maximum position deviation", and "large torque command amplitude". "Small torque command amplitude", "Large acceleration", "Small acceleration", "Large torque", "Small torque", "Large noise", "Small noise", "Large power consumption", "Small power consumption", etc. (partially not shown) It is designed to be clustered. Then, the boundary condition of clustering for each item at the time of clustering in this way becomes the evaluation standard for each item (generation of evaluation standard).

That is, for example, when clustered into two groups of "large overshoot amount" and "small overshoot amount" as described above, when the overshoot amount is Ls [mm] or more, the "large overshoot amount" side. If the overshoot amount is less than Ls [mm] and the overshoot amount is output to the "small overshoot amount" side, the evaluation standard for the overshoot amount in this case is "(as a threshold value)". "Less than Ls [mm] of overshoot amount" is evaluated as "good", "greater than or equal to Ls [mm] of overshoot amount (as a threshold value)" is evaluated as "no", and the threshold value is an evaluation criterion for judgment of quality. It becomes. In this way, the above clustering generates an evaluation criterion regarding "overshoot". When clustering into three or more groups as described above, the threshold value of each group serves as an evaluation standard, and for example, "excellent" evaluation, "good" evaluation, "possible" evaluation, and "bad", respectively. Evaluation, "inferior" evaluation, etc. (Hereafter, the same applies to other evaluation items).

Further, for example, when clustered into two groups of "large settling time" and "small settling time" as described above, when the settling time is Ts [s] or more, it is output to the "large settling time" side and settled. If the time is less than Ts [s] and the output is to the "small settling time" side, the evaluation criteria for the settling time in this case is "less than the settling time Ts [s] (as a threshold value)". Is a "good" evaluation, "a settling time Ts [s] or more (as a threshold value)" is a "no" evaluation, and the threshold value is used as an evaluation criterion for good / bad judgment. In this way, the above clustering generates an evaluation criterion regarding "setting time".

Further, for example, when clustered into two groups of "maximum position deviation large" and "maximum position deviation small" as described above, when the maximum position deviation is Ld [mm] or more, it moves to the "maximum position deviation large" side. If it is output and the maximum position deviation is less than Ld [mm] and it is output to the "maximum position deviation small" side, the evaluation criterion of the maximum position deviation in this case is "maximum (as a threshold value)". "Less than position deviation Ld [mm]" is evaluated as "good", "greater than or equal to maximum position deviation Ld [mm] (as a threshold value)" is evaluated as "no", and the threshold value is used as an evaluation criterion for judgment of quality. .. In this way, the above clustering generates an evaluation criterion regarding the "maximum position deviation".

Further, for example, when clustered into two groups of "torque command amplitude large" and "torque command amplitude small" as described above, when the torque command amplitude is It or more, it is output to the "torque command amplitude large" side. Assuming that the torque command amplitude is output to the "small torque command amplitude" side when the torque command amplitude is less than It, the evaluation standard of the torque command amplitude in this case is "less than the torque command amplitude It (as a threshold value)". "Good" evaluation and "Torque command amplitude It or more (as a threshold value)" are evaluated as "No", and the threshold value is used as an evaluation criterion for good / bad judgment. In this way, the above clustering generates an evaluation standard regarding "torque command amplitude".

For example, when clustered into two groups of "large acceleration" and "small acceleration" as described above, when the acceleration is Am [m / s ² ] or more, it is output to the "large acceleration" side and the acceleration is applied. If it is less than Am [m / s ² ] and it is output to the "small acceleration" side, the evaluation standard of acceleration in this case is "acceleration Am [m / s ² ] or more (as a threshold value)". Is evaluated as "good", "acceleration ^{less than Am [m / s 2} ] (as a threshold value)" is evaluated as "bad", and the threshold value is used as an evaluation criterion for judging good or bad. In this way, the above clustering generates an evaluation criterion regarding "acceleration".

Further, for example, when clustered into two groups of "large torque" and "small torque" as described above, when the torque is Tr [Nm] or more, it is output to the "large torque" side and the torque is Tr. Assuming that the torque is output to the "small torque" side when it is less than [Nm], "torque Tr [Nm] or more (as a threshold value)" is "more than" as the evaluation standard of the torque in this case. "Good" evaluation and "less than torque Tr [Nm] (as a threshold value)" are evaluated as "No", and the threshold value is used as an evaluation criterion for good / bad judgment. In this way, the above clustering generates an evaluation standard regarding "torque".

Further, for example, when clustered into two groups of "loud noise" and "low noise" as described above, when the noise is Ns [dB] or more, it is output to the "loud noise" side and the noise is Ns [dB]. ], And if it is output to the "low noise" side, "less than noise Ns [dB] (as a threshold value)" is evaluated as "good" and "((as a threshold value)" as the evaluation criteria for noise in this case. "Noise Ns [dB] or more (as a threshold value)" is evaluated as "No", and the threshold value is used as an evaluation criterion for quality judgment. In this way, the above clustering generates an evaluation standard regarding "noise".

Further, for example, when clustered into two groups of "high power consumption" and "low power consumption" as described above, when the power consumption is Pe [W] or more, it is output to the "high power consumption" side and consumed. Assuming that the power is output to the "low power consumption" side when the power is less than Pe [W], the evaluation standard of the power consumption in this case is "less than the power consumption Pe [W] (as a threshold value)". Is a "good" evaluation, "power consumption Pe [W] or more (as a threshold value)" is a "no" evaluation, and the threshold value is used as an evaluation criterion for good / bad judgment. In this way, the above clustering generates an evaluation criterion regarding "power consumption".

Although not shown, the information of "control parameter normal" and "control parameter abnormality" as the control abnormality information is also output as binary values so that only one of them becomes a true value.

As described above, in the neural network of the evaluation standard generation unit 71, feature quantities representing the correlation between each state quantity data and each evaluation item value, control abnormality information, and operation abnormality information are learned. ..

In the machine learning process of the evaluation standard generation unit 71, after the multi-layer neural network designed as described above is implemented in software (or hardware) in the evaluation device 6, a large number of evaluation standard generation unit learning data sets are used. Can be learned by so-called supervised learning using.

As shown in FIG. 11, for example, the evaluation standard generation unit learning data set may have various evaluation sequence operations (the same operation as the adjustment sequence operation related to the adjustment unit learning data set, or another operation. Each state quantity data (time series pattern data) when (good) is executed and the above evaluation item value are preset so as to be divided into the same way as those learned by the above clustering. It is a data set in which the index in comparison with the control abnormality information and the operation abnormality information are associated with each other.

Then, in the learning phase of the evaluation standard generation unit 71 in the present embodiment, a combination of teacher data using the state quantity data as input data and the evaluation item value, control abnormality information, and operation abnormality information as output data is used. , (Adjust the weighting coefficient of each edge connecting each node so that the relationship between the input layer and the output layer of the neural network of the evaluation standard generation unit 71 is established.) Learning is performed by so-called back propagation processing or the like. be able to. Not limited to such backpropagation, processing accuracy can be improved by using various known learning methods such as so-called autoencoder, restricted Boltzmann machine, dropout, noise addition, and sparse regularization. Good.

Further, the machine learning process by the data learning process in the offline learning (batch learning) as described above may be performed before the start of operation of the machine control system 1, or the rotary motor 4 and the drive machine 5 are deteriorated over time. It may be performed when necessary after the start of operation for the purpose of improving control accuracy according to changes in the situation and usage environment. Further, by performing the data learning by online learning, it is possible to always set appropriate control parameters in response to changes in the aged deterioration state and the usage environment state during the operation of the machine control system 1. In addition, environmental data (ambient temperature, posture, etc. of the drive machine 5) that may affect the control accuracy in the evaluation sequence operation of the motor / drive machine 4 and 5 is detected by a separate sensor, and the evaluation standard generator learning data. It may be included in the set so that the evaluation standard generation unit 71 learns.

Further, as described above, the evaluation standard generation unit 71 of the evaluation device 6 is not limited to executing machine learning by itself in the learning phase. That is, the learning content in the machine learning executed in the same manner as above using other industrial equipment, which is the same industrial equipment as the rotary motor 4 (in the above method, the combination of the weighting coefficients of each edge, etc.) ) Is acquired by the evaluation standard generation unit 71, and the evaluation standard generation unit 71 may generate the evaluation criteria for each of the above items using this.

Further, as described above, the machine learning algorithm of the evaluation standard generation unit 71 in the learning phase is not only the one based on the illustrated deep learning, but also other machine learning algorithms using, for example, a support vector machine or a Bayesian network (particularly, the figure). (Not shown) may be applied. Even in that case, the basic configuration of outputting the above-mentioned evaluation item value, control abnormality information, and operation abnormality information appropriately corresponding to the input state quantity data is the same.

<Procedure of learning process>
A specific procedure of the machine learning process in the evaluation standard generation unit 71 will be described with reference to FIG. FIG. 12 is a flowchart showing a processing procedure when the CPU 901 of the evaluation device 6 (see FIG. 16 described later) executes a machine learning process in the learning phase.

In FIG. 12, this flow is started, for example, by inputting a command from the host controller 2 to execute the machine learning process.

First, in step S10, the CPU 901 selects one from various evaluation sequence operations prepared in advance.

After that, in step S15, the CPU 901 inputs the position command of the evaluation sequence selected in step S10 to the feedback control unit 31 (for example, via the adjustment unit 32), and performs the corresponding sequence operation in the motor / drive machine. Let 4 and 5 execute.

Then, in step S20, the CPU 901 uses the advance information acquisition unit 65 to perform the position command, the torque command, and the state quantity data of the detection position during the execution of the evaluation sequence operation started in the step S15. And record.

After that, the process proceeds to step S25, and the CPU 901 uses the evaluation standard generation unit 71 to compare the evaluation criteria for each evaluation item corresponding to the evaluation sequence operation started in step S15 with the index " Acquire and record "Large" or "Small" (before learning).

After that, the process proceeds to step S27, and the CPU 901 acquires the control abnormality information and the operation abnormality information corresponding to the evaluation sequence operation started in step S15 by the abnormality information acquisition unit 61, and is it "normal"? Record whether it is "abnormal".

Then, in step S30, the CPU 901 includes the state quantity data recorded in step S20, the index for the evaluation criteria for each evaluation item determined in step S25, and the control abnormality information recorded in step S27. -Create one evaluation standard generator learning data set with the operation abnormality information.

The detailed procedure of this step S30 is shown in FIG.

In FIG. 13, the CPU 901 first acquires the torque command from each state quantity data recorded in step S20 in step S310.

After that, in step S320, the CPU 901 acquires the detection position among the state quantity data recorded in step S20.

Then, in step S330, the CPU 901 acquires an index related to the overshoot amount, that is, "large overshoot amount" or "small overshoot amount" among the indexes for each evaluation standard recorded in step S25.

After that, the process proceeds to step S340, and the CPU 901 acquires the index related to the settling time, that is, "large settling time" or "small settling time" among the indexes for each evaluation standard recorded in step S25.

Then, in step S350, the CPU 901 acquires an index related to the torque command amplitude, that is, "large torque command amplitude" or "small torque command amplitude" among the indexes for each evaluation standard recorded in step S25.

After that, the process proceeds to step S360, and the CPU 901 acquires an index related to the maximum position deviation, that is, "large maximum position deviation" or "small maximum position deviation" among the indexes for each evaluation standard recorded in step S25.

After that, the process proceeds to step S370, and the CPU 901 acquires the indicators of the control abnormality information and the operation abnormality information recorded in step S27, that is, "normal" or "abnormal".

Then, in step S380, the CPU 901 collectively combines all the information (data) acquired in steps S310 to S370 into one file (see FIG. 11). Then, the process proceeds to step S35 in FIG.

Returning to FIG. 12, in step S35, the CPU 901 determines whether or not the data set has been created for all the evaluation sequence operations prepared in advance. If the evaluation sequence operation for which the data set has not been created remains, the determination is not satisfied, and the process returns to step S10 and the same procedure is repeated.

On the other hand, when the data set is created for all the evaluation sequence operations prepared in advance, the determination in step S35 is satisfied, and the process proceeds to step S45.

In step S45, the CPU 901 executes machine learning by the method described above using the evaluation standard generation unit learning data set created in step S30. Then, this flow ends.

In addition, in FIG. 12 and FIG. 13, the case where the above-mentioned four evaluation items of overshoot amount, settling time, torque command amplitude, and maximum position deviation are used has been described as an example, but the present invention is limited to this. Absent. Depending on the use and necessity of the operator, only a part of these four items may be used, or five or more evaluation items including another item may be used.

The machine learning process by data learning processing in offline learning (batch learning) as described above may be performed before the start of operation of the machine control system 1, or the rotary motor 4 and the drive machine 5 may be aged. It may be performed when necessary after the start of operation for the purpose of improving the control accuracy according to the deterioration status and the change of the usage environment. In addition, by performing online learning using control information, operation information, etc. input in real time, it is always appropriate to respond to changes in aging deterioration status and usage environment status during the operation of the machine control system 1. Control parameters can be evaluated. Further, as described above, in addition to executing the machine learning process by the evaluation standard generation unit 71 itself of the evaluation device 6, the learning content obtained by the external machine learning process (combination of weighting coefficients of each edge in this case). May be acquired and used.

<Functional configuration of evaluation device-Part 2>
Returning to FIG. 9, the above-mentioned information acquisition unit 70, consumption degree information acquisition unit 68, determination unit 63, parameter identification unit 64, and output unit 67 of the evaluation device 6 are currently based mainly on the learning results in the learning phase. It functions in the above operation phase to evaluate the control parameters of.

That is, the information acquisition unit 70 acquires control information (in this example, the above torque command; the same applies hereinafter) which is information on the current control of the motor / drive machines 4 and 5 from the motor control device 3, and also acquires the motor / drive machine. Operation information (in this example, the detection position in the rotary motor 4; the same applies hereinafter), which is information on the current operations of 4 and 5, is acquired from the encoder 41a.

The wear degree information acquisition unit 68 inputs wear degree information related to the wear degree of parts (for example, moving parts such as actuators and gears (not shown)) in the motor / drive machines 4 and 5. The consumption degree information of the power conversion unit (inverter, amplifier, etc., which is not shown) in the motor control device 3 may be included as the consumption degree information.

<Evaluation by the evaluation department (evaluation value determination)>
The itemized evaluation criteria generated as described above are input to the evaluation unit 62. In the operation phase, the evaluation unit 62 refers to the motors / drive machines 4 and 5 for each evaluation item based on the control information and operation information acquired by the information acquisition unit 70 and the input item-specific evaluation criteria. The evaluation value of at least one of the control and the operation of the motor / drive machine 4 and 5 is determined, and the control parameter currently set (at the time when the operation phase is being executed) is evaluated (=). Generate the corresponding evaluation information).

An example of the evaluation value determination processing method by the evaluation unit 62 at this time will be described with reference to the flowchart of FIG.

In FIG. 14, first, in step S105, the CPU 901 sets the initial score, which is the base of the evaluation value, to a predetermined value (for example, 50 points in this example).

After that, in step S110, the CPU 901 acquired the overshoot amount corresponding to the acquired information from the evaluation standard generation unit 71 based on the control information or the operation information acquired by the information acquisition unit 70. It is determined whether or not it is smaller than the value of the overshoot amount in the itemized evaluation standard (the overshoot amount Ls [mm] as the threshold value described above). If it is equal to or higher than the threshold value, the determination is not satisfied (S110: No), the score is deducted by 5 points in step S115, and the process proceeds to step S125 described later. If it is less than the threshold value, the determination is satisfied (S110: Yes), the score is increased by 5 points in step S120, and the process proceeds to step S125.

In step S125, the CPU 901 evaluates each item based on the control information or operation information acquired by the information acquisition unit 70, and the settling time corresponding to the acquired information is acquired from the evaluation standard generation unit 71. It is determined whether or not it is smaller than the value of the settling time in the reference (the settling time Ts [s] as the threshold value described above). If it is equal to or higher than the threshold value, the determination is not satisfied (S125: No), the score is deducted by 5 points in step S130, and the process proceeds to step S140 described later. If it is less than the threshold value, the determination is satisfied (S125: Yes), the score is increased by 5 points in step S135, and the process proceeds to step S140.

In step S140, the CPU 901 uses the control information or operation information acquired by the information acquisition unit 70 to obtain the torque command amplitude corresponding to the acquired information for each item acquired from the evaluation reference generation unit 71. It is determined whether or not it is smaller than the value of the torque command amplitude in the evaluation standard (torque command amplitude It as the above-mentioned threshold value). If it is equal to or higher than the threshold value, the determination is not satisfied (S140: No), the score is deducted by 5 points in step S145, and the process proceeds to step S155 described later. If it is less than the threshold value, the determination is satisfied (S140: Yes), the score is increased by 5 points in step S150, and the process proceeds to step S155.

In step S155, the CPU 901 is based on the control information or the operation information acquired by the information acquisition unit 70, and the maximum position deviation corresponding to the acquired information is obtained for each item from the evaluation standard generation unit 71. It is determined whether or not it is smaller than the value of the maximum position deviation in the evaluation standard (maximum position deviation Ld [mm] as the threshold value described above). If it is equal to or higher than the threshold value, the determination is not satisfied (S155: No), the score is deducted by 5 points in step S160, and the process proceeds to step S170 described later. If it is less than the threshold value, the determination is satisfied (S155: Yes), the score is increased by 5 points in step S165, and the process proceeds to step S170.

In step S170, based on the control information or operation information acquired by the information acquisition unit 70, the CPU 901 evaluates the power consumption corresponding to the acquired information by item acquired from the evaluation standard generation unit 71. It is determined whether or not it is smaller than the standard power consumption value (power consumption Pe [W] as the threshold value described above). If it is equal to or higher than the threshold value, the determination is not satisfied (S170: No), the score is deducted by 5 points in step S175, and the process proceeds to step S190 described later. If it is less than the threshold value, the determination is satisfied (S170: Yes), the score is increased by 5 points in step S180, and the process proceeds to step S190.

In step S90, the CPU 901 sets the initial score (50 points in the above example) in step S105, and the CPU 901 takes step S115 or step S120, step S130 or step S135, step S145 or step S150, step S160 or step S165. , The total score is calculated in a form that reflects the deduction or score increase in step S175 or step S180, and this is used as the final evaluation value. Then, this flow ends.

In FIG. 14, the case where the above-mentioned five items of overshoot amount, settling time, torque command amplitude, maximum position deviation, and power consumption are used as the evaluation criteria for each item has been described as an example, but the present invention is limited to this. I can't. Depending on the use and necessity of the operator, only a part of these five items may be used, or six or more itemized evaluation criteria including another item may be used.

Alternatively, in addition to the above method, for example, the evaluation unit 62, as shown in FIG. 15, as described above ( _{assuming that different weights Wi and j} are given in advance for each of the above evaluation items). The control parameters may be evaluated by calculating the total of the evaluation values of each of the determined evaluation items multiplied by the weight and using this as the final evaluation value. Further, an evaluation value is determined for each of the above evaluation items, the final evaluation value is determined by a known multivariate analysis using the evaluation value as a variable, and the above control parameters are evaluated. The evaluation unit 62 may perform the evaluation in consideration of the consumption degree information acquired by the consumption degree information acquisition unit 68.

Is it necessary for the determination unit 63 to adjust each control parameter set at that time based on the determination of the evaluation value (in other words, the evaluation of each control parameter) performed by the evaluation unit 62 as described above? Judgment is made, and the judgment result is generated as judgment information.

When the parameter specifying unit 64 determines that the control parameter needs to be adjusted based on the determination information generated by the determination unit 63, the parameter specifying unit 64 specifies the type of the control parameter that requires the adjustment, and the identification result thereof. Is generated as type information. That is, this type information is information indicating whether or not adjustment is necessary for each control parameter.

In particular, the evaluation unit 62 includes an abnormality presence / absence estimation unit 62A, a precursor estimation unit 62B, and an abnormality type estimation unit 62C.

Based on the evaluation criteria generated by the evaluation standard generation unit 71, the abnormality presence / absence estimation unit 62A has at least one of the control abnormality for the motor / drive machines 4 and 5 and the abnormality of the motor / drive machines 4 and 5. Estimates the presence or absence of one, and outputs the corresponding abnormality presence or absence estimation information. Specifically, for example, based on the above-mentioned evaluation criteria (in other words, based on the above-mentioned control abnormality information and operation abnormality information acquired by the prior information acquisition unit 65), according to the result of machine learning in the above-mentioned learning phase. , The range regarded as the above control abnormality / operation abnormality is extracted, or the pattern of control abnormality / operation abnormality is extracted, and based on the extracted range and pattern, the abnormality of the motor / drive machine 4 and 5 itself (so-called mechanical abnormality). Alternatively, it is estimated whether or not there is an abnormality in the control of the motors / drive machines 4 and 5.

The precursor estimation unit 62B is based on the evaluation criteria generated by the evaluation standard generation unit 71, and is a precursor of a presumed abnormality of the motors / drive machines 4 and 5 and a presumed motor / drive machine 4 At least one of the precursors of control abnormality for, and 5 is estimated. Examples of precursors of abnormalities of the motors / drive machines 4 and 5 include oscillation of the torque command, which is a precursor of mechanical vibration. For example, in the precursor estimation unit 62B, whether or not the torque command is oscillated based on the evaluation criteria (in other words, based on the control abnormality information and the operation abnormality information acquired by the advance information acquisition unit 65). To estimate.

Based on the evaluation criteria generated by the evaluation standard generation unit 71, the abnormality type estimation unit 62C has among the abnormalities of the motors / driving machines 4 and 5 and the abnormalities of control for the motors / driving machines 4 and 5. Estimate at least one type of anomaly. Examples of this type of abnormality include overshoot, overtime, mechanical vibration, excessive power consumption, excessive amplitude of the measured value of the accelerometer, vibration of the measured value of the torque sensor, and sound collector as described above. There is a frequency abnormality (or excessive dB) of the measured value of, and vibration of the torque command. For example, in the abnormality type estimation unit 62C, based on the evaluation criteria (in other words, based on the control abnormality information and the operation abnormality information acquired by the prior information acquisition unit 65), the abnormality type is the overshoot or the like. Estimate which one.

The output unit 67 includes a determination information output unit 67A, a type information output unit 67B, an abnormality presence / absence estimation information output unit 67C, a precursor estimation information output unit 67D, and an abnormality type estimation information output unit 67E.

The determination information output unit 67A outputs the determination information from the determination unit 63 to the outside of the evaluation device 6 (specifically, for example, the adjustment unit 32).

The type information output unit 67B outputs the type information from the parameter specifying unit 64 to the outside of the evaluation device 6 (specifically, for example, the adjusting unit 32).

The abnormality presence / absence estimation information output unit 67C outputs the abnormality presence / absence estimation information from the abnormality presence / absence estimation unit 62A to the outside of the evaluation device 6 (specifically, for example, the adjustment unit 32).

The precursor estimation information output unit 67D outputs the precursor estimation information from the precursor estimation unit 62B to the outside of the evaluation device 6 (specifically, for example, the adjustment unit 32).

The abnormality type estimation information output unit 67E outputs the abnormality type estimation information from the abnormality type estimation unit 62C to the outside of the evaluation device 6 (for details, for example, the adjustment unit 32). At that time, for example, in the case of the above-mentioned mechanical abnormality or oscillation, an evaluation that it is a very serious abnormality may be added, or the above-mentioned overshoot or settling time may be exceeded (or more of them are allowed). (It may be limited to a range), an evaluation that it is a relatively minor abnormality as compared with the above-mentioned serious abnormality may be added.

The determination information, the type information, the abnormality presence / absence estimation information, the precursor estimation information, and the abnormality type estimation information output from the output units 67A to 67E constitute the evaluation information. ..

Then, the adjusting unit 32 acquires the evaluation information output from each of the output units 67A to 67E in the parameter setting phase, and further optimizes the control parameters Kp, T, Kv accordingly. Output to the feedback control unit 31. Thereby, for example, the control parameter (specified by the above-mentioned type information) that needs to be adjusted in the above-mentioned determination information can be output to the feedback control unit 31 in a state of being updated to the optimum value. Further, for example, when it is estimated that there is a control abnormality or an operation abnormality in the above-mentioned abnormality presence / absence estimation information (it may be assumed that there is a precursor of the above-mentioned abnormality in the above-mentioned precursor estimation information), it is specified by the above-mentioned abnormality type estimation information. The control parameters can be output to the feedback control unit 31 in a state of being updated to the optimum values so that the abnormalities of the different types are eliminated (so that the abnormalities do not occur). In addition to being useful for readjustment of control parameters in the adjusting unit 32 of the motor control device 3 in this way, for example, it may be output to a display unit (not shown) provided in the upper control device 2 to notify the operator. In the case of the above-mentioned mechanical abnormality, the drive of the motor / drive machines 4 and 5 can be stopped via the host control device 2.

The processing and the like in the evaluation device 6 described above are not limited to the example of sharing these processing, and may be processed by, for example, a smaller number of processing units (for example, one processing unit). , It may be processed by a further subdivided processing unit. Further, the evaluation device 6 may be implemented in software by a program executed by the CPU 901 (see FIG. 16) described later, and a part or all of the evaluation device 6 may be an ASIC, an FPGA, other electric circuits, or the like (neuromorphic chip). Etc.) may be implemented in hardware by the actual device.

<Effect of this embodiment>
As described above, the machine control system 1 of the present embodiment uses the evaluation criteria generated by the evaluation standard generation unit 71, and the evaluation device 6 provides control information for the motors / drive machines 4 and 5 and the motor / drive machines. At least one of the 4 and 5 operation information is evaluated. As a result, unlike the above-mentioned conventional technology, even if the evaluation standard is not set, it is verified whether or not the current control contents for the motor / drive machine 4 and 5 are appropriate, and the control is optimized. be able to. As a result, if the control content is not appropriate, a warning is issued to the operator based on the evaluation information, or the control parameters Kp, T, Kv are readjusted based on the evaluation information, or the motor / drive machine 4, 5 It is possible to take appropriate measures such as stopping the operation.

Further, in the present embodiment, in particular, the evaluation standard generation unit 71 performs machine learning while performing labeling using at least one of the control abnormality information and the operation abnormality information, and generates the evaluation standard. As a result, more accurate and precise evaluation can be performed. It is also possible to derive a potentially existing abnormal state other than the typical abnormal state that can be assumed.

Further, in the present embodiment, in particular, based on the evaluation standard generated by the evaluation standard generation unit 71, the abnormality presence / absence estimation unit 62A determines that the control of the motor / drive machines 4 and 5 is abnormal and that the motor / drive machines 4 and 5 are abnormal. The presence or absence of at least one of them is determined, and the abnormality presence / absence estimation information output unit 67C outputs the abnormality presence / absence estimation information related to the determination. As a result, if something is wrong with the control of the motor / drive machines 4 and 5, or if something is wrong with the motor / drive machines 4 and 5 itself, that fact can be reliably estimated and dealt with. It is possible to output the abnormality presence / absence estimation information.

Further, in the present embodiment, in particular, based on the evaluation standard from the evaluation standard generation unit 71, the precursor estimation unit 62B predicts an abnormality of the motor / drive machine 4 and 5 and an abnormality of control for the motor / drive machine 4 and 5. Estimate at least one of the precursors of. As a result, the evaluation unit 62 effectively evaluates not only the abnormality of the motor / drive machine 4 and 5 and the control abnormality of the motor / drive machine 4 and 5 but also the precursors thereof, and the current control content. Can be verified if is correct.

Further, in the present embodiment, in particular, based on the above evaluation criteria, the abnormality type estimation unit 62C uses the type of at least one abnormality among the abnormality of the motor / drive machine 4 and 5 and the abnormality of control for the motor / drive machine 4 and 5. Is estimated, and the abnormality type estimation information regarding the estimation of the abnormality type is output by the abnormality type estimation information output unit 67E. As a result, it is clearly separated and shown whether the abnormalities occurring are abnormalities in control of the motors / drive machines 4 and 5 or abnormalities in the motors / drive machines 4 and 5 themselves (so-called mechanical abnormalities). It can be output in a mode.

Further, in the present embodiment, in particular, the wear degree information acquisition unit 68 acquires wear degree information related to the wear degree of the parts provided in the motor / drive machines 4 and 5, and the evaluation unit 62 obtains the control information and the operation. The control parameters Kp, T, and Kv are evaluated according to at least one of the information, the evaluation criteria, and the consumption degree information. As a result, even when the motors / drive machines 4 and 5 are continuously operated for a long period of time, the evaluation can be performed with higher accuracy in consideration of the aging deterioration including the degree of wear, and the control can be performed with higher accuracy. Can be optimized.

Further, in the present embodiment, in particular, the adjusting unit 32 adjusts the control parameters used for controlling the motor / driving machine 4 and 5 based on the learning contents in the machine learning, and the evaluation unit 62 adjusts the control parameters used for controlling the motor / driving machine 4 and 5. The control parameters Kp, T, and Kv are evaluated based on the evaluation of at least one of the control with respect to 5 and the operation of the motors / drive machines 4 and 5. By evaluating the control parameters by the evaluation unit, it is possible to (indirectly) evaluate whether or not the content of the machine learning in the adjustment unit that adjusts the control parameters by the machine learning method is correct. That is, it is possible to verify whether or not the learning content is appropriate, instead of continuing to apply the learning content of the adjustment unit regarding the control parameter unconditionally.

Further, in the present embodiment, in particular, based on the evaluation of the control parameters Kp, T, Kv by the evaluation unit 62, the determination unit 63 determines whether or not the control parameters Kp, T, Kv need to be adjusted. Judgment information related to the judgment is output by the judgment information output unit 67A. As a result, when it is determined that the current control content (in other words, the content learned by machine learning in the adjustment unit 32) is not appropriate and the control parameters Kp, T, Kv need to be further adjusted, the determination information is output. Since the determination information regarding the determination is output from the unit 67A, the adjustment unit 32 can adjust the control parameters Kp, T, and Kv based on the determination information. Based on this determination information, the operator can also adjust the control parameters Kp, T, Kv by an appropriate manual operation.

Further, in the present embodiment, particularly, when the determination unit 63 determines that the control parameters Kp, T, Kv need to be adjusted, the parameter specifying unit 64 needs to adjust the types of the control parameters Kp, T, Kv. Is specified, and the type information output unit 67B outputs type information regarding the types of control parameters Kp, T, and Kv that need to be adjusted. As a result, when it is determined that the control parameters Kp, T, Kv need to be adjusted, the control parameters Kp, T, Kv can be adjusted by specifying the control parameters Kp, T, Kv that need to be adjusted. It can be done easily.

Further, in the present embodiment, in particular, the itemized evaluation standard generation unit 71A uses a plurality of evaluation criteria used for at least one evaluation of the control of the motor / drive machines 4 and 5 and the operation of the motors / drive machines 4 and 5. Generate as an itemized evaluation standard for each evaluation item. Then, the evaluation unit 62 determines the evaluation value for each of a plurality of evaluation items based on the evaluation criteria for each item, and performs control and motor control for the motor / drive machine 4 and 5 by multivariate analysis using the evaluation value as a variable. -At least one of the operations of the drive machines 4 and 5 can be evaluated. As a result, the evaluation value can be clearly determined using the itemized evaluation criteria generated for each subdivided evaluation item, and the evaluation value can be used as an objective index value for reliable evaluation. Highly accurate evaluation can be performed. As a result, even if there are high-severity abnormalities such as vibrations of torque commands and torque sensor detection values, and low-severity abnormalities such as an increase in settling time and overshoot amount, the abnormalities can be mixed. It is possible to determine the evaluation value with high accuracy while taking into account the difference in severity.

Further, in the present embodiment, in particular, the itemized evaluation standard generation unit 71A uses a plurality of evaluation criteria used for at least one evaluation of the control of the motor / drive machines 4 and 5 and the operation of the motors / drive machines 4 and 5. Generate as an itemized evaluation standard for each evaluation item. Then, the evaluation unit 62 determines the evaluation value for each of the plurality of evaluation items based on the evaluation criteria for each item, and calculates the total of the evaluation values multiplied by the weighting to obtain the control information and the operation information. It is also possible to determine the evaluation value for at least one of. _{In this case, for example, a large weighting Wi, j} is given to a torque command having a high severity as an abnormality or a vibration occurrence of a torque sensor detection value, and a small weighting Wi, j is given to an increase in a low-severity settling time or an overshoot amount _{. By giving j} , it is possible to reliably determine the highly accurate evaluation value in consideration of the difference in severity.

<Hardware configuration example of evaluation device>
Next, with reference to FIG. 16, the abnormality information acquisition unit 61, the advance information acquisition unit 65, the information acquisition unit 70, and the consumption degree information acquisition unit 68, which are implemented in software by the program executed by the CPU 901 described above. A hardware configuration example of the evaluation device 6 that realizes processing by the evaluation standard generation unit 71, the evaluation unit 62, the determination unit 63, the parameter identification unit 64, the output unit 67, and the like will be described.

As shown in FIG. 16, the evaluation device 6 includes, for example, a CPU 901, a ROM 903, a RAM 905, a dedicated integrated circuit 907 constructed for a specific application such as an ASIC or an FPGA, an input device 913, and an output device 915. A recording device 917, a drive 919, a connection port 921, and a communication device 923. These configurations are connected so that signals can be transmitted to each other via the bus 909 and the input / output interface 911.

The program can be recorded in, for example, a ROM 903, a RAM 905, a recording device 917, or the like.

The program can also be temporarily or permanently recorded on, for example, a magnetic disk such as a flexible disk, an optical disk such as various CDs, MO disks, or DVDs, or a removable recording medium 925 such as a semiconductor memory. .. Such a recording medium 925 can also be provided as so-called package software. In this case, the program recorded on these recording media 925 may be read by the drive 919 and recorded on the recording device 917 via the input / output interface 911, the bus 909, or the like.

The program can also be recorded on, for example, a download site, another computer, another recording device, or the like (not shown). In this case, the program is transferred via a network NW such as LAN or the Internet, and the communication device 923 receives the program. Then, the program received by the communication device 923 may be recorded in the recording device 917 via the input / output interface 911, the bus 909, or the like.

Further, the program can be recorded in an appropriate externally connected device 927, for example. In this case, the program may be transferred via the appropriate connection port 921 and recorded in the recording device 917 via the input / output interface 911, the bus 909, or the like.

Then, the CPU 901 executes various processes according to the program recorded in the recording device 917, whereby the abnormality information acquisition unit 61, the prior information acquisition unit 65, the information acquisition unit 70, the consumption degree information acquisition unit 68, Processing by the evaluation standard generation unit 71, the evaluation unit 62, the determination unit 63, the parameter identification unit 64, the output unit 67, and the like is realized. At this time, for example, the CPU 901 may directly read the program from the recording device 917 and execute it, or may execute it after loading it into the RAM 905 once. Further, for example, when the CPU 901 receives the program via the communication device 923, the drive 919, or the connection port 921, the CPU 901 may directly execute the received program without recording it in the recording device 917.

Further, the CPU 901 may perform various processes based on signals and information input from an input device 913 such as a mouse, keyboard, microphone (not shown), if necessary.

Then, the CPU 901 may output the result of executing the above processing from an output device 915 such as a display device or an audio output device, and the CPU 901 may connect the processing result to the communication device 923 or the communication device 923 as needed. It may be transmitted via the port 921, or may be recorded on the recording device 917 or the recording medium 925.

<Modification example>
Further, as described above, as described above, the evaluation standard generation unit 71 of the evaluation device 6 of the machine control system 1 is provided with the motor / drive machine 4 in the machine control system 1 in the learning phase before the operation phase. A case where machine learning is performed based on the above-mentioned pre-control information (the above-mentioned torque command in the above-mentioned example), the pre-operation information (the above-mentioned detection position in the above-mentioned example), the control abnormality information, and the operation abnormality information related to 5 will be described as an example. However, it is not limited to this.

That is, before the execution of the operation phase, the prior information acquisition unit 65 provides information on the control of industrial equipment (provided outside the machine control system 1) other than the motors / drive machines 4 and 5. At least one of the other device pre-control information and the other device pre-operation information which is information on the operation of the other industrial device is acquired, and further, the abnormality information acquisition unit 61 obtains the other industrial device. At least one of the control abnormality information indicating the control abnormality and the operation abnormality information indicating the operation abnormality of the other industrial equipment may be acquired. At this time, the abnormality information acquisition unit 61 uses other device control abnormality information related to the other industrial equipment and other equipment operation abnormality related to the other industrial equipment, which are used as teacher data of the evaluation standard generation unit learning data set. Get information (or one of them). Similar to the above, the other device control abnormality information and the other device operation abnormality information are information accompanying the above-mentioned state quantity data related to the other industrial equipment included in the above-mentioned evaluation standard generation unit learning data set in this case, for example. It is input to the evaluation device 6 based on the appropriate operation input of the operator. The other device control abnormality information indicates that the control for the other industrial equipment is abnormal, and the other equipment operation abnormality information indicates that the operation of the other work equipment is abnormal. In this case, the other device control abnormality information and the other device operation abnormality information are output to the evaluation unit 62 and the evaluation standard generation unit 71.

Then, the evaluation standard generation unit 71 performs machine learning in the learning phase, and the other device advance control information and the other device advance operation information acquired by the advance information acquisition unit 65, and the abnormality information acquisition unit 61 Based on at least one of the acquired other device control abnormality information and the other device operation abnormality information, an evaluation standard used by the evaluation unit 62 for evaluation in the operation phase is generated. Then, in the operation phase, the evaluation unit 62 relates to the motors / drive machines 4 and 5 of the machine control system 1 acquired by the information acquisition unit 70 in accordance with the evaluation criteria generated as described above. Based on the control information and the above operation information, the control parameters set at that time are evaluated, and the corresponding evaluation information is generated. The evaluation information generated in this way is output from the output unit 67 to the adjustment unit 32 as described above.

In this case as well, the same effect as described above can be obtained. That is, using at least one of the control information and the operation information of the other industrial equipment and the evaluation standard generated by the evaluation standard generation unit 71, the control and the motor / drive machine 4 and 5 for the motor / drive machine 4 and 5 are used. At least one of the operations of is evaluated, and the corresponding evaluation information is output. As a result, unlike the above-mentioned conventional technology, even when the evaluation standard is not set, it is verified whether or not the current control contents for the motor / drive machine 4 and 5 are appropriate, and the control is optimized. Can be planned. As a result, if the control content is not appropriate, it is possible to take appropriate measures such as issuing a warning to the operator, readjusting the control content by the control device, stopping the industrial equipment, and the like.

Further, in the above example, in particular, by performing labeling using at least one of the other device control abnormality information and the other device operation abnormality information related to the other industrial equipment to generate an evaluation standard, more accuracy is achieved. Highly precise evaluation can be performed. It is also possible to derive a potentially existing abnormal state other than the typical abnormal state that can be assumed.

Further, in the above description, when there is a description such as "vertical", "parallel", "plane", etc., the description does not have a strict meaning. That is, these "vertical", "parallel", and "planar" mean "substantially vertical", "substantially parallel", and "substantially flat", with design and manufacturing tolerances and errors allowed. ..

Further, in the above description, when there is a description such as "same", "same", "equal", "different", etc. in the external dimensions, size, shape, position, etc., the description is not a strict meaning. That is, those "same", "equal", and "different" are tolerant of design and manufacturing tolerances and errors, and are "substantially the same", "substantially the same", "substantially equal", and "substantially equal". It means "different".

In addition to the above, the methods according to the above-described embodiment and each modification may be appropriately combined and used. In addition, although not illustrated one by one, the above-described embodiment and each modification are implemented with various modifications within a range that does not deviate from the purpose.

1 Machine control system 2 High-level control device 3 Motor control device 4 Rotary motor (industrial equipment)
5 Drive machinery (industrial equipment)
6 Evaluation device 31 Feedback control unit 32 Adjustment unit 61 Abnormality information acquisition unit 62 Evaluation unit 62A Abnormality presence / absence estimation unit 62B Precursor estimation unit 62C Abnormality type estimation unit 63 Judgment unit 64 Parameter identification unit 65 Prior information acquisition unit 66 Abnormality identification unit 67 Output Part 67A Judgment information output part 67B Type information output part 67C Abnormality presence / absence estimation information output part 67D Precursor estimation information output part 67E Abnormal type estimation information output part 68 Consumability information acquisition part 70 Information acquisition part 71 Evaluation standard generation part 71A Itemized evaluation Reference generator DB database

Claims (19)

A system including a control device for controlling an industrial device and an evaluation device for controlling the industrial device and evaluating at least one of the operations of the industrial device.
The evaluation device is
An information acquisition unit that acquires at least one of control information that is information related to control of the industrial equipment and operation information that is information related to the operation of the industrial equipment.
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Preliminary information acquisition department to acquire and
An evaluation standard generation unit that generates an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment based on at least one of the pre-control information and the pre-operation information. When,
An evaluation unit that performs control of the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
An output unit that outputs evaluation information, which is information related to the evaluation ,
Control abnormality information indicating whether the control for the industrial equipment before the control for the industrial equipment is abnormal and the operation abnormality indicating whether the operation of the industrial equipment before the operation of the industrial equipment is abnormal. Anomalous information acquisition unit that acquires at least one of the information,
Equipped with a,
The evaluation standard generation unit
A system characterized in that an evaluation criterion is generated based on at least one of the pre-control information, the control abnormality information, the pre-operation information, and the operation abnormality information. The evaluation unit of the evaluation device
Further, an abnormality presence / absence estimation unit for estimating the presence / absence of a control abnormality for the industrial equipment and at least one abnormality of the industrial equipment based on the evaluation criteria is provided.
The output unit
The system according to claim 1 , further comprising an abnormality presence / absence estimation information output unit that outputs abnormality presence / absence estimation information which is information regarding the presence / absence of abnormality. The evaluation unit of the evaluation device
Based on the evaluation criteria, it has a precursor estimation unit that estimates at least one precursor of an abnormality of the industrial equipment and a precursor of a control abnormality for the industrial equipment.
The output unit
The system according to claim 1 or 2 , further comprising a precursor estimation information output unit that outputs precursor estimation information that is information relating to the precursor estimation. The evaluation unit of the evaluation device
It has an abnormality type estimation unit that estimates the type of at least one abnormality of the abnormality of the industrial equipment and the abnormality of control for the industrial equipment based on the evaluation criteria.
The output unit
The system according to any one of claims 1 to 3 , further comprising an abnormality type estimation information output unit that outputs abnormality type estimation information that is information related to the estimation of the abnormality type. The evaluation device is
It is provided with a wear degree information acquisition unit that acquires wear degree information related to the wear degree of parts provided in the industrial equipment.
The evaluation unit
Based on at least one of the control information and the operation information, the evaluation standard, and the consumption degree information, at least one of the control of the industrial equipment and the operation of the industrial equipment is evaluated. The system according to any one of claims 1 to 4 . A system including a control device for controlling an industrial device and an evaluation device for controlling the industrial device and evaluating at least one of the operations of the industrial device.
The evaluation device is
An information acquisition unit that acquires at least one of control information that is information related to control of the industrial equipment and operation information that is information related to the operation of the industrial equipment.
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Preliminary information acquisition department to acquire and
An evaluation standard generation unit that generates an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment based on at least one of the pre-control information and the pre-operation information. When,
An evaluation unit that performs control of the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
It is provided with an output unit that outputs evaluation information, which is information related to the evaluation.
The evaluation standard generation unit
Based on at least one of the pre-control information and the pre-operation information, a plurality of predetermined evaluations are performed on the evaluation criteria used for the control of the industrial equipment and the evaluation of at least one of the operations of the industrial equipment. It has an itemized evaluation standard generator that generates each item as an itemized evaluation standard.
The evaluation unit
An evaluation value is determined for each of the plurality of evaluation items based on the itemized evaluation criteria, and at least one of control over the industrial equipment and operation of the industrial equipment is performed by multivariate analysis using the evaluation value as a variable. It features and be Resid stems to make the evaluation. The control device is
It is equipped with an adjustment unit that adjusts the control parameters used for controlling the industrial equipment based on the learning content in machine learning.
The evaluation unit
The system according to any one of claims 1 to 6 , wherein the control parameters are evaluated based on the evaluation of at least one of the control of the industrial equipment and the operation of the industrial equipment. The evaluation device is
Further, a determination unit for determining whether or not adjustment of the control parameter is necessary based on the evaluation of the control parameter is provided.
The output unit
The system according to claim 7, further comprising a determination information output unit that outputs determination information that is information relating to determination of whether or not adjustment of the control parameter is necessary. The evaluation device is
When it is determined in the determination that the control parameter needs to be adjusted, a parameter specifying unit for specifying the type of the control parameter that needs to be adjusted is further provided.
The output unit
The system according to claim 8, further comprising a type information output unit that outputs type information that is information on the types of control parameters that need to be adjusted. An information acquisition unit that acquires at least one of control information that is information related to control of an industrial device and operation information that is information related to the operation of the industrial device.
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Preliminary information acquisition department to acquire and
An evaluation standard generation unit that generates an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment based on at least one of the pre-control information and the pre-operation information. When,
An evaluation unit that performs control of the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
An output unit that outputs evaluation information, which is information related to the evaluation ,
Control abnormality information indicating whether the control for the industrial equipment before the control for the industrial equipment is abnormal and the operation abnormality indicating whether the operation of the industrial equipment before the operation of the industrial equipment is abnormal. Anomalous information acquisition unit that acquires at least one of the information,
Equipped with a,
The evaluation standard generation unit
An evaluation device for generating the evaluation criterion based on at least one of the pre-control information, the control abnormality information, the pre-operation information, and the operation abnormality information. The evaluation unit
Based on the evaluation criteria, it has an abnormality presence / absence estimation unit that estimates the presence / absence of at least one abnormality of the industrial equipment abnormality and the control abnormality for the industrial equipment.
The output unit
The evaluation device according to claim 10, further comprising an abnormality presence / absence estimation information output unit that outputs abnormality presence / absence estimation information which is information regarding the presence / absence of abnormality. The evaluation unit
Based on the evaluation criteria, it has a precursor estimation unit that estimates at least one precursor of an abnormality of the industrial equipment and a precursor of a control abnormality for the industrial equipment.
The output unit
The evaluation device according to claim 10 or 11 , wherein the evaluation device includes a precursor estimation information output unit that outputs precursor estimation information that is information related to the precursor estimation. The evaluation unit
It has an abnormality type estimation unit that estimates the type of at least one abnormality of the abnormality of the industrial equipment and the abnormality of control for the industrial equipment based on the evaluation criteria.
The output unit
The evaluation device according to any one of claims 10 to 12 , further comprising an abnormality type estimation information output unit that outputs abnormality type estimation information that is information related to the estimation of the abnormality type. It is provided with a wear degree information acquisition unit that acquires wear degree information related to the wear degree of parts provided in the industrial equipment.
The evaluation unit
Based on at least one of the control information and the operation information, the evaluation standard, and the consumption degree information, at least one of the control of the industrial equipment and the operation of the industrial equipment is evaluated. The evaluation device according to any one of claims 10 to 13. An information acquisition unit that acquires at least one of control information that is information related to control of an industrial device and operation information that is information related to the operation of the industrial device.
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Preliminary information acquisition department to acquire and
An evaluation standard generation unit that generates an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment based on at least one of the pre-control information and the pre-operation information. When,
An evaluation unit that performs control of the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
An output unit that outputs evaluation information, which is information related to the evaluation,
With
The evaluation standard generation unit
Based on at least one of the pre-control information and the pre-operation information, a plurality of predetermined evaluations are performed on the evaluation criteria used for the control of the industrial equipment and the evaluation of at least one of the operations of the industrial equipment. It has an itemized evaluation standard generator that generates each item as an itemized evaluation standard.
The evaluation unit
An evaluation value is determined for each of the plurality of evaluation items based on the itemized evaluation criteria, and at least one of control over the industrial equipment and operation of the industrial equipment is performed by multivariate analysis using the evaluation value as a variable. it characterized by performing the evaluation evaluation apparatus. An information acquisition unit that acquires at least one of control information that is information related to control of an industrial device and operation information that is information related to the operation of the industrial device.
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. Preliminary information acquisition department to acquire and
An evaluation standard generation unit that generates an evaluation standard used for controlling the industrial equipment and evaluating at least one of the operations of the industrial equipment based on at least one of the pre-control information and the pre-operation information. When,
An evaluation unit that performs control of the industrial equipment and evaluation of at least one of the operations of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
An output unit that outputs evaluation information, which is information related to the evaluation,
With
The evaluation standard generation unit
Based on at least one of the pre-control information and the pre-operation information, a plurality of predetermined evaluations are performed on the evaluation criteria used for the control of the industrial equipment and the evaluation of at least one of the operations of the industrial equipment. It has an itemized evaluation standard generator that generates each item as an itemized evaluation standard.
The plurality of evaluation items are
Each evaluation item is given different weights,
The evaluation unit
By determining the evaluation value for each of the plurality of evaluation items based on the itemized evaluation criteria and calculating the total of the evaluation values multiplied by the weighting, the control over the industrial equipment and the operation of the industrial equipment are performed. evaluation device you and performing at least one rating. An information acquisition unit that acquires at least one of control information that is information related to control of an industrial device and operation information that is information related to the operation of the industrial device.
Information on pre-control of other equipment, which is information on control of other industrial equipment other than the industrial equipment prior to control on the industrial equipment, and information on the operation of the other industrial equipment prior to the operation of the industrial equipment. The advance information acquisition unit that acquires at least one of the other device advance operation information,
An evaluation standard that generates an evaluation standard used for controlling the industrial device and evaluating at least one of the operations of the industrial device based on at least one of the other device pre-control information and the other device pre-operation information. Generation part and
An evaluation unit that evaluates at least one of control over the industrial equipment and operation of the industrial equipment based on at least one of the control information and the operation information and the evaluation criteria.
An evaluation device including an output unit that outputs evaluation information, which is information related to the evaluation. Other device control abnormality information indicating whether the control for the other industrial device prior to the control for the industrial device is abnormal, and the operation of the other industrial device prior to the operation of the industrial device are abnormal. Further provided with an abnormality information acquisition unit for acquiring at least one of other device operation abnormality information indicating whether or not
The evaluation standard generation unit
A claim characterized in that the evaluation criterion is generated based on at least one of the other pre-control information, the other device control abnormality information, the other pre-operation information, and the other device operation abnormality information. Item 17. The evaluation device according to item 17. This is an evaluation method for evaluation equipment that evaluates industrial equipment.
Acquiring at least one of control information which is information about control for the industrial equipment and operation information which is information about operation of the industrial equipment, and
At least one of the pre-control information which is the information about the control for the industrial equipment before the control for the industrial equipment and the pre-operation information which is the information about the operation of the industrial equipment before the operation of the industrial equipment. To get and
Based on at least one of the pre-control information and the pre-operation information, the evaluation criteria used for the control of the industrial equipment and the evaluation of at least one of the operations of the industrial equipment are generated.
Based on at least one of the control information and the operation information and the evaluation criteria, at least one of the control for the industrial equipment and the operation of the industrial equipment is evaluated.
Outputting evaluation information, which is information related to the evaluation,
Control abnormality information indicating whether the control for the industrial equipment before the control for the industrial equipment is abnormal and the operation abnormality indicating whether the operation of the industrial equipment before the operation of the industrial equipment is abnormal. To get at least one of the information and
The execution,
Generating the evaluation criteria
It is characterized in that the evaluation criterion is generated based on at least one of the pre-control information, the control abnormality information, the pre-operation information, and the operation abnormality information. Evaluation methods.

Images