JP2022145537A - Determination device, determination method, program, and processing system - Google Patents

Abstract

To accurately determine the rotational state of a tool.SOLUTION: A diagnostic device 100 comprises: a receiving unit that receives detection information on a time-varying physical quantity generated when a tool 223 rotates which is an example of a rotating body removably attached to a rotation main shaft 221 being an example of a rotation shaft and rotation angle information when the tool 223 rotates; and a determination unit 102 that determines the rotational state of the tool 223 based on the detection information and the rotation angle information.SELECTED DRAWING: Figure 1

Description

The present invention relates to a determination device, determination method, program, and machining system.

In patent document 1, when checking the imbalance of a tool mounted on the spindle of a machine tool, when a standard tool is mounted on the spindle and when a command tool is mounted on the spindle, the spindle is rotated at a predetermined number of revolutions. and measure the vibration amplitude of the spindle for a predetermined period of time to obtain the average value of the peak values. A method for checking tool unbalance is described such that if less or equal, there is no unbalance.

Patent Document 2 discloses a spindle that can rotate with a workpiece or tool attached, a vibration sensor that measures vibration of the spindle, a controller that controls the rotation of the spindle, and a spindle with the workpiece or tool attached. time-domain data of the vibration of the spindle measured by the vibration sensor during rotation of the spindle to obtain frequency-domain data; a detection unit for detecting vibration accompanying rotation of the spindle based on the intensity of a predetermined natural frequency of the spindle or the intensity of a predetermined frequency band including the predetermined natural frequency; A machine tool is described that can effectively detect anomalies in the machine.

Japanese Patent Publication No. 8-32392 JP 2020-55052 A

An object of the present invention is to accurately determine the rotation state of a rotating body.

A determination device according to the present invention includes a receiving unit that receives detection information of a time-varying physical quantity emitted when a rotating body that is attachable to and detachable from a rotating shaft rotates, and rotation angle information when the rotating body rotates. and a determination unit that determines the rotation state of the rotating body based on the detection information and the rotation angle information.

ADVANTAGE OF THE INVENTION According to this invention, the rotation state of a rotating body can be accurately determined.

1 is a block diagram showing a configuration example of a processing system to which a diagnostic device according to an embodiment of the invention is applied; FIG. It is a block diagram which shows an example of the hardware constitutions of the processing apparatus concerning this embodiment. It is a block diagram which shows an example of the hardware constitutions of the diagnostic apparatus concerning this embodiment. It is a block diagram showing an example of functional composition of a diagnosis device concerning this embodiment. It is a figure which shows the example of the rotation angle sensor concerning this embodiment. It is a figure which shows the rotation main shaft concerning this embodiment. It is a figure which shows the detection information and rotation angle information which the receiving part concerning this embodiment received. It is a flowchart which shows an example of the flow of a diagnostic process in the diagnostic apparatus concerning this embodiment. It is a flowchart which shows an example of the flow of model generation processing by the diagnostic apparatus concerning this embodiment. It is the figure which plotted the complex number obtained by Fourier-transforming to the detection information concerning this embodiment on the complex plane. It is the figure which plotted the absolute value obtained by Fourier-transforming to the detection information concerning a comparative example.

Embodiments of a determination device, a determination method, a program, and a machining system will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a block diagram showing a configuration example of a machining system to which a diagnosis device, which is an example of a determination device according to this embodiment, is applied. As shown in FIG. 1, the processing system according to this embodiment includes a processing device 200 and a diagnostic device 100, which is an example of a determination device.

The processing device 200 and the diagnostic device 100 may be connected in any connection form. For example, the processing apparatus 200 and the diagnostic apparatus 100 are connected by a dedicated connection line, a wired network such as a wired LAN (Local Area Network), a wireless network, or the like.

The processing device 200 includes a machine control unit 201, a tool changer 202, a display unit 203, a storage unit 204, a communication control unit 205, a numerical control unit 206, a tool information input unit 207, an alarm unit 208, an input/output unit 209, and a machine tool. 220 and the like.

The machine tool 220 has a Z-axis stage 226 that can move vertically in FIG. The Z-axis stage 226 has a rotating main shaft 221 that is an example of a rotating shaft that configures the processing device 200 . A tool holder 222 that holds a tool 223 is attached to the rotating spindle 221 . The machine tool 220 includes an XY-axis stage 225 that is movable in two axial directions in a plane orthogonal to the Z-axis stage 226 and that includes a driving unit, below the rotation main shaft 221 . The XY-axis stage 225 holds a workpiece 224 . The rotation main shaft 221 is an example of a rotating shaft, and the tool 223 is an example of a rotating body that can be attached to and detached from the rotating shaft.

The numerical control unit 206 executes processing by the processing device 200 by numerical control. For example, the numerical control unit 206 reads a machining program from the input/output unit 209, generates and outputs numerical control data for controlling the rotation of the main axis and the position of each axis stage. Further, the machining program describes the storage number of the tool changer 202, and the numerical control unit 206 performs tool change according to the description.

Numerical control section 206 outputs the context information to communication control section 205 . The context information is information that defines the operation of the tool 223 of the processing apparatus 200 , and is information that is defined for each type of operation of the tool 223 . In this embodiment, the context information includes, for example, tool information identifying the tool 223, rotation information of the rotation main shaft 221 (for example, the rotation speed of the rotation main shaft 221), Z-axis stage 226, XY-axis stage, and so on. H.225 movement information (moving speed, information during movement), etc. are included.

The tool information includes at least the types of tools such as drills, reamers, and end mills, and the number of cutting edges. This tool information is input by the operator from the tool information input section 207 according to the information displayed on the display section 203 . Alternatively, tool information can be obtained by reading a list file of the tool information from the input/output unit 209 or by inputting information from an external computer (not shown) via the communication control unit 205 . Also, the tool information may be stored in the storage unit 204 so that it can be referenced from the machining program.

Numerical control unit 206 , for example, transmits context information defining the current operation of tool 223 to diagnostic device 100 via communication control unit 205 . When machining the workpiece 224 according to the machining program, the numerical control unit 206 controls the type of the tool 223, the positions of the Z-axis stage 226 and the XY-axis stage 225, the rotation speed of the rotation main shaft 221, etc., according to the machining process. Control. Numerical control unit 206 transmits context information corresponding to a predetermined operation among context information to diagnostic apparatus 100 via communication control unit 205 . Here, the predetermined motion is a preset motion among the motions of the tool 223 . In this embodiment, every time the type of operation of the tool 223 is changed, the numerical control unit 206 sequentially transmits context information corresponding to the changed type of operation to the diagnostic device 100 via the communication control unit 205. .

A communication control unit 205 (an example of a transmission unit) controls communication with an external device such as the diagnostic device 100 . For example, the communication control unit 205 transmits context information corresponding to the current operation of the tool 223 to the diagnostic device 100 .

The physical quantity information detection unit 227 has a sensor that detects, as an analog signal, a physical quantity that is emitted when the tool 223 rotates while the tool 223 is performing a machining operation on the workpiece 224 and changes with time. Further, the physical quantity information detection unit 227 has a function of appropriately amplifying the analog signal detected by the sensor, cutting an arbitrary frequency region, and converting it into a digital signal. The physical quantity information detection unit 227 also functions as an example of a transmission unit that transmits the digital signal as detection information to the diagnostic device 100 . The type of sensor possessed by the physical quantity information detection unit 227 and the physical quantity to be detected may be of any type. For example, the sensor included in the physical quantity information detection unit 227 is a microphone, an acceleration sensor, an AE (acoustic emission) sensor, or the like, and outputs acoustic data, acceleration data, or data indicating an AE wave, respectively, as detection information. . Further, the number of physical quantity information detection units 227 included in the diagnostic apparatus 100 is arbitrary, and may be plural. For example, diagnostic device 100 may include multiple sensors that detect different physical quantities.

In FIG. 1 , the physical quantity information detection unit 227 has a sensor attached to the side surface of the structure holding the rotation main shaft 221 . A sensor included in the physical quantity information detection unit 227 includes an acceleration sensor. Then, when the processing by the processing device 200 is started, the physical quantity information detection unit 227 detects acceleration of vibration generated by the rotation of the rotation main shaft 221 . In the processing apparatus 200, when the tool 223 and the workpiece 224 come into contact with each other and actual cutting is started, a cutting force is generated, which becomes an excitation force to vibrate the tool 223 and the workpiece 224. Vibrations propagate to each other. The physical quantity information detection unit 227 transmits the vibration acceleration and the like to the diagnostic apparatus 100 as detection information.

Further, in this embodiment, when the machining program is started, first, the rotation main shaft 221 is rotated and idled until the number of revolutions reaches the set value. It moves toward the workpiece 224 and contacts it to start machining. The physical quantity information detection unit 227 transmits the vibration signal acquired during idling to the communication control unit 101 of the diagnostic device 100 .

For example, if the cutting edge of the tool 223 is broken, the cutting edge of the tool 223 is chipped, or the like occurs during machining, the cutting force that was uniform for each cutting edge during normal machining becomes unequal. changes the vibration that is applied. Alternatively, in the processing apparatus 200, if chips are mixed between the tool holder 222 and the rotation main shaft 221 when the tool 223 is replaced, the cutting edge at the tip of the tool 223 whirles with respect to the rotation shaft. As a result, the amount of cutting per cutting edge of the tool 223 becomes uneven, and vibration changes occur due to the uneven cutting force, similar to when the cutting edge is damaged.

The diagnostic device 100 receives this vibration detection information through the communication control unit 101 . In addition, the communication control unit 101 controls communication with the processing device 200 and receives context information from the processing device 200 . The determination unit 102 refers to the context information and the detection information to determine whether the processing state of the processing device 200 is normal. Further, when the diagnostic device 100 diagnoses that the processing state of the processing device 200 is abnormal, the diagnostic device 100 transmits alert information to the processing device via the communication control unit 101 . When the communication control unit 205 receives the alert information, the processing apparatus 200 displays the alert information on the display unit 203 and operates the alarm unit 208 . The alarm unit 208 is a patrol lamp, buzzer, speaker, or the like. Further, the machine control unit 201 can interrupt the operation of the processing device 200 according to the processing program and stop the processing of the processing device 200 .

A spindle rotation information acquisition unit 228 is attached to the rotary spindle 221, and the spindle rotation information acquisition unit 228 transmits the acquired rotation angle information when the tool 223 rotates to the communication control unit 101 of the diagnostic apparatus 100. do.

FIG. 2 is a block diagram showing an example of the hardware configuration of the processing apparatus according to this embodiment. As shown in FIG. 2, the processing apparatus 200 according to the present embodiment includes a CPU (Central Processing Unit) 251, a ROM (Read Only Memory) 252, a RAM (Random Access Memory) 253, and a communication I/F ( Interface) 254 , drive control circuit 255 , motor 256 , input/output I/F 257 , input device 258 , and display 259 are connected by bus 260 .

The CPU 251 controls the processing apparatus 200 as a whole. The CPU 251 controls the overall operation of the processing apparatus 200 and implements various functions of the processing apparatus 200 by executing programs stored in the ROM 252 or the like using the RAM 253 as a work area.

Communication I/F 254 is an interface for communicating with an external device such as diagnostic device 100 . The drive control circuit 255 is a circuit that controls driving of the motor 256 . Each of the rotation main shaft 221, the Z-axis stage 226, and the XY-axis stage 225 has a driving section such as a motor 256. A sensor 270 included in the physical quantity information detection unit 227 is attached to the processing device 200 and converts a physical quantity that changes according to the operation of the processing device 200 into an electrical signal. The signal conversion circuit 271 amplifies the electrical signal output from the sensor 270 to a desired magnitude, cuts the noise component contained in the electrical signal, and converts it into a digital signal. Then, the signal conversion circuit 271 outputs the digital signal to the diagnostic device 100 as detection information. That is, the sensor 270 and the signal conversion circuit 271 correspond to the physical quantity information detection section 227 shown in FIG. 1, for example.

The numerical control unit 206 and the communication control unit 205 shown in FIG. 1 may be realized by executing a program stored in the ROM 252 by the CPU 251, that is, by software, or by hardware such as an IC (Integrated Circuit). Alternatively, software and hardware may be used together.

The rotation angle sensor 280 is attached to the processing apparatus 200 and converts a physical quantity that changes according to the rotation angle of the rotation main shaft 221 into an electrical signal. The signal conversion circuit 281 amplifies the electrical signal output from the rotation angle sensor 280 to a desired magnitude, cuts the noise component contained in the electrical signal, and converts it into a digital signal. Then, the signal conversion circuit 281 outputs the digital signal to the diagnostic device 100 as detection information. That is, the rotation angle sensor 280 and the signal conversion circuit 281 correspond to, for example, the spindle rotation information acquisition section 228 shown in FIG.

FIG. 3 is a block diagram showing an example of the hardware configuration of the diagnostic device according to this embodiment. As shown in FIG. 3, the diagnostic device 100 according to the present embodiment includes a CPU 151, a ROM 152, a RAM 153, a communication I/F 154, an auxiliary storage device 155, and an input/output I/F 157 via a bus 160. It has a connected configuration.

The CPU 151 controls the diagnostic device 100 as a whole. The CPU 151 executes a program stored in the ROM 152 or the like using the RAM 153 as a work area, for example, thereby controlling the overall operation of the diagnostic apparatus 100 and realizing the diagnostic function of the processing apparatus 200 .

Communication I/F 154 is an interface for communicating with an external device such as processing device 200 . The auxiliary storage device 155 stores various types of information such as setting information of the diagnostic device 100 , context information received from the processing device 200 , and detection information output from the physical quantity information detection section 227 . Further, the auxiliary storage device 155 stores various calculation results used for determining whether or not the processing state of the processing device 200 is normal. The auxiliary storage device 155 is composed of non-volatile storage means such as HDD (Hard Disk Drive), EEPROM (Electrically Erasable Programmable Read-Only Memory) or SSD (Solid State Drive).

The input/output I/F 157 sequentially displays detection information input from the physical quantity information detection unit 227 on the display 159 and displays determination results by the determination unit 102 . Also, the input/output I/F 157 receives settings required for diagnosis of the processing apparatus 200 input by the user while looking at the display 159 via an input device 158 such as a keyboard and a mouse.

FIG. 4 is a block diagram showing an example of the functional configuration of the diagnostic device according to this embodiment. In addition to the communication control unit 101 and the determination unit 102 described above, the diagnostic apparatus 100 according to the present embodiment includes a storage unit 103, a generation unit 104, a display control unit 105, a display unit 106, an input unit 107, A feature extraction unit 110 , a data extraction unit 112 , and an analysis unit 113 are provided.

The storage unit 103 stores various information necessary for the diagnostic function of the diagnostic device 100 . The storage unit 103 is implemented by, for example, the RAM 153 and the auxiliary storage device 155 shown in FIG. For example, the storage unit 103 stores one or more models (hereinafter referred to as learning models) used for determining whether the machining state of the machining apparatus 200 is abnormal. Here, the learning model is generated by learning, for example, using detection information output from the physical quantity information detection unit 227 when the processing state of the processing device 200 is normal. The learning method of the learning model and the format of the learning model may be any method and format. For example, the learning model and the learning method of the learning model include GMM (Gaussian Mixture Model), HMM (Hidden Markov Model), learning models such as One Class SVM and Two Class SVM, and model learning methods corresponding to the learning model. can be applied. For simplicity, a one-dimensional scalar value may be used as an index value and determination based on simple threshold comparison may be used.

In addition, the storage unit 103 may store the normal processing state and the abnormal processing state of the processing apparatus 200 as rules and store them as a learning model. For example, the rule stored as a learning model in the storage unit 103 is such that the first 10 times of machining after a new tool 223 is attached and machining is started is a learning period for determining rules for diagnosis. A rule stored as a learning model in the storage unit 103 may be determined in advance separately from actual processing, and the determined rule may be stored in the storage unit 103 as a learning model.

In this embodiment, the learning model stored in storage unit 103 is generated for each piece of context information. The storage unit 103 stores, for example, the context information and the learning model corresponding to the context information in association with each other. In this embodiment, the learning model is generated for each combination of the tool type, the automatic changer number of the machine tool, and the spindle speed at the time of model generation, and stored in the storage unit 103 .

Returning to FIG. 4, the communication control unit 101 includes a receiving unit 101a and a transmitting unit 101b. The receiving unit 101a receives various information transmitted from the processing device 200 or an external device. For example, the receiving unit 101a receives context information corresponding to the current operation of the tool 233, detection information output from the physical quantity information detection unit 227, and rotation angle information output from the spindle rotation information acquisition unit 228. do. The transmission unit 101b transmits various types of information to the processing device 200. FIG.

For example, the receiving unit 101a receives, as context information corresponding to the current operation of the machine tool 220, the number of the installed tool 223, the setting value of the spindle rotation speed, the stage drive signal of the machine tool 220, and the rotation of the spindle. Can receive start signal and spindle stop start signal

The feature extraction unit 110 generates a learning model and extracts feature information (feature amount) used in determination by the determination unit 102 from detection information. Here, the feature information may be any information that indicates the feature of the detection information. For example, when the detection information is acoustic data collected by a microphone, the feature extraction unit 110 extracts feature amounts such as energy, frequency spectrum, and MFCC (Mel-Frequency Cepstrum Coefficients) from the detection information. Extract.

The generation unit 104 generates a learning model for determining a normal processing state of the processing device 200 by learning using feature information extracted from detection information when the processing device 200 is in a normal processing state. However, when the learning model is generated by an external device, the diagnosis device 100 does not have to include the generation unit 104 . Specifically, the learning model may be generated by an external device, and the learning model generated by the external device may be received by the receiving unit 101 a and stored in the storage unit 103 . When context information for which a learning model is not defined and detection information corresponding to the context information are input, the generation unit 104 uses feature information extracted from the detection information to generate a pattern corresponding to the context information. A learning model may be generated.

The determination unit 102 determines the processing state of the processing device 200 using the feature information extracted from the detection information. Specifically, the rotational state of the tool 223 is determined based on the detection information and the rotation angle information. In this embodiment, the determination unit 102 determines the processing state of the processing device 200 using the feature information and the learning model corresponding to the context information. For example, the determination unit 102 requests the feature extraction unit 110 to extract feature information from the detection information. The determination unit 102 calculates the likelihood that the feature information extracted from the detection information is normal, using the corresponding learning model. Determining section 102 compares the likelihood with a predetermined threshold. Then, when the likelihood is equal to or greater than the threshold, the determination unit 102 determines that the processing state of the processing device 200 is normal. Moreover, the determination part 102 determines with the processing state of the processing apparatus 200 being abnormal, when a likelihood is less than a threshold value.

The method for determining the machining state of the processing device 200 is not limited to this, and any method can be used as long as it can determine the processing state of the processing device 200 using the feature information and the model. good. For example, instead of directly comparing the likelihood with the threshold, the determination unit 102 compares a value indicating fluctuation in likelihood with the threshold to determine whether the processing state of the processing device 200 is normal. Also good. Alternatively, determination section 102 calculates a score that is a positive numerical value equal to or greater than zero by taking the logarithm of the likelihood and inverting the sign. The score is close to zero if the processing state of the processing device 200 is normal, and increases as the degree of abnormality of the processing state of the processing device 200 increases. Therefore, the determination unit 102 determines that the processing state of the processing device 200 is normal if the score is less than or equal to the predetermined threshold, and if the score is greater than or exceeds the threshold, the processing It is determined that the machining state of the apparatus 200 is abnormal. That is, the determination unit 102 determines the processing state of the processing device 200 by comparing at least one of the likelihood or a value calculated using the likelihood with a threshold value.

Each unit (communication control unit 101, determination unit 102, feature extraction unit 110, generation unit 104) shown in FIG. 4 may be implemented by CPU 151 shown in FIG. (Integrated Circuit) or the like, or may be realized using both software and hardware.

The data extraction unit 112 extracts detection information at a time determined based on the rotation angle information from the detection information received by the communication control unit 101 . The determination unit 102 determines the rotation state of the tool 223 based on the detection information extracted by the data extraction unit 112 .

The analysis unit 113 Fourier-transforms the detection information extracted by the data extraction unit 112 .

Further, the determination unit 102 determines the rotation state of the tool 223 based on a reference value determined based on a complex number obtained by Fourier transforming the detection information extracted by the data extraction unit 112 by the analysis unit 113 . judge.

Next, the operation of diagnostic device 100 according to the present embodiment will be described in detail using FIG. In the present embodiment, the processing apparatus 200 has the physical quantity information detection unit 227 installed near the rotation main shaft 221, and the sensor 270 of the physical quantity information detection unit 227 is an acceleration sensor. The physical quantity information detection unit 227 amplifies the analog signal detected by the sensor 270 with the preamplifier of the sensor 270, samples it at predetermined time intervals, and converts the sampled analog signal to an analog/digital (A/D) converter. (Signal conversion circuit 271) converts to a digital signal. The diagnostic device 100 receives the digital signal output from the physical quantity information detection unit 227 as detection information by the reception unit 101a. The digital signal output from the physical quantity information detection unit 227 is converted into units of acceleration by the calibration value of the sensor 270 as necessary. The description will be made without depending on the specifications of the D converter (signal conversion circuit 271). Therefore, the receiving unit 101a receives the time-domain waveform of the observed value proportional to the acceleration detected by the sensor 270 of the physical quantity information detecting unit 227 as detection information.

The processing device 200 drills a pilot hole with a depth of 5.0 mm in an aluminum alloy plate with a drill with a diameter of 8.2 mm, then rotates a four-blade end mill with a diameter of 8.0 mm at 7500 rpm to perform contouring. did The contouring process was divided into three steps, and the cutting depths in the radial direction of the tool 223 were 100.0 μm (microns), 200.0 μm, and 32.0 μm, respectively. The XY-axis stage 225 rotates so as to widen the diameter of the pilot hole at this depth of cut. At this time, the processing apparatus 200 rotated the XY-axis stage 225 at 90.0 mm/min in the same direction as the rotating direction of the rotating main shaft 221 .

The receiving unit 120 of the diagnostic device 100 requests the processing device 200 to transmit the respective context information from the spindle speed receiving unit 122, the tool information receiving unit 121, and the machining process receiving unit 123, and controls the respective communication. Context information is transmitted and received via the unit 205 and the communication control unit 101 . Here, the context information includes rotation information, machining process information, tool information, and the like.

The rotation information may be either the spindle rotation speed set from the machining program read by the machining device 200 or the spindle rotation speed measured by the tachometer in the machining device 200 . The rotation information is, for example, 7500 rpm set from the machining program. The machining process information includes a number identifying the machining process described in the machining program, and information about the start and end of the operation of the rotary spindle 221 and stage (here, the XY-axis stage 225 and Z-axis stage 226 correspond). ,including. The machining process information is, for example, rotation start and end information of the XY-axis stage 225 . The tool information includes the tool type, diameter, number of teeth, and the like. However, the tool information is not limited to the context information from the processing device 200 , and the context information input from the input unit to the diagnostic device 100 from the input device 158 , the context information stored in the auxiliary storage device 155 , the context information other than the processing device 200 . may be context information or the like received by the receiving unit 101a from an external device. The tool information is, for example, the number of blades of the tool 223 (eg, four).

The in-process waveform extraction unit 116 of the feature extraction unit 110 extracts XY axes for each cutting depth of the tool 223 from the detection information (for example, acceleration waveform data that is acceleration waveform data) input from the physical quantity information detection unit 227. Machining waveform data, which is acceleration waveform data in time intervals corresponding to each of the three machining processes of the rotary motion of the stage 225, the start of the rotary motion, and the end of the rotary motion, is extracted. The analysis unit 113 is an example of a frequency analysis unit that performs frequency analysis on detection information. The analysis unit 113 performs Fourier transform on a predetermined number of samples of continuous waveform data during processing among the extracted waveform data during processing using, for example, an FFT (Fast Fourier Transform) algorithm. The extracted waveform data during processing may be used for all of the data string of the waveform data during processing to be Fourier transformed, or a part thereof may be replaced with zero. However, the waveform-in-process extraction unit 116 determines the sampling time interval of the detection information (acceleration waveform data) before being A/D converted by the signal conversion circuit 271, the data length of the detection information (the number of data in the data string), and the , to determine the frequency resolution that can be analyzed with the Fourier transform. Here, the embodiment will be described on the premise that the combination of the time interval and the data length is set so as to achieve a frequency resolution of approximately 5.8 Hz.

FIG. 5 is a diagram showing an example of a rotation angle sensor according to this embodiment. A main shaft 233 is rotatably supported on the main shaft 221 by a first bearing 231 and a second bearing 232 . One end of the main shaft 233 holds the tapered shank of the tool holder 222 . The other end of the main shaft 233 is connected with a motor 256 (servo motor). The rotation angle of the motor 256 is read by the encoder 241 and input to the drive control circuit 255 . The drive control circuit 255 follows a command from the machine control unit 201 to calculate the rotation speed from the rotation angle information and controls the rotation speed of the motor 256 . When the communication control unit 205 detects the zero position of the spindle rotation information from the drive control circuit 255 , it transmits a rectangular signal to the diagnostic device 100 . In the above, encoder 241 corresponds to rotation angle sensor 280 .

A reflecting portion 245 is provided on the main shaft 233 , and an optical sensor 243 is mounted at a position facing the side surface of the main shaft 233 and illuminating the reflecting portion 245 . The optical sensor 243 also has a light receiving portion for the reflected light from the reflecting portion 245 , and transmits a rectangular signal corresponding to the reflection intensity from the communication control portion 205 to the diagnostic device 100 . In the above, optical sensor 243 corresponds to rotation angle sensor 280 .

FIG. 6 is a diagram showing a rotation main shaft according to this embodiment. The rotating spindle 221 has an interface with BT30, which is a 7/24 tapered shank, the holder 222 has a keyway 321 and a V flange 322, and the total weight with the cutting tool attached is about 600 g. and rotates at 9000 rpm (idling). In addition, simulating chips, a tape 340 having a thickness of about 20 μm cut into a square of about 10 mm was attached to the tapered shank 323 to increase runout. Also, the sticking position of the tape 340 was changed along the circumference.

FIG. 7 is a diagram illustrating detection information and rotation angle information received by the receiving unit according to the embodiment;
The receiving unit 101a receives a vibration signal, which is an example of detection information, and a spindle rotation signal, which is an example of rotation angle information. There are three graphs in the figure, the upper graph is the vibration signal and the lower graph is the spindle rotation signal. The middle row shows the spectrogram obtained by Fourier transforming the vibration signal at regular time intervals for reference. Also, above the vibration signal in the upper row, a rectangular wave corresponding to the spindle rotation start and spindle stop start information acquired by the receiving unit 101a is shown. When the spindle starts rotating, the vibration amplitude increases. In the spectrogram, the frequency component with large amplitude shifts to the high frequency side and reaches steady rotation. Diagnosis is performed during this steady rotation, and if normal, processing proceeds. In this example, the spindle is stopped, but in actual production, the rotation speed is changed to that for machining without stopping, and machining is started. If an abnormality is diagnosed, a spindle stop command is sent to the processing device 200 . The lower part shows the rise of a pulse-like rectangular wave input when the rotation angle of the spindle reaches the zero position. The pulse interval gradually narrows during acceleration from the start of rotation, and becomes constant during steady rotation.

The data extracting unit 112 shown in FIG. 4 uses the spindle rotation angle zero position signal in the lower row as a trigger from the vibration waveform after the passage of time T1 from the spindle rotation start timing until the preset steady rotation is reached, and Fourier transform is performed. Cut out the number of frames to input. This extraction is sequentially performed with reference to preset time intervals and triggered by zero position signals in the vicinity thereof. The clipped signal is Fourier transformed by the analysis unit 113 . From the result, the feature amount extraction unit 110 extracts the bin value of the frequency corresponding to the spindle rotation speed. The feature quantity is a bin containing the rotation speed [rpm] / 60 component and its harmonic components, and further, a combination of high and low bins (adjacent bins) around this. good. Alternatively, a wide band of continuous bins containing the rotation speed component and its harmonic components may be used.

FIG. 8 is a flow chart showing an example of the flow of diagnostic processing in the diagnostic apparatus according to this embodiment. The numerical control unit 206 of the processing device 200 sequentially transmits context information indicating the current operation of the tool 223 to the diagnostic device 100 . The receiving unit 101a receives the context information transmitted from the processing device 200 (step S101). Next, the feature extraction unit 110 reads the learning model corresponding to the received context information from the storage unit 103 (step S102).

The physical quantity information detection unit 227 of the processing device 200 sequentially outputs detection information during processing by the processing device 200 . The receiving unit 101a receives the detection information (sensor data) and the rotation angle information transmitted from the processing device 200 (step S103). The data extraction unit 112 extracts detection information at a time determined based on the rotation angle information from the detection information (step S104). Next, the analysis unit 113 performs frequency analysis of the waveform data during processing using an FFT algorithm or the like (step S105). This frequency analysis is performed while shifting the preset number of data samples and the start position of the data string from the waveform data being processed. The result of frequency analysis on the waveform data being processed is three-dimensional structure data in which a plurality of spectra are arranged in time series. The feature extraction unit 110 extracts feature information from a plurality of spectra or an average spectrum obtained by averaging a plurality of spectra over an arbitrary time range (step S106).

The determination unit 102 uses the feature information extracted by the feature extraction unit 110 and the learning model corresponding to the received context information to determine whether the vibration related to shake or imbalance is normal or abnormal. 200 is determined (step S107). As a result, the machining state of the machining apparatus 200 can be determined using the feature information and the learning model extracted according to the tool 223 and the type of machining. It is possible to reliably detect and monitor the occurrence of an abnormality in the machining state of 200 without erroneously detecting it. The determination unit 102 outputs the determination result to the display unit 106 via the display control unit 105 (step S108). Alternatively, the determination unit 102 transmits alert information to the processing device 200 or an external device via the transmission unit 101b (step S108).

The receiving unit 101a further receives rotating body identification information for identifying the tool 223 in step S103. In this case, in step S107, the determination unit 102 determines the position of the tool 223 based on the detection information, the rotation angle information, and a reference value that can be set to a different value for each tool 223 identified based on the rotating body identification information. Determine the rotation state.

Next, an example of model generation processing by the diagnostic device 100 according to the present embodiment will be described using FIG. 9 . FIG. 11 is a flow chart showing an example of the flow of model generation processing by the diagnosis device according to the present embodiment. In the present embodiment, the generation unit 104 executes model generation processing in advance, for example, before diagnosis processing of the processing device 200 . Alternatively, as described above, the generation unit 104 may execute model generation processing when context information for which a learning model is not defined is input. Moreover, when the learning model is generated externally as described above, the model generation process does not have to be executed in the diagnosis device 100 .

The receiving unit 101a receives the context information transmitted from the processing device 200 (step S201). The receiving unit 101a also receives detection information (sensor data) and rotation angle information transmitted from the processing device 200 (step S202).

The contextual information and sensing information thus received are used to generate a learning model. In this embodiment, the generation unit 104 generates a learning model for each piece of context information, so detection information needs to be associated with the corresponding context information. Therefore, for example, the receiving unit 101a temporarily stores the received detection information in the storage unit 103 or the like in association with the context information received at the same timing. Then, the generating unit 104 confirms that the detection information stored in the storage unit 103 is normal information, and generates a learning model using only the normal detection information. That is, the generation unit 104 generates a learning model using the detection information labeled as normal.

The confirmation (labeling) of whether or not the detection information is normal may be performed at any timing after the detection information is stored in the storage unit 103 or the like, or may be performed in real time while the processing apparatus 200 is operating. You can Alternatively, the generation unit 104 may generate a learning model on the assumption that the detection information is normal without labeling the detection information. If the detection information assumed to be normal is actually abnormal detection information, the generated learning model will not correctly execute the process of determining whether the processing state of the processing apparatus 200 is normal. Therefore, it is possible to determine whether or not a learning model has been generated using the abnormal detection information based on the frequency at which the processing state of the processing apparatus 200 is determined to be abnormal, and to take measures such as deleting the erroneously generated learning model. can take Alternatively, a learning model generated using abnormal detection information may be used as a learning model for determining abnormality.

The data extraction unit 112 extracts detection information at a time determined based on the rotation angle information from the detection information (step S203). Next, the analysis unit 113 performs frequency analysis on the extracted processed waveform data using an FFT algorithm or the like (step S204). The analysis unit 113 performs frequency analysis while shifting the preset number of data samples and the start position of the data string from the waveform data being processed. The obtained frequency analysis results are three-dimensional structured data in which a plurality of spectra are arranged in time series. The feature extraction unit 110 extracts feature information according to the BPF from a plurality of spectra or a spectrum obtained by averaging a plurality of spectra over an arbitrary time range (step S205). This method will be described later.

The generation unit 104 generates a learning model corresponding to this context information using the feature information extracted from the detection information associated with the same context information (step S206). The generation unit 104 stores the generated learning model in the storage unit 103 (step S207).

The generation unit 104 generates a learning model based on the detection information and the rotation angle information in step S206. Specifically, the generation unit 104 extracts the detection information from the detection information received by the reception unit 101a by the data extraction unit 112 that extracts the detection information at the time determined based on the rotation angle information. to generate

In this case, the determination unit 102 performs a Fourier transform on the detection information cut out by the data cutout unit 112. The analysis unit 113 Fourier transforms the detection information. 223 is determined.

FIG. 10 is a diagram in which complex numbers obtained by Fourier transforming the detected information according to the present embodiment are plotted on a complex plane.

As described above, detection information was extracted with spindle rotation information as a trigger, and Fourier transform was performed. Among the obtained complex numbers, bin values containing the frequency component of the spindle rotation speed were plotted on the complex plane.

Here, X is a normal state in which the tape 340 is not attached in FIG. The amplitude of the normal data X is reduced by careful balance adjustment. However, in a machine tool using a plurality of tools, it takes a lot of time and effort to uniformly balance all of them, and an expensive holder having a balancing function must be used. However, in an actual industrial site, machining is performed by allowing even an imbalance within a range in which the target machining accuracy can be obtained. Therefore, normal data X is plotted at a position shifted from the origin of the complex plane.

The dashed line in the figure is a threshold circle 400 set from normal data, consisting of the center and its radius. On the other hand, ● and Δ in FIG. The position of the tape was successively shifted in the direction of rotation from the position shown in FIG. All of these data fell outside the data threshold circle 400 . In addition, since the tape 340 was attached, the runout of the cutting edge was increased, resulting in poor machining.

In the diagnostic program, assuming that the threshold center is (Xs, Ys), the threshold radius is rs, and the measurement data is (Xm, Ym),
(Xm-Xs)^2+(Ym-Ys)^2>rs^2 (1)
is the abnormality diagnosis formula. Note that the threshold radius rs may be set as a parameter in the diagnostic program based on the threshold circle 400 set from the normal data shown in FIG.

When the complex plane graph of FIG. 10 is displayed for each tool on the display unit of the diagnostic device 100, it is possible to grasp the degree of dispersion of the normal data and update the threshold to a more practical one.

(Second example of determination method)
From the values obtained by the Fourier transform, select a plurality of bins containing the main shaft rotation speed [rpm]/60 component and its harmonic components, and a plurality of bins around them, and use these multidimensional feature information for learning of one-class SVM , and anomaly judgment is performed by outlier detection.

(Third embodiment of determination method)
The normal model learned in FIG. 10 is read from the storage unit 103 in step 102 in FIG. The substance of this model is the probability density function P(X), such as the GMM (Gaussian Mixture Model), as described above. X is a feature amount, is extracted according to the BPF settings during learning, and is n-dimensional here (X={x1, x2, . . . xn}). The BPF settings are stored with this model, and are used in step 106 of FIG. 8 to extract each feature.

In step 107 of FIG. 8, the likelihood obtained by inputting the feature quantity into the probability density is determined to be normal if it is equal to or greater than a preset threshold value, and determined to be abnormal if less than the threshold value. Alternatively, a value obtained by reversing the sign of the logarithmic likelihood is defined as an anomaly score, and an index value such that the score increases when the abnormal state is strong, and the score a j is obtained for the number of spectra j = 1 to J. .

aj=-log(P(Xj)) (Equation 5)

As the total score of the degree of anomaly, for example, the maximum value of aj or the average of aj (equation 6) is selected by trial and error to suit the tool and machining method.

A=(Σaj)/J (Formula 6)

The anomaly score is compared with a preset threshold, and if it is equal to or greater than the threshold, it is determined to be abnormal, and if it is less than the threshold, it is determined to be normal.

FIG. 11 is a diagram plotting absolute values obtained by Fourier transforming the detection information according to the comparative example.

In the comparative example shown in FIG. 11, the diagnostic index value is the vibration intensity, which is obtained from the absolute value of the complex number obtained by Fourier transform. All the data plotted are identical to the data plotted in FIG. 10 and are obtained by fast Fourier transforming the time-domain data on the vibration measured by the vibration sensor and the absolute value of the intensity or amplitude of rotation at 9000 rpm. Bins containing the 150 Hz rate were taken and plotted in order of measurement. Here, as in FIG. 10, X is the normal state where the tape 340 is not applied. A dashed line indicates a threshold for abnormality determination set from the value of X. FIG. The threshold consists of an upper limit and a lower limit, which correspond to the values obtained by adding and subtracting the threshold radius rs from the absolute values of the threshold center (Xs, Ys) in FIG. 10, respectively. If it is between the upper limit and the lower limit of this threshold value, it is determined to be normal, and if it is outside the threshold value, it is determined to be abnormal.

Machining without the tape 340 applied was normal, but for all other data, the tape 340 was applied, resulting in greater runout of the cutting edge and poor machining. However, it can be seen that the Δ data among the idling vibration data when the tape 340 is pasted is positioned between the threshold values and may be misdiagnosed as normal.

A program to be executed by the diagnostic apparatus of the present embodiment is preinstalled in a ROM or the like and provided.

The program executed by the diagnostic apparatus of this embodiment is a file in an installable format or an executable format, and can be read by a computer such as a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk), etc. It may be configured to be recorded on a possible recording medium and provided as a computer program product.

Further, the program executed by the diagnostic apparatus of this embodiment may be stored in a computer connected to a network such as the Internet, and may be provided by being downloaded via the network. Also, the program executed by the diagnostic apparatus of this embodiment may be configured to be provided or distributed via a network such as the Internet.

The program executed by the diagnostic apparatus of this embodiment has a module configuration including the above-described units (communication control unit, determination unit, etc.). By reading and executing, each of the above sections is loaded onto the main storage device, and each section is generated on the main storage device.
Further, a machine tool with a diagnostic function may be used, in which each hardware of the diagnostic device of the present embodiment is incorporated in the machine tool and the program is executed.

●Summary●
As described above, the diagnostic device 100, which is an example of a determination device according to an embodiment of the present invention, rotates when the tool 223, which is an example of a rotating body that can be attached to and detached from the rotating main shaft 221, which is an example of a rotating shaft, rotates. A receiving unit 101a that receives the detection information of the time-varying physical quantity emitted from and the rotation angle information when the tool 223 rotates, and the rotation state of the tool 223 is determined based on the detection information and the rotation angle information. and a determination unit 102 for determining the Thereby, the rotation state of the tool 223 can be accurately determined.

The diagnostic apparatus 100 includes a data extraction unit 112 that extracts detection information at a time determined based on the rotation angle information from the detection information received by the communication control unit 101 . The rotation state of the tool 223 is determined based on the detected information.

The diagnostic apparatus 100 includes an analysis unit 113 that Fourier-transforms the detection information extracted by the data extraction unit 112, and the determination unit 102 compares the complex number obtained by Fourier-transforming the analysis unit 113 with a reference value. By doing so, the rotational state of the tool 223 is determined.

The receiving unit 101a further receives rotating body identification information for identifying the tool 223, and the determining unit 102 sets a different value for each tool 223 identified based on the detection information, the rotation angle information, and the rotating body identification information. The rotational state of the tool 223 is determined based on the possible reference values.

The diagnostic apparatus 100 includes a generating unit 104 that generates a model based on the detection information and the rotation angle information, and the determination unit 102 based on the detection information, the rotation angle information, and the reference value based on the model, A rotation state of the tool 223 is determined.

The generation unit 104 generates a model based on the detection information extracted by the data extraction unit 112 that extracts the detection information at the time determined based on the rotation angle information from the detection information received by the reception unit 101a.

The determination unit 102 determines the rotation state of the tool 223 based on a reference value determined based on a complex number obtained by Fourier transforming the detection information extracted by the data extraction unit 112 by the analysis unit 113 . do.

A diagnostic method using the diagnostic device 100, which is an example of a determination method according to an embodiment of the present invention, includes detection information of a time-varying physical quantity emitted when a tool 223 detachable from a rotating spindle 221 rotates, and A reception step by the reception unit 101a for receiving rotation angle information when rotating, and a determination step by the determination unit 102 for determining the rotation state of the tool 223 based on the detection information and the rotation angle information.

A machining system according to one embodiment of the present invention includes the diagnostic device 100 and a machining device 200 having a tool 223 to be diagnosed, which is an example of a determination target of the diagnostic device 100, and the machining device 200 , detection information, and rotation angle information to the diagnostic apparatus 100. The communication control unit 205 is an example of a transmission unit.

REFERENCE SIGNS LIST 100 diagnosis device 101 communication control unit 101a reception unit 101b transmission unit 102 determination unit 103 storage unit 104 generation unit 105 display control unit 106 display unit 107 input unit 110 feature extraction unit 111 BPF setting unit 112 data extraction unit 113 analysis unit 114 frequency shift Estimation unit 115 Frequency analysis unit 116 Machining waveform extraction unit 117 Range setting unit 118 Natural frequency exclusion unit 120 Reception unit 121 Tool information reception unit 122 Spindle rotation speed reception unit 123 Machining process reception unit 200 Machining device 205 Communication control unit (transmitting unit example)
221 Rotation main shaft (an example of a rotation shaft)
222 tool holder 223 tool (an example of a rotating body)
227 physical quantity information detection unit 228 spindle rotation information acquisition unit 241 encoder 243 optical sensor 245 reflection unit 255 drive control circuit 256 motor 270 vibration sensor 271 signal conversion circuit 280 rotation angle sensor 281 signal conversion circuit

Claims (12)

a receiving unit that receives detection information of a time-varying physical quantity generated when a rotating body attachable to and detachable from a rotating shaft rotates, and rotation angle information when the rotating body rotates;
a determination unit that determines the rotation state of the rotating body based on the detection information and the rotation angle information;
A judgment device with a clipping unit for clipping the detection information at a time determined based on the rotation angle information from the detection information received by the reception unit;
2. The determination device according to claim 1, wherein the determination unit determines the rotation state of the rotating body based on the detection information extracted by the extraction unit. An analysis unit that Fourier transforms the detection information cut out by the cutout unit,
3. The determination device according to claim 2, wherein the determination unit determines the rotational state of the rotating body by comparing the complex number obtained by the Fourier transform by the analysis unit with a reference value. The receiving unit further receives rotating body identification information for identifying the rotating body,
The determination unit determines the rotational state of the rotating body based on the detection information, the rotation angle information, and a reference value that can be set to a different value for each of the rotating bodies identified based on the rotating body identification information. The determination device according to any one of claims 1 to 3, which determines the a generation unit that generates a model based on the detection information and the rotation angle information;
The determination device according to any one of claims 1 to 4, wherein the determination unit determines the rotation state of the rotating body based on the detection information, the rotation angle information, and the reference value based on the model. The generation unit generates the model based on the detection information extracted by an extraction unit that extracts the detection information at a time determined based on the rotation angle information from the detection information received by the reception unit. The determination device according to claim 5. The determination unit determines the rotation state of the rotating body based on the reference value determined based on the complex number obtained by Fourier transforming the detection information cut out by the cutout unit by the analysis unit. 7. The determination device according to claim 6, which determines a receiving step of receiving detection information of a time-varying physical quantity generated when a rotating body attachable to and detachable from a rotating shaft rotates, and rotation angle information when the rotating body rotates;
a determination step of determining a rotation state of the rotating body based on the detection information and the rotation angle information;
Judgment method with A program for causing a computer to execute the determination method according to claim 8. A processing system comprising: the determination device according to any one of claims 1 to 7; and a processing device comprising a tool as the rotating body to be determined by the determination device,
A processing system in which the processing device includes a transmission unit that transmits the detection information and the rotation angle information to the determination device. 11. The machining system according to claim 10, wherein the machining system executes the determination method according to claim 7. 11. The processing system according to claim 10, wherein the processing system executes the program according to claim 9.

Images