JP7253679B2 - Failure detection system and failure detection method for component mounting line - Google Patents

Description

The present invention relates to a malfunction detection system for detecting malfunctions of devices constituting a component mounting line and a malfunction detection method for a component mounting line.

2. Description of the Related Art Conventionally, when an abnormality (error) has occurred in any device (portion) of a component mounting apparatus that constitutes a component mounting line for manufacturing a mounting board on which components are mounted on a board, it is reported that the error has occurred. There is known a component mounting apparatus having a function of informing a worker of the above (see, for example, Patent Document 1). The component mounting apparatus described in Patent Literature 1 includes a sensor (abnormality detection device) that detects an abnormality in the device, and notifies the operator of the occurrence of an error when the sensor detects an abnormality.

JP 2013-4951 A

However, in the prior art including Patent Document 1, an abnormality detected by the sensor is only determined as an error, and there is room for improvement in detecting a malfunctioning state of the device, which is a sign of an error that will occur in the future. rice field.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a failure detection system and a failure detection method for a component mounting line that can detect a failure of a device during manufacture of a mounting board on a component mounting line.

A malfunction detection system of the present invention includes a data collection unit that collects data on the operating status of devices that constitute a component mounting line including a component mounting apparatus, and one or more feature amounts included in the data collected by the data collection unit. a judgment unit for judging whether or not the tendency of data deviates from the tendency of the feature amount data in the normal state; and the feature amount data judged by the judgment unit to deviate from the tendency of the feature amount data in the normal state. and a notification unit that notifies that at least one or more of the devices corresponding to the is malfunctioning and may soon become defective .

A malfunction detection method for a component mounting line according to the present invention is a method for detecting malfunction of a device constituting a component mounting line including a component mounting apparatus, wherein the operation status of the device is detected from the component mounting line. a data collection step of collecting data related to the and at least one or more of the devices corresponding to the feature amount data determined to deviate from the trend of the feature amount data in the normal state in the determination step , and the device will soon become defective. and a notification step of notifying that there is a possibility .

According to the present invention, a malfunction of a device can be detected during manufacture of a mounting substrate on a component mounting line.

1 is an explanatory diagram of the configuration of a component mounting system according to an embodiment of the present invention; FIG. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is an explanatory diagram of the configuration of a component mounting apparatus according to an embodiment of the present invention; 1 is a block diagram showing the configuration of a malfunction detection system according to an embodiment of the present invention; FIG. 2 is an explanatory diagram of an example of feature amount data in the malfunction detection system according to one embodiment of the present invention; FIG. 2 is an explanatory diagram of an example of a learning data set in the malfunction detection system according to one embodiment of the present invention; Explanatory diagram of an example of a detection model in the malfunction detection system of one embodiment of the present invention The figure which shows the flow of the malfunction detection method of one embodiment of this invention.

An embodiment of the present invention will be described in detail below with reference to the drawings. The configuration, shape, etc. described below are examples for explanation, and can be changed as appropriate according to the specifications of the component mounting system and the component mounting line. In the following, the same reference numerals are given to the corresponding elements in all the drawings, and redundant explanations are omitted. In FIG. 2, the X direction (perpendicular to the paper surface in FIG. 2) of the substrate transfer direction and the Y direction (horizontal direction in FIG. 2) perpendicular to the substrate transfer direction are shown as two axial directions perpendicular to each other in the horizontal plane. Also, the Z direction (vertical direction in FIG. 2) is shown as the height direction orthogonal to the horizontal plane.

First, a component mounting system 1 will be described with reference to FIG. The component mounting system 1 includes a component mounting apparatus M1, a component mounting apparatus M2, and a component mounting apparatus M3, which are manufacturing facilities, in order from the upstream side (the left side in FIG. 1) in the board transfer direction. The component mounting apparatuses M1 to M3 have a substrate conveying mechanism such as a belt conveyor, and manufacture mounted boards while conveying the substrates from upstream to downstream by the substrate conveying mechanisms of the component mounting apparatuses M1 to M3. The component mounting apparatuses M1 to M3 are connected to a management computer 3 via a wired or wireless communication network 2, and transmit and receive data to and from the other component mounting apparatuses M1 to M3 and the management computer 3. FIG.

Note that the number of component mounting apparatuses M1 to M3 provided in the component mounting line L1 is not limited to three, and may be one, two, four or more. In addition to the component mounting apparatuses M1 to M3, the component mounting line L1 includes devices such as a printing device that prints cream solder on the board and a reflow device that heats the board on which components are mounted and solders the components to the board. may have. Thus, the component mounting apparatuses M1 to M3 and the management computer 3 constitute a component mounting line L1 having a plurality of facilities including the component mounting apparatuses M1 to M3.

In FIG. 1, the management computer 3 executes processing such as transmission of programs and data necessary for production of mounted boards to the component mounting apparatuses M1 to M3. In addition, the management computer 3 collects the operation statuses of various devices provided in the component mounting apparatuses M1 to M3, which are transmitted from the component mounting apparatuses M1 to M3 via the communication network 2, and determines whether the devices are in a normal state. Monitor if it is in an unhealthy state that is likely to become defective in the near future.

In FIG. 1, a management computer 3 is connected to a host computer 5 that manages data common to other component mounting lines L2 and L3 and component mounting lines L1 to L3 via a host communication network 4 different from the communication network 2. and can send and receive data to each other.

Next, referring to FIG. 2, the configuration of component mounting apparatuses M1 to M3 will be described. The component mounting apparatuses M1 to M3 have the same configuration, and the component mounting apparatus M1 will be described below. The component mounting apparatus M1 has a function of mounting a component D on a board B. FIG. A substrate transport mechanism 12 provided on the upper surface of the base 11 transports the substrate B in the X direction, positions it, and holds it. The head moving mechanism 13 moves the mounting head 14 mounted via the plate 13a in the X direction and the Y direction. A suction nozzle 15 is attached to the lower end of the mounting head 14 .

A plurality of tape feeders 16 are mounted side by side in the X direction on the top of a carriage 17 coupled to the base 11 on the side of the substrate transport mechanism 12 . A carrier tape 18 for storing components D to be supplied to the component mounting apparatus M<b>1 is wound around a reel 19 and held on the carriage 17 . The carrier tape 18 inserted into the tape feeder 16 is pitch-fed by a tape feeding mechanism 16a built in the tape feeder 16 at regular intervals. As a result, the components D stored in the carrier tape 18 are sequentially supplied to the component supply port 16b provided at the top of the tape feeder 16. As shown in FIG.

In FIG. 2, the component mounting apparatus M1 includes a control unit C that controls the substrate transport mechanism 12, the head moving mechanism 13, the mounting head 14, and the tape feeder 16 to perform the component mounting operation. In the component mounting operation, the controller C causes the head moving mechanism 13 to move the mounting head 14 above the tape feeder 16, and the suction nozzle 15 vacuum-sucks the component D supplied from the tape feeder 16 to the component supply port 16b. Pick up (arrow a). Next, the control unit C causes the head moving mechanism 13 to move the mounting head 14 holding the component D above the substrate B held by the substrate transport mechanism 12, and the component D is placed on the predetermined component mounting position Ba on the substrate B. (Arrow b).

In FIG. 2, the mounting head 14 has a vacuum sensor 14a for measuring the degree of vacuum when the suction nozzle 15 vacuum-sucks the component D. As shown in FIG. It is possible to detect the presence or absence of a suction failure (suction error) from the measurement result of the degree of vacuum of the suction nozzle 15 during component holding operation by the vacuum sensor 14a. That is, when the suction nozzle 15 normally picks up the component D, the degree of vacuum becomes smaller than a predetermined value, and when the suction nozzle 15 cannot hold the component D or picks up the component D in an abnormal posture, the degree of vacuum does not decrease to the predetermined value. Therefore, the controller C can detect a suction error by comparing the measured degree of vacuum with a predetermined value.

In FIG. 2, a substrate recognition camera 20 is attached to the plate 13a with its optical axis directed downward. The board recognition camera 20 is moved integrally with the mounting head 14 in the X direction and the Y direction by the head moving mechanism 13 . The board recognition camera 20 moves above the tape feeder 16 and images the component D supplied to the supply position of the component supply port 16b.

The control unit C performs image recognition on the imaging result, and calculates the supply position deviation amount by which the actually supplied component D is shifted from the expected normal supply position. Further, based on the calculated supply position deviation amount, the control unit C determines the suction position (stop position of the mounting head 14) when the suction nozzle 15 picks up the component D, or the supply position of the component D of the tape feeder 16. to correct. Further, the control unit C performs image recognition on the imaging result, and detects a supply error in which the component D cannot be recognized because the component D is not supplied to the component supply port 16b.

In FIG. 2, a component recognition camera 21 is mounted on the upper surface of the base 11 between the board transfer mechanism 12 and the tape feeder 16, with the optical axis directed upward. The component recognition camera 21 images the lower surface of the component D held by the suction nozzle 15 (or the suction nozzle 15 that could not hold the component D) when the suction nozzle 15 that picked up the component D passes above. .

The control unit C performs image recognition on the imaging result, and recognizes that the posture of the component D held by the suction nozzle 15 is abnormal, or that the component D that should be held by the suction nozzle 15 cannot be recognized. is not occurring. Further, the control unit C performs image recognition on the imaging result, and calculates the suction position deviation amount by which the component D actually picked up by the suction nozzle 15 is shifted from the expected normal suction position. When the component D is mounted on the component mounting position Ba on the board B, the control unit C performs mounting position correction and mounting posture correction based on the amount of deviation of the suction position.

As described above, the component mounting apparatus M1 includes a device (feeder) tape feeder 16, a mounting head 14, and a nozzle (suction nozzle 15). Then, the controller C controls the detected suction error, supply error, occurrence status of the recognition error, calculated supply position deviation amount, correction amount of the suction position of the component D by the suction nozzle 15, suction position deviation amount, and mounting position correction amount. , correction amount of wearing posture, etc. are transmitted to the management computer 3 in association with the status of the device (normal, abnormal, etc.). In addition, the control unit C associates the measurement results of various sensors provided in each mechanism of the component mounting apparatus M1, such as the degree of vacuum by the vacuum sensor 14a, with the status of the device (normal, abnormal, etc.) and transmits them to the management computer 3. In this manner, a large amount of data regarding the operating status of the component mounting apparatuses M1 to M3 is sequentially transmitted to the management computer 3. FIG.

Next, referring to FIG. 3, the configuration of the management computer 3 will be described. The management computer 3 includes a processing unit 30, a collected data storage unit 37 which is a storage device, a learning data set storage unit 39, a model storage unit 41, an in-line communication unit 43, a higher-level communication unit 44, and a display unit 45. there is The processing unit 30 is a data processing device such as a CPU, and includes a data collection unit 31, a learning data set creation unit 32, a detection model creation unit 33, a determination unit 34, a notification processing unit 35, and an update unit 36 as internal processing units. there is

The in-line communication unit 43 is a communication interface, and transmits and receives data to and from the component mounting apparatuses M1 to M3 via the communication network 2. FIG. The host communication unit 44 is a communication interface, and transmits and receives data to and from other component mounting lines L2 and L3 and the host computer 5 via the host communication network 4 . The display unit 45 is a display device such as a liquid crystal display.

In FIG. 3, the data collection unit 31 collects data about the operating status of the component mounting apparatuses M1 to M3 and stores the collected data as the operating status data 38 in the collected data storage unit 37 . That is, the data collection unit 31 collects the operating status data 38 from the component mounting line L1 including the component mounting apparatuses M1 to M3. The operating status data 38 includes information about errors in the component mounting operation, information relating various correction values to the status of the component mounting operation after correction (normal, abnormal, etc.), and various sensors provided in the component mounting apparatuses M1 to M3. It includes information that associates the measurement result with the status of the component mounting operation before and after the measurement.

In FIG. 3, the learning data set creation unit 32 classifies the feature amount data of the devices provided in the component mounting apparatuses M1 to M3 based on the operation status data 38 into normal operation status sections and bad operation status sections. Alternatively, the device status data 40 with the malfunction label is created and stored in the learning data set storage unit 39 for each device.

Here, with reference to FIG. 4, an example of feature amount data included in the operating status data 38 and a procedure for creating the device status data 40 (learning data set) by the learning data set creating unit 32 will be described. FIG. 4 shows the error rate of suction errors related to one suction nozzle 15 and the average value of the degree of vacuum of the suction nozzle 15 measured by the vacuum sensor 14a of the mounting head 14 on which the suction nozzle 15 is mounted, over the operating time. is represented as a transition in Here, the error rate is the number of errors per hour, and the average vacuum degree is the average vacuum degree for one hour.

As shown in FIG. 4, a stop threshold value and a warning threshold value are set in advance for the error rate of adsorption errors. When the component mounting apparatuses M1 to M3 determine that a suction error has occurred in which the suction nozzle 15 cannot normally pick up the component D, the component mounting devices M1 to M3 automatically retry the component holding operation of taking out and holding a new component D from the tape feeder 16. run to

The stop threshold is an error rate that requires maintenance by stopping the manufacturing of the mounting board because the retry of the component holding operation occurs frequently. As for the warning threshold, since the problem is automatically resolved by retrying the part holding operation, it is not necessary to stop manufacturing the mounting board at the present time, but the operator is instructed to perform maintenance when the equipment is stopped due to setup changes, etc. is the error rate at which a warning is issued to In FIG. 4, the error rate exceeds the warning threshold from 13:00 to 14:00, and the error rate exceeds the stop threshold at 15:00, after which maintenance is performed.

In FIG. 4, when creating a learning data set, first, the learning data set creation unit 32 statistically processes the number of adsorption errors, which are feature data included in the operation status data 38, and the measurement results of the vacuum sensor 14a. Calculate the average value of the error rate and degree of vacuum. Next, the learning data set creation unit 32 classifies the period from 10:00 to 12:00 when the error rate is lower than the warning threshold as a normal section, and classifies the section from 13:00 to 14:00 when the error rate is equal to or higher than the warning threshold and lower than the stop threshold as a bad section. Separate.

Next, the learning data set creation unit 32 extracts the number of suction errors and the degree of vacuum from 10:00 to 12:00 included in the operation status data 38, and creates device status data 40 labeled as normal. The learning data set creation unit 32 also extracts the number of suction errors and the degree of vacuum from 13:00 to 14:00 included in the operation status data 38, and creates device status data 40 with a malfunction label attached. In this way, the learning data set creation unit 32 creates a learning data set (device status data 40) that includes at least the feature amount data in the normal state and the feature amount data in the unhealthy state.

In FIG. 3, the detection model creation unit 33 generates a detection model, which will be described later, by using the normal-labeled feature amount data and the malfunction-labeled feature amount data in the malfunction state, which are included in the device status data 40 . 42 is created and stored in the model storage unit 41 . That is, the detection model creation unit 33 creates the detection model 42 using the learning data set (device status data 40).

Based on the detection model 42, the determination unit 34 determines whether or not the tendency of one or more feature amount data included in the operating status data 38 collected by the data collection unit 31 deviates from the tendency of the feature amount data during normal operation. judge. Details of determination by the determination unit 34 will be described later.

When the determination unit 34 determines that the trend of the feature amount data deviates from the normal trend, the notification processing unit 35 notifies the display unit 45 that the device corresponding to the feature amount data is malfunctioning. That is, the notification processing unit 35 and the display unit 45 are connected to at least one component mounting line L1 corresponding to the feature amount determined by the determination unit 34 that the feature amount data deviates from the tendency of the feature amount data in the normal state. It is a notification unit that notifies that the above device is malfunctioning. Note that the notification processing unit 35 may notify a portable terminal (not shown) possessed by the worker.

Here, a specific example of creating the detection model 42 using the device status data 40 (learning data set) created from the operating status data 38 shown in FIG. 4 will be described with reference to FIGS. 5 and 6. FIG. FIG. 5 is a scatter diagram of the error rate, which is the number of errors per 10 minutes, and the average degree of vacuum for 10 minutes. In FIG. 5, data are plotted in open circles labeled as normal and as black circles labeled as unhealthy.

In FIG. 5, when creating the detection model 42, the detection model creation unit 33 first analyzes the device status data 40 (learning data set) in detail using a technique such as statistical analysis. In this example, the detection model creating unit 33 calculates the average value of the error rate and the degree of vacuum from the number of adsorption errors and the degree of vacuum included in the device status data 40, and analyzes the correlation between the two.

In FIG. 5, there is a positive correlation between the error rate and the degree of vacuum, and when the degree of vacuum increases, the error rate increases and there is a tendency to become unsatisfactory. Furthermore, all the data in the regions where the degree of vacuum is lower than V1 are labeled as normal, and the data in the regions where the degree of vacuum is higher than V2 are all labeled as faulty. Therefore, the detection model creation unit 33 creates a detection model 42 that determines normality when the degree of vacuum is lower than V1 and malfunction when the degree of vacuum is higher than V2 (FIG. 6).

In FIG. 5, when the degree of vacuum is between V1 and V2, data labeled as normal and data labeled as unhealthy are mixed. Therefore, the detection model creating unit 33 analyzes the data for the degree of vacuum between V1 and V2 in more detail. As a result of the analysis, when the rate of increase in the degree of vacuum was higher than G1, all the data were labeled as bad (not shown). Therefore, the detection model creation unit 33 creates a detection model 42 that determines that the degree of vacuum is between V1 and V2 and the increase rate of the degree of vacuum is higher than G1 (FIG. 6).

Next, with reference to FIG. 6, the determination of malfunction by the determination unit 34 based on the detection model 42 will be described. A detection model 42 shown in FIG. 6 is a model for detecting a malfunction of the suction nozzle 15 or the mounting head 14 using the degree of vacuum measured by the vacuum sensor 14a included in the operation status data 38 as feature amount data. In the detection model 42 shown in FIG. 6, the area where the degree of vacuum is V2 or more, or the area where the degree of vacuum is V1 or more and the rate of increase of the degree of vacuum is G1 or more, that is, the hatched area (hereinafter referred to as "unsatisfactory area"). is the condition for judging that the condition is not good.

In FIG. 6, the determination unit 34 calculates the degree of vacuum and the rate of increase in the degree of vacuum, and determines whether or not the calculated degree of vacuum and the rate of increase in the degree of vacuum are in a malfunctioning region indicated by hatching in the drawing. That is, when the calculated degree of vacuum and the increase rate of the degree of vacuum are in the malfunctioning region, it is determined that the feature amount data deviates from the normal trend and the suction nozzle 15 or the mounting head 14 is malfunctioning. After detecting the malfunction, the determination unit 34 may further perform determination to narrow down the cause of the malfunction based on another detection model 42 .

In FIG. 3, the updating unit 36 updates the content of the learning data set (device status data 40) based on the operation status data 38 collected by the data collecting unit 31 after the detection model 42 is created. Note that the updating unit 36 may update the device status data 40 together with part of the operating status data 38 that has already been collected for creating the learning data set.

When the update unit 36 updates the learning data set (device situation data 40), the detection model creation unit 33 uses the updated device situation data 40 to update the detection model 42 at a predetermined timing. The predetermined timing is, for example, a predetermined interval such as once a week, the time of changeover to change the type of mounting substrate manufactured in the component mounting line L1, or the start of work when the component mounting line L1 starts operating. is set as appropriate. Further, the detection model 42 may be updated when it is necessary to review the detection model 42, such as when adsorption errors occur frequently but are not determined to be malfunctioning.

Next, along with the flow of FIG. 7, a malfunction detection method of a component mounting line for detecting malfunction of devices constituting the component mounting line L1 including the component mounting apparatuses M1 to M3 will be described. First, the data collection unit 31 collects data for creating a learning data set from the component mounting line L1 (ST1: first data collection step). The collected data is stored in the collected data storage unit 37 as the operating status data 38 . Next, the learning data set creation unit 32 creates a learning data set (device status data 40) including at least the feature amount data during normal operation and the feature amount data during malfunction based on the operation status data 38 (ST2: learning data set creation process).

Next, the detection model creation unit 33 creates the detection model 42 using the learning data set (ST3: detection model creation step). Next, the data collection unit 31 collects the operation status data 38 for determining malfunction from the component mounting line L1 (ST4: second data collection step). The data for judgment may be not only the operation status data 38 collected after the detection model 42 is created, but also part of the operation status data 38 already collected for creating the learning data set.

In FIG. 7, if it is not time to update the detection model 42 next (No in ST5), the determination unit 34 collects in the second data collection step (ST4) and the first data collection step based on the detection model 42 It is determined whether or not the tendency of one or more feature amount data included in the obtained operating status data 38 deviates from the tendency of the feature amount data during normal operation (ST6: determination step). If the trend of the feature amount data does not deviate from the normal state (No in ST6), the process returns to the second data collection step (ST4) and periodic determination is performed.

If it is determined in the determination step (ST6) that the trend of the feature data is out of the normal state (Yes), the notification processing unit 35 displays that at least one or more devices corresponding to the feature data are malfunctioning. The unit 45 is notified (ST7: notification step). As a result, it is possible to detect a malfunction of the device during manufacturing of the mounting board on the component mounting line L1.

If it is time to update the detection model 42 after the second data collection step (ST4) (Yes in ST5), the update unit 36 updates the operating status data 38 collected in the second data collection step (ST4). The learning data set (device status data 40) is updated (ST8: learning data set update step).

Next, in the detection model creation step (ST3), a detection model 42 is created using the updated device status data 40. FIG. That is, the learning data set update step (ST8) and the detection model creation step (ST3) are update steps for updating the detection model 42 with the operating status data 38 collected in the second data collection step (ST4).

As described above, the management computer 3 of the present embodiment includes the data collection unit 31 that collects the operational status data 38 from the component mounting line L1 including the component mounting apparatuses M1 to M3, and the collected operational status data 38. a judgment unit 34 for judging whether or not the tendency of one or more included feature amount data deviates from the tendency of the feature amount data in the normal state; and a notification unit (notification processing unit 35, display unit 45) that notifies that at least one or more devices constituting a component mounting line L1 corresponding to determined feature amount data is malfunctioning. . As a result, it is possible to detect a malfunction of the device during manufacturing of the mounting board on the component mounting line L1.

The malfunction detection system may be configured such that the host computer 5 includes the data collection unit 31 , the learning data set creation unit 32 , and the detection model creation unit 33 . That is, the host computer 5 collects the operating status data 38 from the component mounting lines L1 to L3, creates device status data 40 (learning data set), and creates a detection model 42. FIG. Then, the created detection model 42 may be sent to the management computer 3 provided for the component mounting lines L1 to L3, and the management computer 3 may detect malfunction of the device. As a result, it is possible to create a more detailed detection model 42 based on the operating status data 38 of the plurality of component mounting lines L1 to L3, and improve the accuracy of malfunction detection.

INDUSTRIAL APPLICABILITY The malfunction detection system and the malfunction detection method for a component mounting line of the present invention have the effect of being able to detect a malfunction of a device during the manufacture of a mounting substrate on a component mounting line, and are useful in the field of mounting components on substrates. is.

3 Management computer (malfunction detection system)
14 mounting head (device)
15 adsorption nozzle (device)
16 tape feeder (device)
L1 Component mounting line M1~M3 Component mounting equipment

Claims (8)

a data collection unit that collects data on the operating status of devices that make up a component mounting line including component mounting equipment;
a determination unit that determines whether or not the tendency of one or more feature amount data included in the data collected by the data collection unit deviates from the tendency of the feature amount data in a normal state;
Possibility that at least one or more of the devices corresponding to the feature amount data determined by the determination unit to deviate from the trend of the feature amount data in the normal state are malfunctioning and the devices will become defective in the near future. and a notification unit that notifies that there is
The malfunction detection system , wherein the device is a mounting head or a suction nozzle, and the judgment unit judges based on the degree of vacuum and an increase rate of the degree of vacuum, which are the feature amount data. 2. The malfunction detection system according to claim 1, wherein the determination unit performs determination based on a detection model created using a learning data set including at least feature amount data in normal state and feature amount data in malfunction state. 3. The malfunction detection system according to claim 2, further comprising an updating section that updates the content of said learning data set used for creating said detection model, with the data collected by said data collecting section. 4. The malfunction detection system according to any one of claims 1 to 3, wherein the device includes at least one of a feeder, a mounting head and a nozzle. A malfunction detection method for a component mounting line for detecting a malfunction of a device constituting a component mounting line including a component mounting apparatus, comprising:
a data collection step of collecting data on the operation status of the device from the component mounting line;
a determination step of determining whether or not the trend of one or more feature amount data included in the data collected in the data collection step deviates from the trend of the feature amount data in a normal state;
Possibility that at least one or more of the devices corresponding to the feature amount data determined to deviate from the trend of the feature amount data in the normal state in the determination step is malfunctioning and the device will become defective in the near future. and a notification step for notifying that there is
A malfunction detection method for a component mounting line, wherein the device is a mounting head or a suction nozzle, and in the determination step, determination is made based on the degree of vacuum and an increase rate of the degree of vacuum, which are the feature data. 6. The component mounting line according to claim 5, wherein in the determination step, the determination is performed based on a detection model created using a learning data set including at least feature amount data during normal operation and feature amount data during malfunction. fault detection method. 7. The malfunction detection method for a component mounting line according to claim 6, further comprising an update step of updating said detection model with the data collected in said data collection step. 8. The malfunction detection method for a component mounting line according to claim 5, wherein said device includes at least one of a feeder, a mounting head and a nozzle.

Images