Identification method, identification device, and identification program

Abstract

This identification device: acquires connection relationship information indicating the mechanical connection relationship between a plurality of servo motors and a connection mechanism; acquires the abnormality of each of the plurality of servo motors; identifies abnormal points from each of the plurality of servo motors and the connection mechanism on the basis of the abnormality of each of the plurality of servo motors and the connection relationship information; and displays the abnormal points on a display.

Description

Identification method, identification device, and identification program

[0001] The present disclosure relates to a technique for identifying an abnormality in a servo system in which multiple servo motors are mechanically connected.

[0002] Patent Document 1 discloses a technology for estimating multiple causal models between variables based on the relationships between multiple mechanisms in processes carried out on a production line, obtaining anomaly detection results for the production line, and estimating the cause of the anomaly in the multiple causal models based on the contribution rate of variables that contributed to the anomaly among the anomaly detection results.

[0003] However, the technology described in Patent Document 1 does not identify a location where a sensor is not installed as an abnormal location. Therefore, if a sensor is not installed in a connection mechanism that mechanically connects servo motors, when an abnormality occurs in the connection mechanism, the connection mechanism cannot be identified as an abnormal location.

[0004] JP 2023-092184 A

[0005] The present disclosure has been made to solve such problems, and aims to provide a technology that can identify a connection mechanism that mechanically connects servo motors as an abnormality without installing a sensor in the connection mechanism.

[0006] An identification method in one aspect of the present disclosure is a method for identifying an abnormality location in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, wherein a computer acquires connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism, acquires an abnormality level for each of the plurality of servo motors, and identifies the abnormality location from each of the plurality of servo motors and the connection mechanism based on the abnormality level for each of the plurality of servo motors and the connection relationship information, and displays the abnormality location on a display.

[0007] According to the present disclosure, the connection mechanism that mechanically connects the servo motors can be identified as an abnormal location without installing a sensor in the connection mechanism.

[0008] FIG. 1 is a diagram illustrating an example of a configuration of a production system according to a first embodiment of the present disclosure. FIG. 2 is a diagram illustrating an operation mode. FIG. 3 is a graph illustrating a relationship between a threshold value and an abnormality degree. FIG. 4 is a flowchart illustrating an example of processing by an identification device in a storage phase in which operation data is stored. FIG. 5 is an explanatory diagram of processing in which operation data is stored in an operation data storage unit. FIG. 6 is a flowchart illustrating an example of an abnormality location identification processing executed by the identification device according to the first embodiment. FIG. 7 is a diagram illustrating an example of an abnormality display screen. FIG. 8 is a diagram illustrating another example of an abnormality display screen. FIG. 9 is a diagram illustrating an example of a connection relationship display field that displays the connection relationship of a cooperative servo system. FIG. 10 is a diagram illustrating an example of a configuration of a production system according to a second embodiment of the present disclosure. FIG. 11 is a flowchart illustrating an example of an abnormality cause identification processing by the identification device according to the second embodiment. FIG. 12 is a diagram illustrating an example of an abnormality display screen.

[0009] (Findings underlying the present disclosure) In production equipment that uses servo motors, multiple servo motors often operate in coordination. Specifically, multiple servo motors are mechanically connected to each other via belts, or multiple servo motors are mechanically connected via arm elements, such as in a robot arm.

[0010] In such production equipment, it is possible to identify abnormalities in multiple servo motors using measurement signals from built-in sensors. However, if an abnormality occurs in the connection mechanism that mechanically connects multiple servo motors, there is a problem in that if a sensor is not attached to the connection mechanism, it is not possible to identify the connection mechanism as the abnormal location.

[0011] If sensors were attached to all connection mechanisms where an abnormality may occur, it would be possible to identify the connection mechanisms as abnormal locations based on measurement signals from the sensors. However, due to cost constraints, it is difficult to install sensors in all connection mechanisms. Furthermore, due to physical constraints, it is difficult to install sensors in some locations.

[0012] Conventional techniques for estimating the cause of an abnormality, such as that described in Patent Document 1, have the problem that they are unable to identify a connection mechanism in which no sensor is installed as an abnormality location, as described above.

[0013] The present disclosure has been made to solve such problems, and aims to provide a technology that can identify a connection mechanism that mechanically connects servo motors as an abnormality without installing a sensor in the connection mechanism.

[0014] (1) An identification method according to one aspect of the present disclosure is a method for identifying an abnormality in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, wherein a computer acquires connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism, acquires an abnormality level for each of the plurality of servo motors, and identifies the abnormality in each of the plurality of servo motors and the connection mechanism based on the abnormality level for each of the plurality of servo motors and the connection relationship information, and displays the abnormality on a display.

[0015] According to this configuration, since the abnormality level of each of the plurality of servo motors and the connection relationship information indicating the mechanical connection relationship of the plurality of servo motors are acquired, it is possible to identify not only the plurality of servo motors but also the connection mechanism as an abnormal part based on these abnormality levels and the connection relationship information. Therefore, it is possible to identify the connection mechanism as an abnormal part without installing a sensor on the connection mechanism.

[0016] (2) In the identification method described in (1) above, the connection relationship information may be configured as graph data in which each of the plurality of servo motors is represented by a plurality of blocks and the connection relationships are represented by lines connecting the plurality of blocks, and the graph data may be generated based on an input operation by an operator.

[0017] In this case, the connection relationship information is configured using graph data in which the servo motors are shown as blocks and the connection mechanisms are shown as wires, so that the connection relationship information can be expressed in an easy-to-understand manner.

[0018] (3) In the identification method described in (2) above, the graph data may be displayed on the display, and a mark indicating that the block or the connection corresponding to the abnormal location is the abnormal location may be displayed.

[0019] In this case, the abnormality can be clearly indicated.

[0020] (4) In the identification method described in any of (1) to (3) above, if the connection relationship information is not acquired, the abnormal part may be identified from each of the plurality of servo motors based on the abnormality degree of each of the plurality of servo motors, and the abnormality degree corresponding to each of the plurality of servo motors may be displayed on the display, and the abnormality degree of the servo motor identified as the abnormal part may be highlighted on the display.

[0021] In this case, even if the connection relationship information cannot be acquired, it is possible to avoid a situation in which an abnormality in the servo motor is not notified.

[0022] (5) In the identification method described in any one of (1) to (4) above, when the plurality of servo motors includes a first servo motor and a second servo motor connected to the first servo motor via the connection mechanism and operating due to operation of the first servo motor, identifying the abnormality location may include determining whether the abnormality level of each of the first servo motor and the second servo motor indicates an abnormality, identifying the connection mechanism of the first servo motor and the second servo motor as the abnormality location when it is determined that the abnormality levels of both the first servo motor and the second servo motor indicate an abnormality, and identifying the one servo motor of the first servo motor and the second servo motor as the abnormality location when it is determined that the abnormality level of the servo motor indicates an abnormality.

[0023] In this case, it is possible to accurately identify which of the first servo motor, the second servo motor, or the connection mechanism is the abnormal part, in the first servo motor and the second servo motor, which have a causal relationship in operation.

[0024] (6) In the identification method described in any one of (1) to (7) above, when the servo system includes an operation unit composed of a plurality of cooperative servo motors among the plurality of servo motors that operate in cooperation with each other, identifying the abnormality location may include determining whether the abnormality level of each of the plurality of cooperative servo motors indicates an abnormality, identifying the operation unit as the abnormality location when it is determined that the abnormality levels of all of the plurality of cooperative servo motors indicate an abnormality, and identifying the cooperative servo motor whose abnormality level indicates an abnormality as the abnormality location when it is determined that the abnormality levels of all of the plurality of cooperative servo motors do not indicate an abnormality.

[0025] In this case, it is possible to accurately identify which of the cooperative servo motors or the operating unit is the abnormal part in a plurality of cooperative servo motors.

[0026] (7) The identification method described in any one of (1) to (6) above may further acquire target operation data from the servo system, search for registered operation data having the greatest similarity to the target operation data from among a plurality of registered operation data pre-registered in a memory and associated with abnormality cause information indicating the cause of the abnormality, estimate the abnormality cause indicated by the abnormality cause information associated with the searched registered operation data as the abnormality cause of the servo system, and further display the estimated abnormality cause on the display.

[0027] In this case, the cause of the abnormality indicated by the target operation data can be accurately identified, and the identified cause of the abnormality can be presented.

[0028] (8) In the identification method described in (7) above, the target operation data and the plurality of registered operation data may each include a command signal for driving the servo motor, a measurement signal of the servo motor when the servo motor operates based on the command signal, and the degree of abnormality, and the display may include displaying the command signal, the measurement signal, and the degree of abnormality contained in the searched registered operation data, and the command signal, the measurement signal, and the degree of abnormality contained in the target operation data.

[0029] In this case, the command signal, measurement signal, and abnormality cause information contained in the searched registered operation data are displayed along with the command signal, measurement signal, and abnormality level corresponding to the target operation data, allowing the operator to analyze the cause of the abnormality by comparing these signals.

[0030] (9) In the identification method described in (8) above, the plurality of registered operation data may further include at least one of the operator's judgment result of normality or abnormality, the measurement date and time of the searched registered operation data, and a description of the restoration work for restoring the servo system to normal operation, and the display may further include displaying at least one of the judgment result, the measurement date and time, and the description of the restoration work associated with the searched registered operation data.

[0031] In this case, at least one of the judgment results, measurement date and time, description of the cause, and description of the recovery work contained in the searched registered operation data is displayed, thereby presenting information useful for analyzing the cause of the abnormality.

[0032] (10) In the identification method described in (8) or (9) above, the display may further include displaying the command signal, the measurement signal, and the degree of abnormality contained in the searched registered operation data and the command signal, the measurement signal, and the degree of abnormality contained in the target operation data in a manner that allows the operation modes to be distinguished.

[0033] In this case, the command signals, measurement signals, and abnormality levels contained in the searched registered operation data and the command signals, measurement signals, and abnormality levels corresponding to the target operation data are displayed in a manner that allows them to be distinguished for each operation mode, so that the cause of the abnormality can be analyzed for each operation mode.

[0034] (11) In the identification method described in (8) or (9) above, the similarity may be the similarity between the command signal included in the plurality of registered motion data and the command signal included in the target motion data.

[0035] In this case, the similarity can be calculated accurately.

[0036] (12) In the identification method described in any one of (1) to (11) above, the computer may be any one of a servo amplifier, a motion controller, a personal computer, and a cloud server.

[0037] In this case, the abnormal location is identified by one of the servo amplifier, the motion controller, the personal computer, and the cloud server.

[0038] (13) In another aspect of the present disclosure, an identification device is an identification device that identifies an abnormality in a servo system that includes a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, wherein a processor of the identification device acquires connection relationship information that indicates the mechanical connection relationship between the plurality of servo motors and the connection mechanism, acquires an abnormality level for each of the plurality of servo motors, and identifies the abnormality in each of the plurality of servo motors and the connection mechanism based on the abnormality level for each of the plurality of servo motors and the connection relationship information, and displays the abnormality on a display.

[0039] According to this configuration, it is possible to provide an identification device that can identify the connection mechanism as an abnormal location without installing a sensor in the connection mechanism.

[0040] (14) In another aspect of the present disclosure, an identification program causes a computer to execute an identification method for identifying an abnormality in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, and causes the computer to execute the following processing: acquire connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism; acquire the abnormality level of each of the plurality of servo motors; identify the abnormality in each of the plurality of servo motors and the connection mechanism based on the abnormality level of each of the plurality of servo motors and the connection relationship information; and display the abnormality in the each of the plurality of servo motors and the connection mechanism;

[0041] According to this configuration, it is possible to provide an identification program that can identify the connection mechanism as an abnormal location without installing a sensor in the connection mechanism.

[0042] The present disclosure can also be realized as an abnormality location identification system that operates by such an abnormality location identification program. Needless to say, such a computer program can be distributed on a computer-readable non-transitory recording medium such as a CD-ROM or via a communication network such as the Internet.

[0043] Note that each of the embodiments described below represents a specific example of the present disclosure. The numerical values, shapes, components, steps, and step orders shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concept are described as optional components. Furthermore, in all of the embodiments, the respective contents can be combined.

[0044] 1 is a diagram illustrating an example of the configuration of a production system 1 according to a first embodiment of the present disclosure. The production system 1 includes an identification device 10, a motion controller 20, a servo amplifier 30, and a servo system 40. The motion controller 20, the servo amplifier 30, and the servo system 40 configure a production facility 60. The production facility 60 is an example of a facility.

[0045] The identification device 10 is a device that identifies an abnormality in a servo system 40. The servo system 40 includes a plurality of servo motors M and a connection mechanism K that mechanically connects the plurality of servo motors M. The connection mechanism K is composed of mechanical members that transmit the power of one servo motor M to the other servo motor M. Examples of the connection mechanism K include a belt, an arm mechanism that connects multiple joints of a robot arm, and a plate. The configuration of the servo system 40 will be described in detail below.

[0046] The identification device 10 may be configured as a personal computer installed at the site where the motion controller 20, servo amplifier 30, and servo system 40 are installed, or may be configured as a cloud server. The motion controller 20, servo amplifier 30, and identification device 10 are connected via a network NT. Examples of the network NT are a local area network or the Internet. The motion controller 20 and servo amplifier 30, and the servo amplifier 30 and servo system 40 are connected via a LAN cable or the like.

[0047] The servo system 40 includes, for example, a production device used to produce a product. An example of a production device is an industrial robot that performs, for example, equipment mounting, processing, machining, or transport. The servo system 40 includes a work arm that grips and processes parts. The work arm includes multiple arm elements and one or more joints that connect the multiple arm elements. The production device is installed, for example, on a factory production line. The production device has been described as being composed of an industrial robot, but this is just one example, and the production device may be composed of any device that is driven by a servo motor.

[0048] The servo motor M is a motor that precisely operates the production equipment in accordance with a drive signal output from the servo amplifier 30. For example, the servo motor M is provided at a joint of a working arm and rotates the arm element in the forward or reverse direction by a predetermined angle. The servo motor M includes a sensor (not shown) that detects the state of the servo motor M, and inputs a measurement signal detected by the sensor to the servo amplifier 30. An example of a sensor is a torque sensor that detects the torque of the servo motor M. Therefore, the measurement signal is a torque signal. However, this is just one example, and the measurement signal may be an acceleration signal or a velocity signal, and is not limited to a torque signal.

[0049] The servo amplifier 30 controls the servo motor M so that the servo motor M operates in accordance with the command signal output from the motion controller 20. The servo amplifier 30 generates a drive signal according to the command signal output from the motion controller 20 and inputs it to the servo motor M. The servo amplifier 30 feedback-controls the servo motor M based on the measurement signal output from the servo motor M so that the servo motor M operates in accordance with the command signal.

[0050] The motion controller 20 generates a command signal for operating the servo motor M in a predetermined operation pattern, and inputs the generated command signal to the servo amplifier 30. The command signal is time-series data that specifies the position of the servo motor M from the start to the end of a certain operation pattern.

[0051] The command signal has been described as a position command signal that specifies the position of the servo motor M, but this is just one example, and the command signal may be a speed command signal, an acceleration command signal, or a torque command signal that specifies the speed, acceleration, or torque of the servo motor M. Alternatively, the command signal may include at least two of the position command signal, the speed command signal, the acceleration command signal, and the torque command signal.

[0052] The identification device 10 includes a processor 11, a communication device 12, an input device 13, a display 14, and a memory 15. The processor 11 is configured as a central processing unit (CPU), and includes an acquisition unit 111, a first identification unit 112, and a display control unit 113. Note that the acquisition unit 111 to the display control unit 113 may be configured as dedicated integrated circuits such as ASICs.

[0053] The acquiring unit 111 acquires the command signals and measurement signals transmitted from the servo amplifier 30 using the communication device 12. The acquiring unit 111 generates operation data based on the acquired command signals and measurement signals, and stores the generated operation data in the operation data storage unit 151.

[0054] The acquisition unit 111 acquires connection relationship information indicating the mechanical connection relationships between the multiple servo motors M and the connection mechanism K from the connection relationship information storage unit 154. The connection relationship information is configured as graph data in which each of the multiple servo motors M is represented by a plurality of blocks and the connection relationships are represented by lines connecting the multiple blocks. This graph data is generated based on an input operation by an operator. The operator generates the graph data by placing blocks corresponding to the servo motors M on the screen of a drawing application based on the configuration of the actual servo system 40 and connecting the placed blocks with lines according to the connection relationships between the servo motors M. The acquisition unit 111 generates connection relationship information including the input graph data and stores the generated connection relationship information in the connection relationship information storage unit 154. Therefore, the connection relationship information is information created in advance. The operator is a person who manages the production equipment 60.

[0055] The acquisition unit 111 acquires the degree of abnormality that indicates the temporal change in the degree of abnormality of each of the plurality of servo motors M. In detail, the acquisition unit 111 acquires the degree of abnormality by inputting the command signal and the measurement signal transmitted from the servo amplifier 30 into the learning model stored in the learning model storage unit 152.

[0056] The learning model is generated by performing unsupervised machine learning on operational data (hereinafter referred to as normal data) of the servo system 40 under normal conditions. The learning model is a model that receives command signals and measurement signals and outputs the degree of abnormality of the servo system 40 based on the input command signals and measurement signals. Therefore, the command signals and measurement signals under normal conditions included in the operational data stored in the operation data storage unit 151 are used as learning data for the learning model.

[0057] As the learning model algorithm, for example, the k-nearest neighbor method or the k-means method can be adopted. The degree of anomaly is an index that represents the degree of deviation between the operation data and normal data, and the value increases as the degree of deviation from normal data increases, and decreases as the degree of deviation from normal data decreases.

[0058] An example of the processing of the learning model when the k-nearest neighbor method is adopted will be described below. The learning model calculates the distance between a command signal and a measurement signal to be judged and multiple command signals and measurement signals in normal states. Next, the learning model extracts the top k normal command signals and measurement signals from the multiple normal command signals and measurement signals in descending order of distance from the command signal and measurement signal to be judged. Next, the learning model calculates the average value of the distances between the extracted top k command signals and measurement signals and the command signal and measurement signal to be judged as the degree of abnormality. Note that the distance is the Euclidean distance between a vector defined by the values ​​of the command signal and measurement signal in normal states at a certain time point t and a vector defined by the values ​​of the command signal and measurement signal to be judged at time point t. As a result, the degree of abnormality is composed of time series data calculated according to time point t.

[0059] The first identifying unit 112 identifies an abnormal part from each of the plurality of servo motors M and the connection mechanism K based on the abnormality degree of each of the plurality of servo motors M and the connection relationship information. Details of the identification of the abnormal part will be described later.

[0060] The display control unit 113 displays the abnormality location identified by the first identifying unit 112 on the display 14 .

[0061] The display control unit 113 displays the graph data included in the connection relationship information on the display 14, and displays a mark indicating that the block or connection corresponding to the abnormal location is an abnormal location.

[0062] The communication device 12 connects the identification device 10 to the network NT. The communication device 12 receives command signals and measurement signals corresponding to the command signals from the servo amplifier 30. The communication device 12 may also receive command signals and measurement signals corresponding to the command signals from the motion controller 20.

[0063] The input device 13 is configured with a mouse, a keyboard, a touch panel, or the like, and receives instructions from the user.

[0064] The display 14 is configured with a display device such as a liquid crystal display or an organic EL display, and displays an abnormality display screen 700 shown in FIG.

[0065] The memory 15 is configured by a hard disk drive (HDD) or a solid state drive (SSD), and includes an operation data storage unit 151, a learning model storage unit 152, a threshold storage unit 153, and a connection relationship information storage unit 154.

[0066] The motion data storage unit 151 stores the motion data generated by the acquisition unit 111 .

[0067] The learning model storage unit 152 stores a learning model that receives a command signal and a measurement signal and outputs an abnormality level. The learning model may be configured as a learning model that has been pre-machine-trained for each operation mode. For example, the learning model may be configured as a learning model corresponding to an acceleration mode, a deceleration mode, a transient mode, and a steady mode. For example, a learning model for acceleration mode is generated by unsupervised machine learning of a command signal and a measurement signal in a normal state in acceleration mode. In this case, the acquisition unit 111 calculates the abnormality level by inputting the command signal and the measurement signal into the learning model for the corresponding operation mode, such as inputting the command signal and the measurement signal for acceleration mode into the learning model for acceleration mode and inputting the command signal and the measurement signal for deceleration mode into the learning model for deceleration mode.

[0068] The threshold storage unit 153 stores thresholds to be compared with the abnormality degrees calculated by the learning model. In this embodiment, the thresholds stored correspond to the acceleration mode, deceleration mode, transient mode, and steady mode, respectively.

[0069] 2 is a diagram for explaining the operation modes, which shows, from top to bottom, the waveforms of a position command signal, a velocity command signal, an acceleration command signal, and a measurement signal.

[0070] The operating period of the servo motor M is divided into an acceleration period P1, a deceleration period P2, and a constant speed period P3. The constant speed period P3 is further divided into a transient period P31 including the initial period of the constant speed period P3, and a steady period P32 including the final period of the constant speed period P3. The transient period P31 is a period during which the value of the speed command signal is zero but the value of the measurement signal is greater than a predetermined value due to inertia. The steady period P32 is a period during which the value of the measurement signal is equal to or less than the predetermined value.

[0071] The acquisition unit 111 acquires a position command signal from the servo amplifier 30 and generates a speed command signal by differentiating the acquired position command signal. The acquisition unit 111 generates an acceleration command signal by differentiating the speed command signal. The acquisition unit 111 sets a period during which the absolute value of the acceleration command signal is equal to or greater than a certain value and has a positive sign as an acceleration period P1. The acquisition unit 111 sets a period during which the absolute value of the acceleration command signal is equal to or greater than a certain value and has a negative sign as a deceleration period P2. The acquisition unit 111 sets a period during which the absolute value of the acceleration command signal is less than a certain value as a constant speed period P3. The acquisition unit 111 sets a period from the start of the constant speed period P3 until a predetermined time has elapsed as a transient period P31. The acquisition unit 111 sets the remaining period from the end of the transient period P31 in the constant speed period P3 as a steady period P32.

[0072] The acquisition unit 111 determines that the operating mode of the servo motor M during the acceleration period P1 is the acceleration mode, the operating mode of the servo motor M during the deceleration period P2 is the deceleration mode, the operating mode of the servo motor M during the constant speed period P3 is the constant speed mode, the operating mode of the servo motor M during the transient period P31 is the transient mode, and the operating mode of the servo motor M during the steady period P32 is the steady mode.

[0073] FIG. 3 is a graph 300 showing the relationship between the threshold and the degree of abnormality. In FIG. 3, the vertical axis represents the degree of abnormality, and the horizontal axis represents time. The degree of abnormality 303 is divided into an acceleration period P1, a deceleration period P2, and a constant-speed period P3. The constant-speed period P3 is further divided into a transient period P31 and a steady-state period P32. A different threshold value 302 is set for each operating period, i.e., a different value for each operating mode. In this example, the threshold value 302 decreases in the order of acceleration period P1, deceleration period P2, transient period P31, and steady-state period P32. If the degree of abnormality 303 is equal to or greater than the threshold value 302, the acquisition unit 111 determines that the servo system 40 is abnormal. If the degree of abnormality 303 is less than the threshold value, the acquisition unit 111 determines that the servo system 40 is normal. Therefore, for example, the steady-state period P32 is more likely to be determined to be abnormal than the acceleration period P1 and the deceleration period P2. In this way, by setting different threshold values ​​depending on the operating mode, appropriate abnormality determination can be performed depending on the operating mode.

[0074] 4 is a flowchart showing an example of processing by the identification device 10 in the storage phase in which operation data is stored. First, in step S1, the acquisition unit 111 acquires command signals and measurement signals transmitted from the servo amplifier 30 using the communication device 12. When the production equipment 60 is in operation, the servo amplifier 30 transmits command signals and measurement signals at a predetermined sampling rate, and therefore the acquisition unit 111 acquires the command signals and measurement signals at the predetermined sampling rate.

[0075] Next, in step S2, the acquisition unit 111 generates operation data by assigning identifiers to the command signals and measurement signals acquired in step S1. Here, the operation data is managed in units of one operation pattern. Therefore, when the acquisition unit 111 acquires all the time-series data of the command signals and measurement signals from the start to the end of one operation pattern, the acquisition unit 111 assigns identifiers and the measurement dates and times of the operation data to the time-series data of the command signals and measurement signals, and generates operation data.

[0076] Next, in step S3, the acquisition unit 111 stores the operation data generated in step S2 in the operation data storage unit 151. Note that the operator can input the normal / abnormal determination result, a description of the cause of the abnormality, and a description of the work required to restore the production equipment 60 to normal operation for the stored operation data from a cause display screen 900 described in embodiment 2. When this information is input, the acquisition unit 111 simply includes this information in the contents of the operation data. When the processing of step S3 is completed, the processing returns to step S1. That is, the processing of FIG. 4 is repeatedly executed while the production equipment 60 is in operation.

[0077] 5 is an explanatory diagram of the process by which operation data is stored in the operation data storage unit 151. When the acquisition unit 111 acquires a command signal and a measurement signal corresponding to one operation pattern, it inputs the acquired command signal and measurement signal into a learning model to calculate the degree of abnormality. The acquisition unit 111 compares the degree of abnormality with a threshold value and determines whether the servo system 40 is abnormal or normal. If the acquisition unit 111 determines that there is an abnormality, it associates an abnormal label with the command signal and the measurement signal. On the other hand, if the acquisition unit 111 determines that there is a normality, it associates a normal label with the command signal and the measurement signal.

[0078] When an operator who has actually confirmed whether or not there is an abnormality in the servo system 40 inputs an instruction indicating that there is an abnormality using the input device 13, the acquisition unit 111 associates an abnormality label with the command signal and the measurement signal. On the other hand, when an instruction indicating that there is a normality using the input device 13 is input by the operator, the acquisition unit 111 associates a normality label with the command signal and the measurement signal.

[0079] When an operator inputs a comment using the input device 13, the acquisition unit 111 associates the comment with the command signal and the measurement signal. The comment includes the date and time when the abnormality occurred, a memo describing the confirmation content of the servo system 40, the content of the recovery work, etc.

[0080] The acquiring unit 111 generates operation data by associating labels and comments with command signals and measurement signals, and stores the generated operation data in the operation data storage unit 151. At this time, the acquiring unit 111 stores operation data including a normal label in the normal data storage unit 161, and stores operation data including an abnormal label in the abnormal data storage unit 162.

[0081] In this way, the acquiring unit 111 distinguishes between the action data including the normal label and the action data including the abnormal label and stores the data in the action data storage unit 151 .

[0082] 6 is a flowchart showing an example of an abnormal portion identification process executed by the identification device 10 according to Embodiment 1. In step S11, the acquisition unit 111 acquires connection relationship information from the connection relationship information storage unit 154.

[0083] Next, in step S12 , the acquisition unit 111 acquires the command signal and the measurement signal from the servo amplifier 30 .

[0084] Next, in step S14, the acquisition unit 111 acquires the degree of abnormality by inputting the command signal and the measurement signal acquired in step S12 into a learning model.

[0085] Next, the first identifying unit 112 identifies the abnormality location based on the connection relationship information acquired in step S11 and the abnormality degree acquired in step S13.

[0086] FIG. 7 is a diagram showing an example of an abnormality display screen 700. Details of the abnormality location identification process will be described below using FIG. 7. The abnormality display screen 700 includes a connection relationship display field 710 and an abnormality degree display field 720. The connection relationship display field 710 displays graph data included in the connection relationship information. In this example, a servo system 40 including three servo motors M1, M2, and M3 and two connection mechanisms K1 and K2 is displayed. The servo motors M1, M2, and M3 are each displayed as a block. The connection mechanisms K1 and K2 are each displayed as a line connecting the blocks.

[0087] Servo motors M1 and M2 are connected via a connection mechanism K1. The connection mechanism K1 transmits the operation of servo motor M1 to servo motor M2. Servo motor M2 operates due to the operation of servo motor M1. Servo motors M2 and M3 are connected via a connection mechanism K2. The connection mechanism K2 transmits the operation of servo motor M2 to servo motor M3. Servo motor M3 operates due to the operation of servo motor M2.

[0088] The arrows of the connections indicate the direction of power transmission of the servo motors M. In this example, power is transmitted from servo motor M1 to servo motor M2, and from servo motor M2 to servo motor M3. Therefore, the arrows of the connections corresponding to the connection mechanism K1 point from servo motor M1 to servo motor M2, and the arrows of the connections corresponding to the connection mechanism K2 point from servo motor M2 to servo motor M3. In this way, the connection relationship of the servo system 40 in which one servo motor M operates due to the operation of the other servo motor M is called a causal type.

[0089] The abnormality level display field 720 displays a graph showing the temporal change in the abnormality level of each of the servo motors M1 to M3 displayed in the connection relationship display field 710. The vertical axis of the graph represents the abnormality level, and the horizontal axis represents time. Abnormality levels 721, 722, and 723 indicate the abnormality levels of the servo motors M1, M2, and M3, respectively.

[0090] In this example, the abnormality level 721 of servo motor M1 does not exceed the threshold, but the abnormality level 722 of servo motor M2 exceeds the threshold. After that, the abnormality level 723 of servo motor M3 exceeds the threshold. Servo motors M are components that are inherently unlikely to fail. Therefore, it is unlikely that an abnormality has occurred in both servo motors M2 and M3, and it is more likely that an abnormality has occurred in connection mechanism K2. Therefore, the first identifying unit 112 does not identify servo motors M2 and M3 as the abnormal location, but rather identifies connection mechanism K2 as the abnormal location.

[0091] That is, the first identifying unit 112 determines whether the abnormality levels 721, 722, and 723 of the servo motor M1 (an example of a first servo motor), the servo motor M2 (an example of first and second servo motors), and the servo motor M3 (an example of a second servo motor) indicate an abnormality. Here, the first identifying unit 112 may determine that the abnormality levels 721 to 723 indicate an abnormality if the period during which the abnormality levels 721 to 723 exceed their thresholds is equal to or longer than a predetermined time. If the first identifying unit 112 determines that the abnormality levels of both the servo motor M2 and the servo motor M3 indicate an abnormality, it identifies the connection mechanism K2 provided between the servo motor M2 and the servo motor M3 as the abnormal location.

[0092] FIG. 8 is a diagram showing another example of the abnormality display screen 700. In FIG. 8, the configuration of the servo system 40 is the same as in FIG. 7. In this example, the abnormality level 722 indicates an abnormality only for the servo motor M2. Therefore, the first identifying unit 112 identifies the servo motor M2 as the abnormal location. In other words, when the first identifying unit 112 determines that the abnormality level of one of the servo motors M2 and M3 on both sides of the connection mechanism indicates an abnormality, it identifies the other servo motor M2 as the abnormal location, not the connection mechanism K2.

[0093] 9 is a diagram showing an example of a connection relationship display field 710 that displays the connection relationships of a cooperative servo system 40. Hereinafter, a method for identifying an abnormality in the cooperative servo system 40 will be described with reference to FIG. 9. The cooperative type is a servo system 40 in which a plurality of servo motors M cooperate to operate one connection mechanism K. For example, a configuration in which a vehicle axle is operated cooperatively by a plurality of servo motors M corresponds to the cooperative servo system 40.

[0094] The servo system 40 shown in Fig. 9 includes two operating units 901 and 902. The operating unit 901 includes four servo motors M1 to M4. The servo motors M1 to M4 are an example of cooperative servo motors that cooperatively operate the connection mechanism K1. An example of the connection mechanism K1 is an axle. The operating unit 902 has the same configuration as the operating unit.

[0095] The first identifying unit 112 determines that the abnormality level of only the servo motor M1 indicates an abnormality in the operational unit 901. In this case, the first identifying unit 112 identifies the servo motor M1 as the abnormal location.

[0096] On the other hand, the first identifying unit 112 has determined that the abnormality levels of the servo motors M5 to M8 in the operation unit 902 indicate an abnormality. Generally, servo motors M are unlikely to fail, so it is unlikely that all of the servo motors M5 to M8 that make up the operation unit 902 have failed simultaneously, and it is more likely that the connection mechanism K2 has failed. Therefore, the first identifying unit 112 identifies the connection mechanism K2, rather than the servo motors M5 to M8, as the abnormal location.

[0097] Assume that the abnormality levels of servo motors M1 and M2 in operation unit 901 indicate an abnormality. Although it is rare for multiple servo motors M1 and M2 to fail simultaneously, if the abnormality levels of servo motors M3 and M4 connected to the common connection mechanism K1 do not indicate an abnormality, it is highly likely that servo motors M1 and M2 have failed. In this case, the first identification unit 112 identifies servo motors M1 and M2 as the abnormal locations.

[0098] Returning to Fig. 6, in step S15, the display control unit 113 displays the abnormality location. In the example of Fig. 7, since the connection mechanism K2 is identified as the abnormality location, the display control unit 113 displays a mark R1 indicating the abnormality location for the servo motor M2. In the example of Fig. 8, since the servo motor M2 is identified as the abnormality location, the display control unit 113 displays a mark R1 for the servo motor M2. In the example of Fig. 9, since the servo motor M1 and the operating unit 902 are identified as the abnormality locations, the display control unit 113 displays a mark R1 for the servo motor M1 and the operating unit 902.

[0099] As described above, according to this embodiment, the abnormality levels of the plurality of servo motors M and the connection relationship information indicating the mechanical connection relationships of the plurality of servo motors M are acquired, so that not only the plurality of servo motors but also the connection mechanism K can be identified as an abnormal location based on these abnormality levels and the connection relationship information. Therefore, the connection mechanism K can be identified as an abnormal location without installing a sensor on the connection mechanism K.

[0100] (Embodiment 2) An identification device 10A of embodiment 2 identifies the cause of an abnormality in a servo system 40. Fig. 10 is a diagram showing an example of the configuration of a production system 1A according to embodiment 2 of the present disclosure. Note that in this embodiment, the same components as those in embodiment 1 are given the same reference numerals, and description thereof will be omitted. In the identification device 10A, the processor 11 of the identification device 10 further includes a second identification unit 114.

[0101] The acquisition unit 111 acquires command signals and measurement signals from the servo amplifier 30 and stores them in the operation data storage unit 151. Here, the acquired command signals and measurement signals are an example of target operation data. The target operation data is operation data that is the target for identifying the cause of an abnormality. In this embodiment, the operation data stored in the operation data storage unit 151 is called registered operation data.

[0102] The target operation data and the registered operation data each include a command signal for driving the servo motor M, a measurement signal of the servo motor M when the servo motor operates based on the command signal, and an abnormality degree obtained by inputting the command signal and the measurement signal into a learning model.

[0103] Each piece of registered operation data includes the operator's determination of normality or abnormality, the measurement date and time of the searched registered operation data, information on the cause of the abnormality, and a description of the restoration work required to restore normal operation of the servo system 40. The information on the cause of the abnormality is a description of the cause of the abnormality entered by the operator.

[0104] The second identification unit 114 searches for registered operation data with the highest similarity to the target operation data from among a plurality of registered operation data pre-registered in the operation data storage unit 151 and associated with abnormality cause information indicating the cause of the abnormality. The second identification unit 114 estimates the abnormality cause indicated by the abnormality cause information associated with the searched registered operation data as the cause of the abnormality in the servo system 40. The operator's normal / abnormal determination result, the operator's description of the cause of the abnormality, and a description of the work required to restore the servo system 40 to normal operation are input by the operator on the cause display screen 900. The measurement date and time of the operation data are the year, month, day, and time when the measurement signal included in the operation data was measured. Furthermore, the operation data may include a normal / abnormal determination result determined by the acquisition unit 111 based on the abnormality level output by the learning model.

[0105] The similarity is the degree of similarity between the command signal included in the multiple registered operation data and the command signal included in the target operation data. Here, the command signal included in the multiple registered operation data is called the registered command signal, and the command signal included in the target command signal is called the target command signal. The similarity is defined as the difference between the registered command signal and the target command signal. This difference is the total value obtained by adding up the differences between the value of the registered command signal and the value of the target command signal calculated for each of multiple sample points from the start point to the end point of the target command signal. The smaller the difference between the registered command signal and the target command signal, the higher the similarity.

[0106] The display control unit 113 displays the cause of the abnormality estimated by the second identifying unit 114 on the display 14 .

[0107] The display control unit 113 displays the command signal, measurement signal, and abnormality level contained in the registered motion data searched by the second identification unit 114, and the command signal, measurement signal, and abnormality level contained in the target motion data.

[0108] The display control unit 113 displays on the display 14 the determination result, the measurement date and time, a description of the cause, and a description of the recovery work associated with the searched registered operation data.

[0109] The display control unit 113 displays the command signals, measurement signals, and abnormality levels contained in the registered operation data searched by the second identification unit 114 and the command signals, measurement signals, and abnormality signals contained in the target operation data in a manner that allows the operation modes to be distinguished.

[0110] 11 is a flowchart showing an example of an abnormality cause identification process performed by the identification device 10A according to embodiment 2. First, in step S21, the acquisition unit 111 acquires target operation data from the servo amplifier 30. The target operation data includes a command signal and a measurement signal.

[0111] Hereinafter, the processes of steps S22 and S23 and the process of step S24 are performed in parallel. In step S22, the second identification unit 114 searches for registered motion data that has the greatest similarity to the target motion data from among the multiple registered motion data stored in the motion data storage unit 151. In detail, the second identification unit 114 searches for the registered motion data that has the greatest similarity by comparing the command signals included in the multiple registered motion data with the command signals included in the target motion data. Hereinafter, the registered motion data that has the greatest similarity will be referred to as the searched registered motion data.

[0112] In step S23, the second identifying unit 114 calculates the degree of abnormality of the searched and registered motion data. Specifically, the second identifying unit 114 calculates the degree of abnormality of the searched and registered motion data by inputting the command signals and measurement signals included in the searched and registered motion data into a learning model.

[0113] In step S24, the second identifying unit 114 calculates the degree of abnormality of the target motion data. Specifically, the second identifying unit 114 calculates the degree of abnormality of the target motion data by inputting the command signal and the measurement signal included in the target motion data into a learning model.

[0114] Next, in step S25, the second identification unit 114 displays on the display 14 a cause display screen 900 that displays the abnormality cause indicated by the abnormality cause information contained in the searched and registered operation data, and the respective abnormality levels of the target operation data and the searched and registered operation data.

[0115] FIG. 12 is a diagram showing an example of a cause display screen 900. A first display field 910, a second display field 920, and a third display field 930 are displayed in the right column of the cause display screen 900. The first display field 910 displays a command signal 911 of the target motion data. The second display field 920 displays a measurement signal 921 included in the target motion data and a measurement signal 922 included in the searched and registered motion data in a superimposed manner. The third display field 930 displays an abnormality level 931 of the target motion data and an abnormality level 932 of the searched motion data in a superimposed manner. In the first display field 910 to the third display field 930, the vertical axis indicates the value of each signal, and the horizontal axis indicates time. That is, the first display field 910 to the third display field 930 display the command signal 911, the measurement signals 921 and 922, and the abnormality levels 931 and 932 in chronological order.

[0116] The first to third display fields 910 to 930 distinguish between the acceleration period, deceleration period, transient period, and steady period. For example, the first to third display fields 910 to 930 distinguish between the operation periods by displaying the background of each operation period in a different color, by displaying a border around each operation period, or by displaying text indicating the operation period in each operation period. This allows the first to third display fields 910 to 930 to distinguish between the multiple operation modes.

[0117] The first display column 910 to the third display column 930 display an emphasis object 990 indicating that there has been a change in the abnormality level. Here, the emphasis object 990 is displayed during a period in which the abnormality level 931 is equal to or greater than a threshold. The emphasis object 990 is an object that displays, in a semi-transparent color, a rectangular area indicating a period in which the abnormality level 931 is equal to or greater than the threshold.

[0118] The left column of the cause display screen 900 displays an event summary display column 940 , a label display column 950 , an abnormality cause display column 960 , and a recovery content display column 970 .

[0119] The event summary display field 940 displays an event corresponding to the command signal 911 displayed in the first display field 910. An event is information indicating an occurrence in the servo system 40. In this example, an abnormality occurred during the acceleration period in operation pattern A, and a message indicating this is displayed as an event.

[0120] The label display field 950 is a field where an operator who has actually checked whether or not there is an abnormality in the servo system 40 enters the confirmation result. An operator who has determined that the servo system 40 is normal enters a comment to the effect that it is normal in the label display field 950, and an operator who has determined that there is an abnormality enters a comment to the effect that it is abnormal in the label display field 950. For example, if an abnormality actually occurs in the servo system 40 even though the determination result by the learning model is normal, the operator can enter a comment to that effect in the label display field 950. Note that the label display field 950 may display a normal label or an abnormal label generated based on the determination result of the abnormality degree 931 by the acquisition unit 111.

[0121] The abnormality cause display field 960 is a field that displays the abnormality cause indicated by the abnormality cause information included in the registered operation data. In this example, the abnormality cause is slippage of a belt connected to the servo system 40, so a comment indicating this is displayed. Note that if no abnormality cause information is associated with the searched and registered data, the abnormality cause display field 960 will be blank. In this case, the operator simply inputs the abnormality cause into the abnormality cause display field 960. As a result, the abnormality cause information indicated by the abnormality cause input into the abnormality cause display field 960 is associated with the target operation data and stored in the operation data storage unit 151. As a result, when this target operation data is subsequently searched for as searched and registered operation data, the abnormality cause display field 960 will display the abnormality cause corresponding to this searched and registered operation data.

[0122] The restoration content display field 970 is a field where the operator inputs the work content of the restoration work for the abnormal servo system 40. In this example, belt cleaning is input as the work content.

[0123] The acquisition unit 111 updates the target motion data by including in the target motion data the information entered in the event summary display field 940, the label display field 950, and the recovery content display field 970. The acquisition unit 111 also updates the target motion data by including in the target motion data abnormality cause information indicating the abnormality cause displayed in the abnormality cause display field 960. The acquisition unit 111 then stores the updated target motion data in the motion data storage unit 151. Thereby, this target motion data is used as registered motion data thereafter.

[0124] As described above, according to this embodiment, it is possible to accurately identify the cause of an abnormality indicated by the target operation data and present the identified cause of the abnormality.

[0125] (Modifications) The present disclosure can employ the following modifications.

[0126] (1) The identification device 10 may be implemented in the servo amplifier 30 or the motion controller 20, or may be implemented in a personal computer or a cloud server.

[0127] (2) The memory 15 may be implemented in the servo amplifier 30 or the motion controller 20, or may be implemented in a personal computer or a cloud server.

[0128] (3) In the first embodiment, when the acquisition unit 111 does not acquire connection relationship information, the first identifying unit 112 may identify an abnormal location from each of the multiple servo motors M based on the abnormality level of each of the multiple servo motors M. A case in which connection relationship information is not acquired corresponds, for example, to a case in which the operator has not created graph data for the servo system 40. In this case, the first identifying unit 112 may determine whether the abnormality level of each of the multiple servo motors M exceeds a threshold, and determine that a servo motor M whose abnormality level exceeds the threshold is abnormal. In this case, the display control unit 113 may highlight on the display the servo motor M determined to be abnormal. In this case, the display control unit 113 may display blocks representing servo motors M whose abnormality levels have been acquired in the connection relationship display field 710 of FIG. 7 and display a mark R1 on the blocks representing servo motors M whose abnormality levels indicate abnormality.

[0129] The present disclosure is useful in production equipment that includes servo motors.

Claims

1. A method for identifying an abnormality in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, comprising the steps of: a computer acquires connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism; acquires an abnormality level for each of the plurality of servo motors; identifies the abnormality level among each of the plurality of servo motors and the connection mechanism based on the abnormality level for each of the plurality of servo motors and the connection relationship information; and displays the abnormality level on a display.

2. The identification method according to claim 1, wherein the connection relationship information is configured as graph data in which each of the plurality of servo motors is represented by a plurality of blocks and the connection relationships are represented by lines connecting the plurality of blocks, and the graph data is generated based on an input operation by an operator.

3. The identification method according to claim 2, further comprising the steps of: displaying said graph data on said display; and displaying a mark indicating that said abnormal portion is located on a block or said connection corresponding to said abnormal portion.

4. An identification method as described in claim 1 or 2, wherein, if the connection relationship information is not obtained, the abnormal part is identified from among the plurality of servo motors based on the abnormality degree of each of the plurality of servo motors, the abnormality degree corresponding to each of the plurality of servo motors is displayed on the display, and the abnormality degree of the servo motor identified as the abnormal part is highlighted on the display.

5. The identification method according to claim 1 or 2, wherein, when the plurality of servo motors include a first servo motor and a second servo motor connected to the first servo motor via the connection mechanism and operating due to operation of the first servo motor, identifying the abnormality location includes: determining whether the abnormality level of each of the first servo motor and the second servo motor indicates an abnormality; identifying the connection mechanism of the first servo motor and the second servo motor as the abnormality location when it is determined that the abnormality levels of both the first servo motor and the second servo motor indicate an abnormality; and identifying the one of the first servo motor and the second servo motor as the abnormality location when it is determined that the abnormality level of the one of the first servo motor and the second servo motor indicates an abnormality.

6. The identification method according to claim 1 or 2, wherein, when the servo system includes an operating unit composed of a plurality of cooperative servo motors among the plurality of servo motors that operate in coordination, identifying the abnormality location includes: determining whether the abnormality degree of each of the plurality of cooperative servo motors indicates an abnormality; identifying the operating unit as the abnormality location when it is determined that the abnormality degrees of all of the plurality of cooperative servo motors indicate an abnormality; and identifying the cooperative servo motor whose abnormality degree indicates an abnormality as the abnormality location when it is determined that the abnormality degrees of all of the plurality of cooperative servo motors do not indicate an abnormality.

7. The identification method according to claim 1, further comprising the steps of: acquiring target motion data from the servo system; searching for registered motion data having the greatest similarity to the target motion data from among a plurality of registered motion data pre-registered in a memory, the plurality of registered motion data being associated with abnormality cause information indicating a cause of the abnormality; inferring the abnormality indicated by the abnormality cause information associated with the searched registered motion data as the abnormality cause of the servo system; and displaying the inferred abnormality cause on the display.

8. The identification method of claim 7, wherein the target motion data and the plurality of registered motion data each include a command signal for driving the servo motor, a measurement signal of the servo motor when the servo motor operates based on the command signal, and the degree of abnormality, and the display on the display includes displaying the command signal, the measurement signal, and the degree of abnormality contained in the searched registered motion data, and the command signal, the measurement signal, and the degree of abnormality contained in the target motion data.

9. The identification method of claim 8, wherein the plurality of registered operation data further includes at least one of the following: an operator's judgment result of normality or abnormality, the measurement date and time of the searched registered operation data, and a description of the restoration work for restoring the servo system to normal operation; and the display on the display further includes displaying at least one of the judgment result, the measurement date and time, and the description of the restoration work associated with the searched registered operation data.

10. The identification method according to claim 8 or 9, wherein the display further includes displaying the command signal, the measurement signal, and the degree of abnormality contained in the searched registered operation data, and the command signal, the measurement signal, and the degree of abnormality contained in the target operation data in a manner that enables distinction of operation mode.

11. The identification method according to claim 8 or 9, wherein the degree of similarity is a degree of similarity between the command signal included in the plurality of registered motion data and the command signal included in the target motion data.

12. The identification method according to claim 1 or 2, wherein the computer is one of a servo amplifier, a motion controller, a personal computer, and a cloud server.

13. An identification device that identifies an abnormality in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, wherein a processor of the identification device executes the following processes: acquires connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism; acquires an abnormality degree for each of the plurality of servo motors; identifies the abnormality point among each of the plurality of servo motors and the connection mechanism based on the abnormality degree for each of the plurality of servo motors and the connection relationship information; and displays the abnormality point on a display.

14. An identification program that causes a computer to execute an identification method for identifying an abnormality in a servo system including a plurality of servo motors and a connection mechanism that mechanically connects the plurality of servo motors, the identification program causing the computer to execute the following processes: acquire connection relationship information indicating the mechanical connection relationship between the plurality of servo motors and the connection mechanism; acquire the degree of abnormality of each of the plurality of servo motors; identify the abnormality in each of the plurality of servo motors and the connection mechanism based on the degree of abnormality of each of the plurality of servo motors and the connection relationship information; and display the abnormality on a display.

Images