Determination system, determination method, and determination program

Abstract

To properly determine a state of an apparatus for processing a workpiece.SOLUTION: A determination system according to one example determines a state of an apparatus including a work device and a motor for actuating the work device. The determination system includes: an acquisition unit that acquires first data acquired in response to an output of a first command to the motor in order to operate the work device at a first pressure and second data acquired in response to an output of a second command to the motor in order to operate the work device at a second pressure; a calculation unit that calculates an amount of characteristic indicating a relation between the first data and the second data; and a determination unit that determines a state of the apparatus based on the amount of characteristic.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] One aspect of the present disclosure relates to a determination system, a determination method, and a determination program. [Background technology]

[0002] Patent Document 1 describes a spot welding system having a spot welding gun that performs welding by applying pressure to a workpiece to be welded between a movable electrode tip driven by a servo motor and a fixed electrode tip facing the movable electrode tip. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5638102 Summary of the Invention [Problem to be solved by the invention]

[0004] In one aspect of the present disclosure, it is desirable to appropriately determine the state of a device that processes a workpiece. [Means for solving the problem]

[0005] A determination system according to one aspect of the present disclosure determines the state of an apparatus including a work implement and a motor for operating the work implement. The determination system includes an acquisition unit that acquires first data obtained in response to outputting a first command to the motor for operating the work implement at a first pressure and second data obtained in response to outputting a second command to the motor for operating the work implement at a second pressure, a calculation unit that calculates a feature amount indicating the relationship between the first data and the second data, and a determination unit that determines the state of the apparatus based on the feature amount.

[0006] A determination method according to one aspect of the present disclosure is executed by a determination system that determines the state of an apparatus including a work implement and a motor that operates the work implement. The determination method includes the steps of acquiring first data obtained in response to outputting to the motor a first command for operating the work implement at a first pressure and second data obtained in response to outputting to the motor a second command for operating the work implement at a second pressure, calculating a feature amount that indicates a relationship between the first data and the second data, and determining the state of the apparatus based on the feature amount.

[0007] A determination program according to one aspect of the present disclosure causes a computer to function as a determination system for determining the state of an apparatus including a work implement and a motor for operating the work implement. The determination program causes the computer to execute the steps of acquiring first data obtained in response to outputting to the motor a first command for operating the work implement at a first pressure and second data obtained in response to outputting to the motor a second command for operating the work implement at a second pressure, calculating a feature amount indicating the relationship between the first data and the second data, and determining the state of the apparatus based on the feature amount. [Effects of the Invention]

[0008] According to one aspect of the present disclosure, the state of a device for processing a workpiece can be appropriately determined. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 illustrates an example of a configuration of a robot system. [Figure 2] FIG. 2 illustrates an example of a hardware configuration of a determination device. [Figure 3] FIG. 2 is a diagram illustrating an example of a functional configuration of a determination device. [Figure 4] FIG. 10 is a diagram illustrating an example of collection of response data. [Figure 5] 10 is a flowchart illustrating an example of response data collection. [Figure 6]10 is a graph showing an example of a command and a response. [Figure 7] 10 is a flowchart illustrating an example of determining the state of a target device. [Figure 8] 10A and 10B are diagrams illustrating an example of feature amount history data and a reference window. [Figure 9] FIG. 10 is a diagram illustrating an example of determining the state of a target device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] [Robot System] In this embodiment, a determination system according to the present disclosure is applied to a determination device 4 of a robot system 1. The robot system 1 is a system that automates various tasks such as processing and assembly by having a robot execute operations taught by an operator. FIG. 1 is a diagram showing an example of the configuration of the robot system 1. In one example, the robot system 1 includes one or more robots 2, one or more robot controllers 3 corresponding to the one or more robots 2, and a determination device 4. FIG. 1 shows a configuration in which one robot 2 is connected to one robot controller 3. However, multiple robots 2 may be connected to one robot controller 3.

[0012] In one example, the robot 2 is a multi-axis, serial-link, vertical, articulated robot configured to be able to perform various processes while holding a work implement 5 at its tip. The position and orientation of the tip of the robot 2 can be freely changed within a predetermined range. The robot 2 may be a six-axis vertical, articulated robot, or a seven-axis vertical, articulated robot with six axes plus one redundant axis. In one example, multiple robots 2 are arranged so that any one of the robots 2 can perform the same process on the same workpiece placed in the same position.

[0013] The robot 2 is an example of a device that includes a work implement 5 and a motor 5a that operates the work implement 5. In the present disclosure, such a device is also referred to as a target device. The work implement is a device that processes a workpiece, for example, a device that applies some kind of physical change to the workpiece. The work implement 5 can be various devices such as a welding gun, a press, etc. The motor 5a may be a component of the work implement 5 or may be external to the work implement 5. In one example, the work implement 5 is a welding gun attached to the robot 2 as an end effector. This welding gun spot welds the workpiece using power supplied from a spot welder 6.

[0014] The robot controller 3 is a device that controls the robot 2 according to a pre-generated operation program. The operation program includes data for controlling the robot 2. The robot 2 executes a series of processes under the control of the robot controller 3. In the present disclosure, this series of processes is also referred to as a job. The smallest unit of processing that constitutes a job is referred to as a task. Therefore, a job includes one or more tasks. The robot 2 may execute various tasks, such as "picking up a part," "placing a part," "fitting a part (to a workpiece)," and "taking a standby position." The operation program indicates, for example, the order in which the tasks are executed and a path indicating the trajectory of the robot 2. The trajectory of the robot 2 refers to the path of movement of the robot 2 or its components. For example, the trajectory of the robot 2 may be the trajectory of the tip of the robot. In one example, the robot controller 3 calculates joint angle target values ​​(target angle values ​​of each joint of the robot 2) for matching the position and posture of the tip of the robot with the target values ​​indicated in the operation program, and controls the robot 2 according to the angle target values.

[0015] The determination device 4 is a computer that determines the state of the target device, the robot 2. In one example, the determination device 4 determines the state of the robot 2 based on data obtained from the robot 2, the work equipment 5, or the motor 5a. To obtain data for making this determination, the determination device 4 outputs a command to the motor 5a to operate the work equipment 5. The command refers to an instruction for controlling the work equipment 5. The determination device 4 collects responses obtained from the motor 5a, the work equipment 5, or the robot 2 that have operated in accordance with the command. The response refers to an output in response to the command, and indicates, for example, the behavior or state of an object that has operated in accordance with the command. The object may be, for example, at least one of the work equipment 5, the motor 5a, and the robot 2. In the present disclosure, data indicating the set of collected responses is also referred to as response data. The determination device 4 then determines the state of the robot 2 based on the response data.

[0016] In this disclosure, the state of the device refers to the condition of the device itself or a component of the device, for example, whether the device or component is normal or abnormal. The condition of the device itself is, for example, the condition of the robot 2. The condition of a component of the device is, for example, the condition of the work implement 5 or the motor 5a. If the work implement 5 is a welding gun, examples of abnormalities in the welding gun include wear of the electrode (electrode tip), misalignment of the axis between the pair of electrodes, deterioration of mechanical characteristics such as backlash, and abnormalities in circuit elements such as the converter IC. Possible causes of abnormalities in the device or component include aging deterioration and defective products.

[0017] [Judgment device] 2 is a diagram showing an example of the hardware configuration of the determination device 4. The determination device 4 includes a main body 10, a monitor 20, and an input device 30.

[0018] The main body 10 is composed of at least one computer. The main body 10 has a circuit 160, which has at least one processor 161, a memory 162, a storage 163, and an input / output port 164. The storage 163 records programs for configuring each functional module of the main body 10. The storage 163 is a computer-readable recording medium such as a hard disk, a non-volatile semiconductor memory, a magnetic disk, or an optical disk. The memory 162 temporarily stores programs loaded from the storage 163, calculation results of the processor 161, etc. The processor 161 configures each functional module by executing programs in cooperation with the memory 162. The input / output port 164 inputs and outputs electrical signals between the monitor 20, the input device 30, and the robot controller 3 in response to commands from the processor 161.

[0019] The monitor 20 is a device for displaying information output from the main body 10. The monitor 20 may be any device capable of displaying graphics, a specific example of which is a liquid crystal panel. The input device 30 is a device for inputting information into the main body 10. The input device 30 may be any device capable of inputting desired information, a specific example of which is a keypad, a mouse, etc.

[0020] The monitor 20 and the input device 30 may be integrated as a touch panel. For example, the main body 10, the monitor 20, and the input device 30 may be integrated as a tablet computer.

[0021] FIG. 3 is a diagram illustrating an example of the functional configuration of the determination device 4. In one example, the determination device 4 includes functional modules such as an instruction unit 101, a collection unit 102, a database 103, an acquisition unit 104, a calculation unit 105, and a determination unit 106. The instruction unit 101 is a functional module that outputs a command to the motor 5a to operate the work equipment 5. "Outputting a command to the motor" means outputting the command so that the command is ultimately transmitted to the motor. The collection unit 102 is a functional module that collects responses to the command. The database 103 is a functional module that stores the responses obtained by the collection unit 102 as response data. As long as the determination device 4 can access the database 103, the database 103 may be implemented on a computer separate from the determination device 4 or on a computer system separate from the robot system 1. The acquisition unit 104 is a functional module that acquires response data from the database 103. The calculation unit 105 is a functional module that calculates feature quantities based on the response data. In the present disclosure, a feature amount refers to a numerical value that represents a feature of the operation of a target device, for example, a numerical value that represents a feature of the operation of at least one of the robot 2, the work equipment 5, and the motor 5a. The determination unit 106 is a functional module that determines the state of the robot 2 based on the feature amount.

[0022] In the example of FIG. 3 , the instruction unit 101 transmits a command to the motor 5a via the robot controller 3, and the collection unit 102 collects a response via the robot controller 3. For example, the robot controller 3 controls the motor 5a based on the command, and the motor 5a operates the work implement 5 under its control. The robot controller 3 then receives a response to the command from at least one of the robot 2, the work implement 5, and the motor 5a, and the robot controller 3 transmits the response to the determination device 4. The determination device 4 may transmit the command and collect the response using other methods. For example, the instruction unit 101 may transmit the command directly to the motor 5a. The collection unit 102 may collect the response directly from at least one of the robot 2, the work implement 5, and the motor 5a.

[0023] 4 is a diagram showing an example of response data collection for one robot 2. In this example, the instruction unit 101 repeatedly combines actual operation and inspection operation, and the collection unit 102 stores one response record indicating the response at each inspection operation (i.e., each inspection time point) in the database 103. As a result, the database 103 stores multiple response records corresponding to multiple inspection time points as response data indicating a chronological history of responses.

[0024] In this disclosure, actual operation refers to an operation in which one or more workpieces are processed by a target device. In connection with this actual operation, one job corresponding to the processing of one workpiece is called an actual job. For example, in actual operation, robot 2 executes an actual job of spot welding a workpiece using a welding gun one or more times. In this actual job, the welding gun is energized by power supplied from spot welder 6, and the welding gun performs spot welding by heating caused by the current.

[0025] In this disclosure, an inspection operation refers to an operation in which a target device is operated to obtain a response record. This inspection operation refers to an operation in which the target device is operated without processing a workpiece. In relation to this inspection operation, performing an operation corresponding to a real job without processing a workpiece is called an empty job. When a workpiece device 5 executes an empty job, no workpiece is given to the workpiece device 5. This inspection operation (empty job) obtains a response record under conditions in which disturbance factors (external factors) related to the workpiece have been eliminated. Therefore, the response record can be said to be data indicating the state of the target device itself, or the state of the components of the target device itself.

[0026] In one example, the instruction unit 101 causes the robot 2 to execute multiple actual jobs in one actual operation, and then causes the robot 2 to execute one null job in one inspection operation. If the work equipment 5 is a welding gun, the instruction unit 101 operates the robot 2 in each inspection operation without energizing the welding gun. For example, the instruction unit 101 operates the robot 2 without energizing the welding gun and without applying pressure to the electrodes of the welding gun. The collection unit 102 stores the response record obtained from the null job in the database 103. As shown in FIG. 4, the determination device 4 repeats the processing procedure of performing one inspection operation after one actual operation multiple times, and multiple response records (e.g., a large number of response records) for one robot 2 are accumulated in the database 103.

[0027] [Judgment method] As an example of a determination method according to the present disclosure, the collection of response data executed by the determination device 4 will be described with reference to FIG. 5. FIG. 5 is a flowchart showing the processing procedure for the collection as process flow S1. That is, the determination device 4 executes process flow S1. In one example, the determination device 4 executes process flow S1 in each inspection operation of each robot 2. Therefore, in process flow S1, the robot 2 and the work equipment 5 do not process a workpiece.

[0028] In step S11, the instruction unit 101 outputs a first command to the motor 5a to operate the work implement 5 at a first pressure. This first command is, for example, a torque command. In one example, the first pressure is a pressure required to process a workpiece using the work implement 5. For example, the first pressure is a pressure applied between a pair of electrodes of a welding gun. In one example, the instruction unit 101 sends the first command to the robot controller 3, and the robot controller 3 controls the motor 5a based on the first command. In accordance with the control, the motor 5a operates the welding gun at the first pressure, and at this time, the first pressure is applied between the pair of electrodes. In this process, the instruction unit 101 outputs the first command without energizing the welding gun. For example, the instruction unit 101 outputs the first command without energizing the welding gun and with the electrodes of the welding gun in contact with each other without applying pressure.

[0029] In step S12, the collection unit 102 collects a first response to the first command. The first response is information obtained in response to outputting the first command to the motor 5a, and is typically collected when the work implement 5 and motor 5a are in a steady state. The first response may be information obtained from at least one of the robot 2, the work implement 5, and the motor 5a. In one example, the first response indicates the position of the motor 5a moving along the gun axis of the welding gun, and this position may reflect the state of the welding gun. The gun axis is represented by a straight line passing between the tips of the pair of electrodes.

[0030] In step S13, the instruction unit 101 outputs a second command to the motor 5a to operate the work implement 5 at a second pressure. This second command is, for example, a torque command. Like the first pressure, the second pressure is a pressure required to process a workpiece using the work implement 5, for example, the pressure applied between the pair of electrodes of a welding gun. The second pressure is different from the first pressure and is, for example, higher than the first pressure. In one example, the instruction unit 101 sends the second command to the robot controller 3, and the robot controller 3 controls the motor 5a based on the second command. The motor 5a operates the welding gun at the second pressure in accordance with the control, and at this time, the second pressure is applied between the pair of electrodes. In this process, the instruction unit 101 outputs the second command without energizing the welding gun. For example, the instruction unit 101 outputs the second command without energizing the welding gun and without applying pressure to the electrodes of the welding gun.

[0031] In step S14, the collection unit 102 collects a second response to the second command. The second response is information obtained in response to outputting the second command to the motor 5a, and is typically collected when the work implement 5 and the motor 5a are in a steady state. Like the first response, the second response may also be information obtained from at least one of the robot 2, the work implement 5, and the motor 5a. For example, the second response indicates the position of the motor 5a moving along the gun axis of the welding gun.

[0032] In step S15, the collection unit 102 stores a response record indicating the first response and the second response in the database 103. In one example, the collection unit 102 sets a record identifier for uniquely identifying the pair of the first response and the second response, generates a response record indicating the combination of this record identifier and the first response and the second response, and stores this response record in the database 103. The data item set as the identifier may be, for example, at least one of a sequence number, an inspection date and time, and an identifier of the robot 2. In one example, the response record may include a data item indicating a determination result based on the response indicated in the record. When the response record is stored in step S15, the determination result is a null value (null).

[0033] FIG. 6 is a graph showing an example of commands and responses during one inspection operation (i.e., one execution of process flow S1). The horizontal axis of the graph represents elapsed time, and the vertical axis represents the pressure applied to the welding gun (working device 5) and the position of motor 5a moving along the gun axis of the welding gun. In this example, instruction unit 101 outputs a first command to motor 5a to operate the welding gun at a first pressure P1. Collector 102 collects position L1 of motor 5a in a steady state as a first response to the first command. Thereafter, instruction unit 101 outputs a second command to motor 5a to operate the welding gun at a second pressure P2. Collector 102 collects position L2 of motor 5a in a steady state as a second response to the second command. As shown in this example, instruction unit 101 may output a second command to motor 5a to increase the pressure of working device 5 from the first pressure to the second pressure without decreasing the pressure of working device 5 from the first pressure. By controlling the pressure in this manner, both the pressure and the position change stepwise. In one example, the first pressure P1 is 3000 N and the second pressure P2 is 4000 N. The instruction unit 101 may output the first command and the second command and collect the first response and the second response without changing the posture of the target device. FIG. 6 shows a situation in which the pressure further increases from the second pressure P2, and the position of the motor 5a further changes in response to this change. However, such a further increase in pressure is not required.

[0034] One execution of the process flow S1 corresponds to one idle job. Each idle job is executed after an actual operation. As can be seen from FIGS. 4 and 5, the instruction unit 101 repeats a combination of an actual operation in which the robot 2 processes one or more workpieces and a process of outputting a first command and a second command to the motor 5a after the actual operation multiple times. As a result of this repeated process, the database 103 stores multiple response records for one robot 2.

[0035] As an example of a determination method according to the present disclosure, the determination of the state of a target device executed by the determination device 4 will be described with reference to FIG. 7. FIG. 7 is a flowchart showing the processing procedure for this determination as process flow S2. That is, the determination device 4 executes process flow S2. In one example, the determination device 4 executes process flow S2 for each robot 2. For example, the determination device 4 executes process flow S2 for a certain robot 2 after response data necessary or sufficient for making a determination about that robot 2 has been accumulated in the database 103.

[0036] In step S21, the acquisition unit 104 sets judgment parameters. The judgment parameters are data used to judge the state of a target device such as the robot 2. For example, the judgment parameters may include a threshold value used for judgment, or may include the size of a reference window, which will be described later. The acquisition unit 104 may set the judgment parameters based on data input by the user, or may use judgment parameters previously stored in the storage 163 as they are.

[0037] In step S22, the acquisition unit 104 acquires response data corresponding to one robot 2 from the database 103. The acquisition unit 104 may read all of the response data for that robot 2, or may read a portion of the response data corresponding to a specific time span. In either case, this response data includes first data indicating a first response and second data indicating a second response. That is, the acquisition unit 104 acquires first data obtained in response to outputting to the motor 5a a first command to operate the work implement 5 at a first pressure, and second data obtained in response to outputting to the motor a second command to operate the work implement 5 at a second pressure. The response data indicates a history of responses over time. Therefore, the acquisition unit 104 acquires time-series data of the work implement 5 operating at the first pressure as the first data, and time-series data of the work implement 5 operating at the second pressure as the second data. As described above with reference to FIGS. 4 and 5, this first data and second data are obtained by repeating a combination of actual operation and inspection operation multiple times.

[0038] In step S23, the calculation unit 105 calculates, based on the response data, a feature indicating the relationship between the first data and the second data (in other words, a feature indicating the relationship between the first response and the second response). For each of a plurality of test operations (i.e., a plurality of test time points), the calculation unit 105 calculates at least one of the difference between the first response and the second response (i.e., the difference between the first data and the second data) and the ratio between the first response and the second response (i.e., the ratio between the first data and the second data) as the feature. Through this process, the calculation unit 105 generates feature history data indicating changes over time in the feature. Regarding the calculation of the ratio, the calculation unit 105 may calculate the ratio of the second data to the first data, or the ratio of the first data to the second data.

[0039] In step S24, the determination unit 106 sets a reference window for the feature history data. In the present disclosure, the reference window refers to a range set for the feature history data to determine the state of the target device at a certain point in time. The size of the reference window is specified, for example, by a determination parameter. In the present disclosure, the point in time at which the state of the target device is determined is also referred to as the target time point. The determination unit 106 sets a reference window for the feature history data that includes multiple time points prior to the target time point. The reference window does not include the target time point.

[0040] FIG. 8 is a diagram illustrating an example of feature history data and a reference window. In this example, graph 210 shows feature history data 211 indicating a change over time in the difference between the first data and the second data. Graph 220 shows feature history data 221 indicating a change over time in the ratio between the first data and the second data. In this example, the determination unit 106 sets a reference window 212 for the feature history data 211 and a reference window 222 for the feature history data 221. The determination unit 106 sets the positions and widths of the reference windows 212 and 222 to be the same. In other words, when the determination unit 106 sets reference windows for both the difference and the ratio, the determination unit 106 matches the positions and widths of both reference windows. In the example of FIG. 8, the trend in the ratio begins to change after the elapsed time exceeds 700, indicating a high possibility that an abnormality has occurred from that point onward.

[0041] Returning to FIG. 7, in step S25, the determination unit 106 calculates statistical values ​​of the feature quantities within the reference window. As an example, when two corresponding sets of feature quantities are calculated, such as a combination of a difference and a ratio, the determination unit 106 calculates the mean (mean vector) and covariance (covariance matrix) of the two sets of feature quantities as statistical values. The mean and covariance represent a two-dimensional multivariate normal distribution. Alternatively, the determination unit 106 may calculate statistical values ​​such as the mean and variance for each of the difference and ratio.

[0042] In step S26, the determination unit 106 determines the state of the robot 2 (target device) at the target time based on the feature amount at the target time and the calculated statistical value. In one example, the determination unit 106 determines the state of the robot 2 by comparing the feature amount at the target time with a given threshold set for the statistical value. The threshold is defined, for example, by a determination parameter. For example, the determination unit 106 calculates the Mahalanobis distance between the feature amount at the target time and the distribution of the feature amount within a reference window based on the feature amount at the target time and the statistical value, and determines the state of the robot 2 based on this Mahalanobis distance. If the Mahalanobis distance is equal to or less than the threshold, the determination unit 106 determines that the robot 2 is normal, and if the Mahalanobis distance exceeds the threshold, the determination unit 106 determines that the robot 2 is abnormal. The determination unit 106 may perform the determination based on a bivariate (two-dimensional) Mahalanobis distance corresponding to a combination of the difference and the ratio, or may perform the determination based on a univariate (one-dimensional) Mahalanobis distance corresponding to each of the difference and the ratio. When making a judgment based on both the difference and the ratio, the judgment unit 106 may judge that the robot 2 is normal if both Mahalanobis distances are below a threshold, and may judge that the robot 2 is abnormal if at least one of the Mahalanobis distances exceeds the threshold.

[0043] FIG. 9 shows an example of determining the state of robot 2. The multivariate normal distribution, expressed by the mean and covariance of the combination of differences and ratios, is represented by contour lines. Point cloud 301 indicates individual feature values ​​(combinations of differences and ratios) within the reference window, and box Th indicates a threshold value for the Mahalanobis distance. In this example, the determination unit 106 calculates the Mahalanobis distance, which is the distance between the feature value at the target time and the distribution of feature values ​​within the reference window, and compares the Mahalanobis distance with a threshold value (box Th). The threshold value for the Mahalanobis distance may be defined as a multiple of the standard deviation σ, e.g., 2σ, 3σ, or 4σ. The standard deviation σ indicates the variance when the distribution of data observed over multiple inspection runs (empty jobs) is assumed to be a normal distribution. If the calculated Mahalanobis distance is equal to or less than the threshold value, the determination unit 106 determines that robot 2 is normal. If the calculated Mahalanobis distance is greater than the threshold value, the determination unit 106 determines that robot 2 is abnormal. When the feature amount at the target time is represented by point 311, the Mahalanobis distance is equal to or less than the threshold, so the judgment unit 106 judges that the robot 2 is normal. When the feature amount at the target time is represented by point 312, the Mahalanobis distance exceeds the threshold, so the judgment unit 106 judges that the robot 2 is abnormal. Figure 9 shows an example of judging the state of the target device based on both the difference and the ratio.

[0044] Returning to FIG. 7, in step S27, the determination unit 106 outputs the determination result. For example, the determination unit 106 may store the determination result in a recording medium such as the storage 163. Alternatively, the determination unit 106 may display the determination result on the monitor 20 in the form of text, a computer graphic (CG) video, a still image, or the like. In one example, the determination unit 106 writes the determination result in a response record corresponding to the target time point. For example, the determination unit 106 may write a flag indicating whether the robot 2 is normal or abnormal in the response record.

[0045] As shown in step S28, the determination device 4 repeatedly executes steps S24 to S27 until all target time points to be determined have been processed. In step S24, the determination unit 106 resets the reference window by moving the position of the reference window by a predetermined amount along the time axis. For example, the determination unit 106 shifts the reference window by one time point. In FIG. 8, the arrows attached to the right ends of the reference windows 212 and 222 indicate the direction in which the reference window is moved. In step S25, the determination unit 106 calculates statistical values ​​of the feature amounts within the reset reference window. In step S26, the determination unit 106 determines the state of the robot 2 at the next target time point based on the feature amounts at that time point and the calculated statistical values. In step S27, the determination unit 106 outputs the determination result. That is, the determination unit 106 may determine the state of the robot 2 at each of multiple target time points while moving the reference window along the time axis.

[0046] When repeating the determination while simply moving the reference window along the time axis, the reference window may include the feature amount at the target time point at which the robot 2 is determined to be abnormal. In one example, when setting the reference window to determine the state of the robot 2 at a second target time point that is later than the plurality of first target time points, the determination unit 106 sets the reference window such that the first target time point at which the robot 2 is determined to be abnormal is excluded from the reference window.

[0047] A specific example of setting such a reference window will be described. 100 The reference window has a width corresponding to 10 time points. 10 Then, assuming that the robot 2 is normal, the judgment unit 106 judges that the robot 2 is normal at time T 11 In order to determine the state of robot 2 at time T1 to T 10 A reference window is set in the range of time T 11 If it is determined that the robot 2 is normal, the determination unit 106 12 In order to determine the state of robot 2 at time T2, the reference window is set to time T3. 11 Robot 2 is at time T 50It is judged to be normal up to time T 51 Assume that the determination unit 106 first determines that an abnormality exists at time T 52 To determine the state of robot 2 at time T, the reference window is set as 42 ~T 51 not in the range of 41 ~T 50 This is set to the range of the second target time T 52 When setting a reference window to determine the state of the robot 2 at the first target time T 51 This means that the reference window is set so that the time T 52 Assume that the robot 2 is determined to be normal at time T 53 To determine the state of robot 2 at time T, the reference window is set as 42 ~T 50 ,T 52 If the time T 53 Assume that the robot 2 is determined to be normal even at time T 54 To determine the state of robot 2 at time T, the reference window is set as 43 ~T 50 ,T 52 ,T 53 If the time T 54 Assume that robot 2 is determined to be abnormal at time T 55 To determine the state of robot 2 at time T, the reference window is set as 43 ~T 50 ,T 52 ,T 53 In this way, the determination unit 106 may set the reference window while excluding the first target time point determined to be abnormal so that the size of the reference window, i.e., the number of feature amounts included in the reference window, is maintained at a constant value.

[0048] [program] Each functional module of the determination device 4 is realized by loading a determination program onto the processor 161 or memory 162 and having the processor 161 execute the program. The determination program includes code for realizing each functional module of the determination device 4. The processor 161 operates the input / output port 164 in accordance with the determination program, and executes reading and writing of data from and to the memory 162 or storage 163. Each functional module of the determination device 4 is realized by such processing.

[0049] The determination program may be provided by being permanently recorded on a non-transitory recording medium such as a CD-ROM, a DVD-ROM, a semiconductor memory, etc. Alternatively, the determination program may be provided via a communication network as a data signal superimposed on a carrier wave.

[0050] [effect] As described above, a determination system according to one aspect of the present disclosure determines the state of an apparatus including a work implement and a motor for operating the work implement. The determination system includes an acquisition unit that acquires first data obtained in response to outputting a first command to the motor for operating the work implement at a first pressure and second data obtained in response to outputting a second command to the motor for operating the work implement at a second pressure, a calculation unit that calculates a feature amount indicating the relationship between the first data and the second data, and a determination unit that determines the state of the apparatus based on the feature amount.

[0051] A determination method according to one aspect of the present disclosure is executed by a determination system that determines the state of an apparatus including a work implement and a motor that operates the work implement. The determination method includes the steps of acquiring first data obtained in response to outputting to the motor a first command for operating the work implement at a first pressure and second data obtained in response to outputting to the motor a second command for operating the work implement at a second pressure, calculating a feature amount that indicates a relationship between the first data and the second data, and determining the state of the apparatus based on the feature amount.

[0052] A determination program according to one aspect of the present disclosure causes a computer to function as a determination system for determining the state of an apparatus including a work implement and a motor for operating the work implement. The determination program causes the computer to execute the steps of acquiring first data obtained in response to outputting to the motor a first command for operating the work implement at a first pressure and second data obtained in response to outputting to the motor a second command for operating the work implement at a second pressure, calculating a feature amount indicating the relationship between the first data and the second data, and determining the state of the apparatus based on the feature amount.

[0053] In this aspect, the state of the equipment is determined based on the relationship between two pieces of data obtained by operating the work equipment at each of two pressure levels. By considering the relationship between the two pieces of data, disturbance factors are eliminated, allowing the state of the equipment to be determined appropriately. If the state of the equipment were determined based on a single piece of data, i.e., an absolute value, the absolute value could fluctuate significantly due to special disturbance factors (e.g., the surrounding environment of the equipment) at the time of measurement, making it difficult to objectively determine the state of the equipment. Because the feature value indicating the relationship between the first and second data is a relative value, the influence of the disturbance factors is eliminated. Therefore, by using the feature value, the state of the equipment can be determined stably and accurately. One aspect of the present disclosure, for example, enables automatic determination without relying on the knowledge and experience of an operator, thereby enabling early detection of equipment abnormalities and efficient identification of defective units.

[0054] In a determination system according to another aspect, the calculation unit may calculate a difference between the first data and the second data and a ratio between the first data and the second data as feature quantities, and the determination unit may determine the state of the device based on both the difference and the ratio. By taking into account two types of feature quantities (relative values), the difference and the ratio, the state of the device can be determined reliably. For example, an abnormality in the device can be reliably detected.

[0055] In another aspect of the determination system, the acquisition unit acquires time-series data of the work equipment operating at a first pressure as first data and time-series data of the work equipment operating at a second pressure as second data. The calculation unit generates feature history data indicating changes in the feature over time. In order to determine the state of the equipment at a target time, the determination unit may set a reference window including multiple time points prior to the target time for the feature history data, calculate statistical values ​​of the feature within the reference window, and determine the state of the equipment based on the feature and statistical values ​​at the target time. The first data and the second data fluctuate over time, and the feature history data also fluctuates accordingly. By calculating statistical values ​​of the feature over a predetermined time span in the past and considering the statistical values ​​and the feature at the target time, the state of the equipment at the target time can be accurately determined even in situations where data fluctuates.

[0056] In the determination system according to another aspect, the determination unit may calculate the average and covariance of the feature amounts within the reference window as statistical values. By taking the average and covariance into consideration, the state of the device can be accurately determined.

[0057] In a determination system according to another aspect, the determination unit may determine the state of the device at each of a plurality of first target time points while moving the reference window along the time axis, and when setting the reference window to determine the state of the device at a second target time point that is later than the plurality of first target time points, set the reference window so that the first target time point at which the device is determined to be abnormal is excluded from the reference window. This process allows the reference window to be set using data determined to be normal, without using data determined to be abnormal, so that statistics obtained from the reference window also continue to indicate normal operation of the device. Therefore, the state of the device can be accurately determined over time.

[0058] The determination system according to another aspect may further include an instruction unit that outputs the first command and the second command to the motor. This configuration makes it possible to comprehensively determine the state of the device and issue instructions for that determination.

[0059] In a determination system according to another aspect, the instruction unit may output a second command to the motor to increase the pressure of the work implement from the first pressure to the second pressure without decreasing the pressure of the work implement from the first pressure. This pressure control prevents a situation in which the pressure changes from the first pressure to the second pressure by passing through the first pressure again, thereby enabling accurate calculation of a feature quantity indicating the relationship between the first data and the second data.

[0060] In another aspect of the determination system, the work equipment may be a welding gun, and the command unit may output the first command and the second command to the motor while the welding gun is not energized. This process eliminates disturbance factors related to the welding gun, such as nuggets that occur in the welded portion of the workpiece, allowing the state of the equipment to be determined appropriately. For example, the state of the equipment can be determined stably or accurately.

[0061] In a determination system according to another aspect, the instruction unit may output a first command and a second command to the motor under conditions in which the welding gun is not energized and the electrodes of the welding gun are brought into contact with each other without applying pressure. During operation of the welding gun, the process of not energizing the welding gun and bringing the electrodes of the welding gun into contact with each other without applying pressure is performed to find a change in the distance between the pair of electrodes of the welding gun (in other words, to measure the amount of wear on the electrodes). In this aspect, the first data and the second data are collected using an opportunity to perform such necessary processing on the welding gun, thereby improving the efficiency of work related to the welding gun (e.g., inspection).

[0062] In another aspect of the determination system, the apparatus may be a robot, and the welding gun may be attached to the robot as an end effector. The welding gun attached to the robot may assume various postures in response to the operation of the robot. In this aspect, disturbance factors resulting from posture changes can be eliminated to appropriately determine the state of the apparatus.

[0063] In another aspect of the determination system, the instruction unit may repeat a combination of an actual operation in which the device processes one or more workpieces and a process of outputting a first command and a second command to the motor after the actual operation multiple times, and the acquisition unit may acquire the first data and the second data obtained by the multiple repetitions. By acquiring the first data and the second data during the actual operation, changes in the state of the device that occur as the device continues to be used can be appropriately captured as the first data and the second data.

[0064] [Variations] The present disclosure has been described in detail above based on the embodiments. However, the present disclosure is not limited to the above embodiments. Various modifications of the present disclosure are possible without departing from the spirit and scope of the present disclosure.

[0065] The functional configuration of the determination system is not limited to the above example, and the determination method according to the present disclosure may be executed using a functional configuration different from the above example.

[0066] The hardware configuration of the determination system is not limited to the implementation of each functional module by executing a program. For example, at least some of the functional modules may be configured by logic circuits specialized for the respective functions, or may be configured by an ASIC (Application Specific Integrated Circuit) that integrates such logic circuits.

[0067] The processing steps of the method executed by at least one processor are not limited to the above examples. For example, some of the steps (processing) described above may be omitted, or the steps may be executed in a different order. Also, two or more of the steps described above may be combined, or some of the steps may be modified or deleted. Alternatively, other steps may be executed in addition to the steps described above.

[0068] When comparing the magnitude of two numbers within a computer system or computer, either of the two criteria "greater than or equal to" and "greater than" can be used, or either of the two criteria "less than or equal to" and "under". [Explanation of symbols]

[0069] 1...Robot system, 2...Robot, 3...Robot controller, 4...Judgment device, 5...Work equipment, 5a...Motor, 6...Spot welding machine, 10...Main body, 20...Monitor, 30...Input device, 101...Instruction unit, 102...Collection unit, 103...Database, 104...Acquisition unit, 105...Calculation unit, 106...Judgment unit, 211, 221...Feature history data, 212, 222...Reference window

Claims

1. A determination system for determining the state of an apparatus including a welding gun and a motor for operating the welding gun, an instruction unit that outputs a first command to operate the welding gun at a first pressure and then outputs a second command to operate the welding gun at a second pressure to the motor under a condition in which the welding gun is not energized and the electrodes of the welding gun are in contact without applying pressure to each other, the instruction unit outputting the second command to the motor to increase the pressure of the welding gun from the first pressure to the second pressure without decreasing the pressure of the welding gun from the first pressure; an acquisition unit that acquires first data obtained in response to outputting the first command to the motor and second data obtained in response to outputting the second command to the motor; a calculation unit that calculates a feature amount indicating a relationship between the first data and the second data; a determination unit that determines a state of the device based on the feature amount; A determination system comprising:

2. the calculation unit calculates, as the feature amount, a difference between the first data and the second data and a ratio between the first data and the second data; the determination unit determines the state of the device based on both the difference and the ratio. The determination system according to claim 1 .

3. The acquisition unit acquiring time-series data of the welding gun operating at the first pressure as the first data; acquiring time-series data of the welding gun operating at the second pressure as the second data; the calculation unit generates feature amount history data indicating changes over time in the feature amount; The determination unit setting a reference window including a plurality of time points prior to the target time point for determining the state of the device at the target time point for the feature amount history data; Calculating a statistical value of the feature amount within the reference window; determining a state of the device based on the feature amount and the statistical value at the target time point; The determination system according to claim 1 or 2.

4. the determination unit calculates an average and a covariance of the feature amounts within the reference window as the statistical values; The determination system according to claim 3 .

5. The determination unit determining a state of the device at each of a plurality of first time points of interest while moving the reference window along a time axis; When setting the reference window to determine the state of the device at a second target time point that is later than the plurality of first target times, the reference window is set so that the first target time point at which the device is determined to be abnormal is excluded from the reference window. The determination system according to claim 3 or 4.

6. the device is a robot; The welding gun is attached to the robot as an end effector. The determination system according to any one of claims 1 to 5.

7. the instruction unit repeats a combination of an actual operation of processing one or more workpieces by the device and a process of outputting the first command and the second command to the motor after the actual operation multiple times; the acquisition unit acquires the first data and the second data obtained by the multiple repetitions. The determination system according to any one of claims 1 to 6.

8. A determination method executed by a determination system for determining the state of an apparatus including a welding gun and a motor for operating the welding gun, comprising: a step of outputting a first command to operate the welding gun at a first pressure and then outputting a second command to the motor to operate the welding gun at a second pressure under a condition where the welding gun is not energized and the electrodes of the welding gun are in contact without applying pressure, the second command being output to the motor to increase the pressure of the welding gun from the first pressure to the second pressure without decreasing the pressure of the welding gun from the first pressure; acquiring first data obtained in response to outputting the first command to the motor and second data obtained in response to outputting the second command to the motor; calculating a feature amount indicating a relationship between the first data and the second data; determining a state of the device based on the feature amount; A determination method including:

9. A judgment program that causes a computer to function as a judgment system for judging the state of an apparatus that includes a welding gun and a motor that operates the welding gun, comprising: a step of outputting a first command to operate the welding gun at a first pressure and then outputting a second command to the motor to operate the welding gun at a second pressure under a condition where the welding gun is not energized and the electrodes of the welding gun are in contact without applying pressure, the second command being output to the motor to increase the pressure of the welding gun from the first pressure to the second pressure without decreasing the pressure of the welding gun from the first pressure; acquiring first data obtained in response to outputting the first command to the motor and second data obtained in response to outputting the second command to the motor; calculating a feature amount indicating a relationship between the first data and the second data; determining a state of the device based on the feature amount; A determination program that causes the computer to execute the above.

Images