Data processing system, data processing method, and program

Abstract

Misleading is not caused by deterioration diagnosis of a servo system (7). A data processing system has an acquisition unit (2), a first generation unit (3A), a second generation unit (3B), and a presentation unit (47). The acquisition unit (2) acquires at least one of a control signal of the servo system (7) and a detection signal from a sensor (61). The first generation unit (3A) generates first data related to three or more characteristic amounts based on a prescribed region in the signal waveform. The second generation unit (3B) generates three or more second data each representing a change trend over time of the first data related to the three or more characteristic amounts. The presentation unit (47) compares the three or more second data with each other, and in a case where there is a specific second data that presents a different change trend, performs a specific processing related to an object data that is the first data that is the cause of the different change trend to present the specific second data. The specific processing includes a processing related to at least one of non-presentation of the object data, correction of the object data, and notification about the object data.

Description

Technical Field

[0001] This disclosure generally relates to a data processing system, data processing method, and program. More specifically, this disclosure relates to a data processing system, data processing method, and program used in the degradation diagnosis of a servo system. Background Technology

[0002] The degradation estimation device described in Patent Document 1 includes an inspection result acquisition unit, an attribute data acquisition unit, and an estimation unit. The inspection result acquisition unit acquires the inspection results of the equipment to be maintained. The attribute data acquisition unit acquires the attribute data of the equipment to be maintained. The estimation unit takes the inspection results and attribute data of the equipment to be maintained as inputs to estimate the degradation level of the equipment to be maintained.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-160528 Summary of the Invention

[0006] Furthermore, information related to degradation diagnosis may sometimes show temporary, irregular trends due to noise or other factors. The presentation of such information may mislead users.

[0007] This disclosure was made in view of the above reasons, and its purpose is to provide a data processing system, data processing method and procedure that is not likely to mislead the diagnosis of degradation.

[0008] One aspect of this disclosure relates to a data processing system used in the degradation diagnosis of at least one of the load and the servo motor in a servo system comprising a load, a servo amplifier, and a servo motor that powers the load under the control of the servo amplifier. The data processing system includes an acquisition unit, a first generation unit, a second generation unit, and a presentation unit. The acquisition unit acquires at least one signal from a control signal used in the control of the servo system and a detection signal output from a sensor detecting the state of the servo system. The first generation unit generates first data related to three or more characteristic quantities based on a defined region in the signal waveform of the at least one signal. The second generation unit generates three or more second data points, which are time-series data representing the degradation progression of the object, each representing a trend of change of the first data related to the three or more characteristic quantities over time. The presentation unit compares the three or more second data points with each other. In cases where a specific second data point exhibits a different trend of change than the other second data points, the presentation unit performs specific processing related to the object data to present the specific second data point, the object data being the first data causing the different trend of change. The specific processing includes at least one of the following: non-presentation of the object data, correction of the object data, and notification regarding the object data.

[0009] Another aspect of this disclosure relates to a data processing method concerning the degradation diagnosis of at least one of the following objects in a servo system: a load, a servo amplifier, and a servo motor that powers the load under the control of the servo amplifier. The data processing method includes an acquisition step, a first generation step, a second generation step, and a presentation step. In the acquisition step, at least one signal is acquired, consisting of a control signal used in the control of the servo system and a detection signal output from a sensor detecting the state of the servo system. In the first generation step, first data relating to three or more characteristic quantities is generated based on a defined region in the signal waveform of the at least one signal. In the second generation step, three or more second data points are generated, which are time-series data representing the degradation progression of the object, each representing the trend of change of the first data relating to the three or more characteristic quantities over time. In the presentation step, the three or more second data points are compared with each other. In the presentation step, if there is a specific second data point exhibiting a different trend of change than other second data points, specific processing related to the object data is implemented to present the specific second data point, which is the first data point causing the different trend of change. The specific processing includes at least one of the following: non-presentation of the object data, correction of the object data, and notification regarding the object data.

[0010] Another aspect of this disclosure relates to a program for causing one or more processors to perform the data processing method described above.

[0011] According to this disclosure, it has the advantage of not easily misleading the diagnosis of degradation. Attached Figure Description

[0012] Figure 1 It is a general module structure diagram of the system as a whole, including the data processing system involved in one implementation.

[0013] Figure 2 This is a diagram illustrating an example of screen display in the data processing system.

[0014] Figure 3 It is a graph showing the waveform of the current used as a diagnostic parameter in the data processing system.

[0015] Figure 4A It is a graph used to illustrate the first data related to feature quantity A in this data processing system.

[0016] Figure 4B It is a graph used to illustrate the first data related to feature quantity B in this data processing system.

[0017] Figure 4C It is a graph used to illustrate the first data related to the characteristic quantity C in this data processing system.

[0018] Figure 5 It is a diagram used to illustrate the second data displayed from the display device in the data processing system and its overall reliability.

[0019] Figure 6 It is a flowchart used to illustrate the actions in the data processing system. Detailed Implementation

[0020] (summary)

[0021] The data processing system, data processing method, and program involved in the embodiments will now be described with reference to the accompanying drawings. However, the embodiments described below are merely one of the various embodiments of this disclosure. The embodiments described below are acceptable as long as they achieve the objectives of this disclosure, and various modifications can be made according to design, etc.

[0022] (Feature 1)

[0023] Figure 1 This is a summary modular structure diagram of the entire system, including the data processing system 1 involved in one implementation method. For example... Figure 1 As shown, a data processing system 1 according to one method includes an acquisition unit 2 and a generation unit 3. The acquisition unit 2 acquires at least one of a control value and a detection value as input values. The control value is used in the control of a servo system 7, which includes a load 73, a servo amplifier 71, and a servo motor 72 that provides power to the load 73 according to the control of the servo amplifier 71. The detection value is output from a sensor 61 that detects the state of the servo system 7. The generation unit 3 performs at least an extraction process on the input value acquired by the acquisition unit 2 to generate diagnostic parameters. The diagnostic parameters are used for deterioration diagnosis of at least one object OB1 in the load 73 and the servo motor 72 in the servo system 7. The input value is a value that changes over time. The generation unit 3 extracts a portion of the input value during the extraction process as the diagnostic parameters.

[0024] According to the data processing system 1 described above, the value of the period extracted by the generation unit 3 from the input value can be used in the degradation diagnosis. In this way, by removing features in the input value that may hinder degradation diagnosis, the accuracy of degradation diagnosis can be improved compared to using the value of the entire period from the input value in the degradation diagnosis.

[0025] One approach involves a data processing method that includes an acquisition step and a generation step. In the acquisition step, at least one of a control value and a detection value is acquired as an input value. The control value is used in the control of a servo system 7, which includes a load 73, a servo amplifier 71, and a servo motor 72 that provides power to the load 73 according to the control of the servo amplifier 71. The detection value is output from a sensor 61 that detects the state of the servo system 7. In the generation step, the input value acquired in the acquisition step is subjected to at least an extraction process to generate diagnostic parameters. The diagnostic parameters are used for degradation diagnosis of at least one object OB1 in the load 73 and the servo motor 72 of the servo system 7. The input value is a value that changes over time. In the generation step, during the extraction process, a portion of the input value is extracted as the diagnostic parameters.

[0026] This data processing method is used on a computer system (data processing system 1). That is, this data processing method can also be implemented through a program. One type of program involves a program used to cause one or more processors to execute the aforementioned data processing method. The program can be recorded on a computer-readable, non-transitory recording medium.

[0027] (Feature 2)

[0028] In addition, such as Figure 1 As shown, in one embodiment, the data processing system 1 is used for degradation diagnosis of at least one object OB1 in the load 73 and the servo motor 72 within the servo system 7. The servo system 7 includes a load 73, a servo amplifier 71, and a servo motor 72 that provides power to the load 73 under the control of the servo amplifier 71. In the following example, the object OB1 is assumed to be the load 73, and the data processing system 1 is used for degradation diagnosis of the load 73. However, the object OB1 could also be the servo motor 72, or both the load 73 and the servo motor 72. The load 73 is not particularly limited here; it could be, for example, a ball screw, gear, or conveyor belt. The servo system 7 is used, for example, to perform a specified operation in the manufacturing process of a product (or semi-finished product).

[0029] like Figure 1 As shown, the data processing system 1 includes an acquisition unit 2, a first generation unit 3A, a second generation unit 3B, and a presentation unit 47.

[0030] The acquisition unit 2 acquires at least one of the control signals used in the control of the servo system 7 and the detection signals output from the sensor 61 that detects the state of the servo system 7.

[0031] Figure 4A , Figure 4B as well as Figure 4CThis is a graph illustrating the first data D1 and the second data D2 related to feature quantity A, feature quantity B, and feature quantity C respectively in the data processing system 1. The first generation unit 3A generates the first data D1 related to three or more feature quantities (refer to...) based on a predetermined region (all or part of the feature period exhibiting the predetermined feature) in the signal waveform of at least one signal. Figures 4A to 4C Regarding the "characteristic quantity" mentioned here, for example, it can be assumed to be a statistical characteristic quantity, specifically the average (value), standard deviation (value), maximum (value), minimum (value), or histogram characteristics within the specified region. Alternatively, the "characteristic quantity" can also be the first principal component based on so-called "principal component analysis." "Three or more characteristic quantities" can be characteristic quantities of the same type or characteristic quantities of different types. For example, when the first generation unit 3A generates first data D1 related to three characteristic quantities based on a specified region in a signal waveform (current signal waveform), the "three characteristic quantities" can be the average, standard deviation, and maximum, respectively. On the other hand, for example, when the first generation unit 3A generates first data D1 related to three characteristic quantities respectively based on specified regions in three signal waveforms (e.g., current, torque, speed signal waveforms), the "three characteristic quantities" can, for example, all be the average. Below, as an example, the first generation unit 3A generates first data D1 related to three characteristic quantities respectively based on specified regions in three signal waveforms. Figures 4A to 4C In the diagram, the first data point D1 is plotted as a point.

[0032] The second generation section 3B generates three or more second data points D2 (see reference). Figures 4A to 4C The three or more second data points D2 represent time series data indicating the degradation progression of object OB1, and respectively represent the changing trends of the first data point D1 related to the three or more feature quantities over time. Figures 4A to 4C In the diagram, each second data point D2 is plotted as a broken line formed by connecting multiple first data points D1 (plotted points) arranged in a time series.

[0033] The presentation unit 47 compares three or more second data points D2 with each other. Furthermore, it compares specific second data point D20 (see reference) that exhibits a different trend of change than the other second data points D2. Figure 4CIn the case of object data D10, the presentation unit 47 performs specific processing related to object data D10 to present specific second data D20, where object data D10 is the first data D1 that causes different trends of change. Specific processing includes at least one of the following: non-presentation of object data D10, correction of object data D10, and notification regarding object data D10. For example, if more than half of the three or more second data D2 show a monotonically decreasing trend of change, and on the other hand, less than half (e.g., one) of the second data D2 show a trend of change that is not equivalent to a monotonically decreasing trend, the latter second data D2 corresponds to the specific second data D20. Figure 4C In the example, it can be determined that the specific second data D20 has a temporary interval showing an increasing trend (time point t2~t3), and the first data D1 at time point t3 is the object data D10 that is the cause of the different changing trends.

[0034] According to the data processing system 1 described above, when there is a specific second data point D20 exhibiting a different trend, specific processing related to the object data D10 that is the cause of the different trend is performed to present the specific second data point D20. Therefore, users are less likely to misunderstand the object data D10, which is more likely to be affected by noise, as the real data. As a result, the data processing system 1 has the advantage of not easily causing misleading results in degradation diagnosis.

[0035] Additionally, one approach involves a data processing method related to the aforementioned degradation diagnosis of object OB1. The data processing method includes an acquisition step, a first generation step, a second generation step, and a presentation step. In the acquisition step, at least one signal is acquired, including a control signal used in the control of the servo system 7 and a detection signal output from a sensor 61 that detects the state of the servo system 7. In the first generation step, first data D1 related to three or more characteristic quantities is generated based on a defined region in the signal waveform of the at least one signal. In the second generation step, three or more second data D2s are generated, which are time-series data representing the degradation progression of object OB1, each representing the changing trend of the first data D1 related to the three or more characteristic quantities over time. In the presentation step, the three or more second data D2s are compared with each other. Furthermore, in the presentation step, if a specific second data D20 exhibits a different changing trend than the other second data D2s, specific processing related to object data D10 is performed to present that specific second data D20, where object data D10 is the first data D1 that causes the different changing trend. The specific processing includes at least one of the following: non-presentation of object data D10, correction of object data D10, and notification regarding object data D10. According to the above-described data processing method, it has the advantage of not easily misleading the diagnosis of degradation. This data processing method is used on a computer system (data processing system 1). That is, this data processing method can also be implemented by a program. One method involves a program for causing one or more processors to execute the above-described data processing method. The program can be recorded on a computer-readable, non-transitory recording medium.

[0036] (Feature 3)

[0037] Additionally, one aspect of the data processing system 1 involves a data processing system that outputs diagnostic parameters. The diagnostic parameters are used for degradation diagnosis of at least one object OB1 in the servo system 7, which includes a load 73, a servo amplifier 71, and a servo motor 72 that powers the load 73 under the control of the servo amplifier 71. The diagnostic parameters include at least one of a control value used in the control of the servo system 7, a detection value output from a sensor 61 that detects the state of the servo system 7, and a generated value generated based on the control value or the detection value. The data processing system 1 includes an acquisition unit 2, a reliability determination unit 44, and a reliability output unit (output unit 51). The acquisition unit 2 acquires the diagnostic parameters. The reliability determination unit 44 assigns information related to the reliability of the diagnostic parameters in the degradation diagnosis of the servo system 7 to the diagnostic parameters. The reliability output unit outputs the reliability-related information in association with the diagnostic parameters to a presentation device (display device 81).

[0038] According to the data processing system 1 described above, users can determine whether specific diagnostic parameters can be used in degradation diagnosis by referring to the reliability presented by the display device. This improves convenience for users.

[0039] One approach involves a data processing method for outputting diagnostic parameters. The diagnostic parameters are used for degradation diagnosis of at least one object OB1 in a servo system 7, including a load 73, a servo amplifier 71, and a servo motor 72 that powers the load 73 under the control of the servo amplifier 71. The diagnostic parameters include at least one of a control value used in the control of the servo system 7, a detection value output from a sensor 61 that detects the state of the servo system 7, and a generated value generated based on the control value or the detection value. The data processing method includes an acquisition step, a reliability determination step, and a reliability output step. In the acquisition step, the diagnostic parameters are acquired. In the reliability determination step, information related to the reliability of the diagnostic parameters in the degradation diagnosis of the servo system 7 is assigned to the diagnostic parameters. In the reliability output step, the reliability-related information is output to a presentation device (display device 81) in association with the diagnostic parameters.

[0040] This data processing method is used on a computer system (data processing system 1). That is, this data processing method can also be implemented through a program. One type of program involves a program used to cause one or more processors to execute the aforementioned data processing method. The program can be recorded on a computer-readable, non-transitory recording medium.

[0041] (Details)

[0042] (1) Overall structure

[0043] like Figure 1 As shown, the data processing system 1 is used together with the sensor 61, the upper controller 62, the servo system 7, the display device 81, and the operating device 82.

[0044] The data processing system 1 uses information obtained from at least one of the sensor 61 and the upper-level controller 62 to perform degradation diagnosis of the servo system 7. The display device 81 displays the diagnosis results. In addition, the user of the data processing system 1 can make settings related to degradation diagnosis by operating the operation device 82. By making appropriate settings, the accuracy of degradation diagnosis can be improved.

[0045] The data processing system 1 is located, for example, away from the facility where the servo system 7 is located (e.g., a factory). The sensor 61, the upper controller 62, the display device 81, and the operating device 82 are located, for example, in the facility where the servo system 7 is located. The sensor 61, the upper controller 62, the display device 81, and the operating device 82 communicate with the data processing system 1 via a wide area network such as the Internet.

[0046] (2) Servo System

[0047] The servo system 7 includes a servo amplifier 71, a servo motor 72, and a load 73. The data processing system 1 is used for degradation diagnosis of at least one object OB1 (here, load 73) of the load 73 and the servo motor 72. The servo motor 72 can be a linear motor or a rotary motor. In this embodiment, the case where the servo motor 72 is a rotary motor will be described as an example.

[0048] The servo motor 72 has an output shaft, which is rotated under the control of the servo amplifier 71. A load 73 is connected to the output shaft of the servo motor 72. The load 73 is powered by the servo motor 72. An example of the load 73 is a ball screw, gear, or conveyor belt. The servo system 7 is used, for example, to perform specified operations in the manufacturing process of a product (or a semi-finished product).

[0049] When the servo system 7 deteriorates, problems may occur, such as abnormal noises, oscillations, load slippage, and decreased accuracy of load 73. By performing degradation diagnosis on the servo system 7 through the data processing system 1, the user can understand whether the servo system 7 has deteriorated.

[0050] The causes of malfunctions in the servo system 7 include foreign matter adhering to the servo motor 72 or load 73, wear and tear on the servo motor 72 or load 73, and damage to the servo motor 72 or load 73. Malfunctions in the servo system 7 manifest as detectable characteristics such as torque disturbances in the servo motor 72, changes in resonance characteristics, and changes in friction. The data processing system 1 performs degradation diagnosis based on these characteristics.

[0051] The data processing system 1 can perform degradation diagnosis when the servo system 7 is performing a specified task, or it can perform degradation diagnosis by running the servo system 7 for trial operation when the specified task is stopped.

[0052] (3) Sensor

[0053] Sensor 61 is used to detect the state of servo system 7. Sensor 61 outputs a detection signal (electrical signal) containing the detected value to servo amplifier 71. Servo amplifier 71 controls the operation of servo motor 72 based on the detection signal and control signals (control values) from the upper-level controller 62 (described later). In addition, in this embodiment, sensor 61 also outputs the detection signal to data processing system 1. Preferably, multiple sensors 61 are provided. In this embodiment, current sensors, torque sensors, speed sensors, and position sensors (encoders, etc.) are provided as multiple sensors 61 for description.

[0054] A current sensor detects the current supplied to the servo motor 72. A torque sensor detects the torque of the servo motor 72. A speed sensor detects the rotational speed of the servo motor 72. A position sensor detects the position of the object being detected, which moves in accordance with the rotation of the servo motor 72. For example, the position sensor detects the rotation angle of the servo motor 72. Additionally, for example, if the load 73 is a ball screw, the position sensor detects the axial position of the ball screw, or a component connected to the ball screw. Furthermore, a camera can be used instead of a position sensor to detect the position of the object being detected.

[0055] (4) Upper-level controller

[0056] The upper-level controller 62 outputs a control signal to the servo amplifier 71. Thus, the upper-level controller 62 controls the operation of the servo system 7. The control signal contains control values. For example, the control signal may include at least one of the following: a command value for the rotational speed of the servo motor 72, a command value for the rotational angle, and a command value for the torque. The servo amplifier 71 adjusts the power supplied to the servo motor 72 according to this control signal and the detection signal from the sensor 61, thereby controlling the operation of the servo motor 72.

[0057] Additionally, the upper-level controller 62 also outputs a control signal containing the (first) control value to the data processing system 1. The data processing system 1 performs degradation diagnosis based on the control signal (first control value). The data processing system 1 can also perform degradation diagnosis based on the detection signal from the sensor 61.

[0058] Furthermore, the servo amplifier 71 has a power conversion unit that generates a control signal (second control value) for adjusting the power supplied from the power conversion unit to the servo motor 72. The servo amplifier 71 can also output a control signal containing the second control value to the data processing system 1. In this case, the data processing system 1 can also acquire the control signal generated by the servo amplifier 71 and perform degradation diagnosis based on the control signal. In other words, the "control signal used in the control of the servo system 7" in this disclosure can be a control signal containing the first control value from the upper-level controller 62, or it can be a control signal containing the second control value generated by the servo amplifier 71. The "control value used in the control of the servo system 7" can be either the first control value or the second control value.

[0059] The various detection values ​​output from sensor 61, the various (first) control values ​​output from upper-level controller 62, and the (second) control values ​​output from servo amplifier 71 are respectively equivalent to the input values ​​acquired by acquisition unit 2. That is, the input values ​​(control values ​​and detection values) used as diagnostic parameters include at least one of the value of the current supplied to servo motor 72, the torque of servo motor 72, the speed of servo motor 72, and the value of the position (rotation angle) of servo motor 72.

[0060] (5) Data processing system

[0061] (5.1) Structural elements

[0062] Data processing system 1 includes a computer system having one or more processors and memories. At least a portion of the functions of data processing system 1 are implemented by the processor of the computer system executing programs recorded in the computer system's memory. The programs can be recorded in memory, provided via electrical communication lines such as the Internet, or provided via non-transitory recording media such as memory cards.

[0063] The data processing system 1 includes an acquisition unit 2, a generation unit 3, a processing unit 4, an output unit 51, a receiving unit 52, and a storage unit 53. Furthermore, the acquisition unit 2, generation unit 3, processing unit 4, output unit 51, and receiving unit 52 only illustrate functions implemented by more than one processor and do not necessarily represent a physical structure.

[0064] (5.2) Acquisition Department

[0065] The acquisition unit 2 acquires diagnostic parameters. For example, the data processing system 1 also includes a communication interface device, through which the acquisition unit 2 acquires diagnostic parameters.

[0066] like Figure 1As shown, as diagnostic parameters, there are input values ​​and generated values. One example of an input value is a detection value output from sensor 61. Another example of an input value is a control value output from at least one of the upper-level controller 62 and the servo amplifier 71. An example of a generated value is an extracted value, a statistic, or a principal component. The generated value is generated by the generation unit 3 based on the input value. In this embodiment, the acquisition unit 2 acquires the input value as a diagnostic parameter. In other words, the acquisition unit 2 acquires at least one of the control signal (input value) from at least one of the upper-level controller 62 and the servo amplifier 71, and the detection signal (input value) from sensor 61 (acquisition step). The acquisition unit 2 outputs the input value to the generation unit 3 and the processing unit 4.

[0067] The generation unit 3 generates one or more diagnostic parameters based on an input value. Furthermore, the input value itself is also a diagnostic parameter, and therefore can be used in degradation diagnosis. In this embodiment, the diagnostic parameters used in degradation diagnosis are generated values ​​generated by the generation unit 3.

[0068] (5.3) Generation section

[0069] The generation unit 3 generates generated values ​​and outputs them to the processing unit 4. The generation unit 3 includes an extraction unit 31, a statistics unit 32, a statistical analysis unit 33, and a trend generation unit 34. In this embodiment, the extraction unit 31, the statistics unit 32, and the statistical analysis unit 33 correspond to the first generation unit 3A, and the trend generation unit 34 corresponds to the second generation unit 3B (see reference). Figure 1 ).

[0070] The extraction unit 31 performs extraction processing on the input values ​​to generate extracted values. The extraction processing is the process of extracting a portion of the input values ​​as the extracted values.

[0071] The statistics section 32 generates statistics based on the input values. Examples of statistics include the mean, standard deviation, maximum value, minimum value, or a feature quantity that can be obtained from a histogram.

[0072] The statistical analysis unit 33 performs statistical analysis on the input values ​​to generate diagnostic parameters that differ from the input values. More specifically, the statistical analysis unit 33 performs principal component analysis on multiple input values ​​to generate principal components.

[0073] Furthermore, the generation unit 3 can combine two or more of the extraction processes in the extraction unit 31, the processing in the statistics unit 32, and the processing in the statistical analysis unit 33 to generate diagnostic parameters. In this embodiment, the generation unit 3 can combine at least one of the processing in the statistics unit 32 and the processing in the statistical analysis unit 33 with the extraction process in the extraction unit 31 to generate diagnostic parameters. In other words, the generation unit 3 generates diagnostic parameters (generated values) by performing at least one of the processing of converting input values ​​into statistics and statistical analysis, as well as extraction processing.

[0074] As an example, the generation unit 3 first generates extracted values ​​through the extraction process in the extraction unit 31. Furthermore, the generation unit 3 generates diagnostic parameters by performing processes such as obtaining the average value of the extracted values ​​or calculating the standard deviation of the extracted values ​​in the statistics unit 32.

[0075] As another example, generation unit 3 first generates multiple extracted values ​​through the extraction process in extraction unit 31. Then, generation unit 3 generates multiple principal components by performing principal component analysis on the multiple extracted values ​​in statistical analysis unit 33. Generation unit 3 outputs the multiple principal components as diagnostic parameters.

[0076] In this embodiment, the following example will be used: A diagnostic parameter among multiple diagnostic parameters that is directly used in degradation diagnosis is a generated value generated by performing at least the following process. That is, the diagnostic parameter directly used in degradation diagnosis is a generated value generated by averaging the extracted values ​​generated by the extraction unit 31 using the statistics unit 32. On the other hand, the input value for the diagnostic parameter is used indirectly in degradation diagnosis in a form that is converted into a generated value and then used in degradation diagnosis.

[0077] In this disclosure, diagnostic parameters (generated values) are sometimes referred to as first data D1 (refer to...). Figures 4A to 4C The first generation unit 3A (extraction unit 31, statistics unit 32, and statistical analysis unit 33) generates, for example, first data D1 (first generation step) related to three characteristic quantities (e.g., average value) based on a specified region (all or part of the characteristic period described later) in the signal waveforms of the three signals.

[0078] The trend generation unit 34 (second generation unit 3B) generates time-series data representing the degradation progress of object OB1, namely, the second data D2 (second generation step). Preferably, the trend generation unit 34 generates three or more (here, three...) Figures 4A to 4C The three data points shown are the second data points D2. Each second data point D2 represents the trend of change of the first data point D1 (diagnostic parameter) over time, which is related to the corresponding feature quantity. Figures 4A to 4CThe horizontal axis is set to time to display the second data D2 related to the "characteristic quantity A", "characteristic quantity B", and "characteristic quantity C" that change over time. As an example, all characteristic quantities A through C are set as average values, but the types of signals upon which characteristic quantities A through C are based differ. Specifically, "characteristic quantity A" is, for example, the average value (average current value) of a specified region (all or part of the characteristic period) in the signal waveform of the current supplied to the servo motor 72. "Characteristic quantity B" is, for example, the average value (average torque) of a specified region (all or part of the characteristic period) in the signal waveform of the torque of the servo motor 72. "Characteristic quantity C" is, for example, the average value (all or part of the characteristic period) of a specified region (all or part of the characteristic period) in the signal waveform of the speed of the servo motor 72.

[0079] The generation unit 3 stores the first data D1 related to features A to C generated by the first generation unit 3A in the storage unit 53 as historical record information. The trend generation unit 34 generates second data D2 corresponding to each feature based on the first data D1 related to features A to C generated at a certain point in time (e.g., the current point in time) and the past first data D1 related to features A to C stored in the storage unit 53. Figures 4A to 4C In the diagram, each second data point D2 is represented as a broken line connecting multiple first data points D1 (plot points) arranged in a time series at generation intervals T1.

[0080] The generation interval T1 between two adjacent first data points D1 (plotting points), that is, the interval between time points t1 and t2, t2 and t3, t3 and t4, etc., is fixed in the example diagram. There is no particular limitation on the generation interval T1; for example, it can be several hours, a day, or a month. The generation interval T1 can be set and changed by the user using the operating device 82.

[0081] exist Figures 4A to 4C In this example, time point t7 is set as the current time point. The trend generation unit 34 uses the latest first data D1 generated at time point t7 (the current time point) and the first data D1 generated at time points t1 to t6 before time point t7 in the storage unit 53 to generate the second data D2 for each feature quantity A to C.

[0082] The trend generation unit 34 outputs the three generated second data points D2 to the processing unit 4. The second data points D2 are processed by the presentation unit 47, which will be described later in the processing unit 4.

[0083] As object OB1 deteriorates over time, the characteristics A through C generally show a monotonically decreasing trend. However, at least one of the characteristics A through C can also be a characteristic that shows a monotonically increasing trend as object OB1 deteriorates over time.

[0084] (5.4) Output section

[0085] The output unit 51 functions as a display output unit that outputs input values ​​to the display device 81. The output unit 51 outputs input values, for example, via a communication interface device. Additionally, the output unit 51 outputs generated values ​​to the display device 81. That is, the output unit 51 outputs diagnostic parameters (input values ​​or generated values) to the display device 81 (presentation device).

[0086] In addition, the output unit 51 functions as a reliability output unit that outputs reliability-related information in association with diagnostic parameters to the display device 81 (presentation device).

[0087] (5.5) Receiving Unit

[0088] The receiving unit 52 receives signals from the operating device 82. The receiving unit 52 receives signals, for example, via a communication interface device.

[0089] (5.6) Processing Department

[0090] The processing unit 4 has the functions of a division unit 41, a period determination unit 42, a correction unit 43, a reliability determination unit 44, a learning unit 45, a diagnostic unit 46, a presentation unit 47, and an estimation unit 48.

[0091] (5.6.1) Division section

[0092] The division unit 41 divides the input value into multiple periods based on the characteristics of the input value's waveform for display on the display device 81. Information related to the multiple periods determined by the division unit 41 is output to the display device 81 via the output unit 51. The display device 81 displays the input value divided into the multiple periods defined by the division unit 41.

[0093] exist Figure 2 The diagram shows an example where the control value of the speed of the servo motor 72 is set as the input value, and the input value is divided into multiple periods p1 to p15 and displayed on the display device 81. The servo motor 72 is controlled to repeat the same action in cycles of periods p1 to p15. That is, the servo motor 72 performs an action on a workpiece in cycles of periods p1 to p15. Each period p1 to p15 has the characteristics of monotonically decreasing, monotonically increasing, or having a fixed value. The division unit 41 divides the input value into multiple periods p1 to p15 by analyzing the rate of change of the input value.

[0094] The user operates the device 82 (reference) Figure 1 The receiving unit 52 receives a designation signal output from the operating device 82 based on the user's operation of the operating device 82. The designation signal contains information for determining the period specified by the user. When the receiving unit 52 receives the designation signal, the generation unit 3 extracts the value of the period specified by the user's operation of the operating device 82 from the input values ​​during the extraction process. More specifically, when the receiving unit 52 receives the designation signal, the generation unit 3 extracts the value of the period specified by the user's operation of the operating device 82 from the input values ​​during the extraction process.

[0095] For example, the user specifies a period p7. The extraction unit 31 of the generation unit 3 generates the value of period p7 from the input values ​​as the extracted value.

[0096] Here, the extraction unit 31 can generate the value of the user-specified period p7 from the input values ​​displayed on the display device 81 as the extracted value. Alternatively, the extraction unit 31 can also generate the value of the user-specified period p7 from input values ​​that are different from the input values ​​displayed on the display device 81 as the extracted value. Figure 2 In the example, the input value displayed by display device 81 is speed. Figure 3 This is an example of the current value in p7 during the period specified by the user. That is, Figure 3 The period from the starting point ti to the ending point tf is the same as the period p7. The extraction unit 31 can also set such a current value as the extraction value.

[0097] That is, the acquisition unit 2 acquires multiple input values. These multiple input values ​​include a first input value and a second input value. In the example above, the first input value is speed, and the second input value is the current value. The generation unit 3 performs the following first and second processes in the extraction process: in the first process, it determines a characteristic period in the first input value that exhibits a predetermined characteristic; in the second process, it extracts the value included in the characteristic period from the second input value as a diagnostic parameter (extracted value). Specifically, in the first process, the generation unit 3 sets the period p7 specified by the user's operation of the operating device 82 as the characteristic period. The predetermined characteristic in period p7 is the monotonous decrease of speed (first input value). Furthermore, the input values ​​are also divided into multiple periods p1 to p15, each with its own characteristic, for periods other than p7. Therefore, the extraction process is a process of extracting the value of the input value from the period determined by a predetermined characteristic. In the second process, the generation unit 3 extracts the value of the current value (second input value) included in period p7 (characteristic period) as a diagnostic parameter.

[0098] The generation unit 3 can also set all values ​​included in the feature period as diagnostic parameters.

[0099] Alternatively, generation unit 3 may set the values ​​of a portion of the feature period as diagnostic parameters. In summary, generation unit 3 may also extract the values ​​of a portion of the feature period as diagnostic parameters during the process of extracting the values ​​included in the feature period from the second input value. For example, generation unit 3 may also extract a portion of the feature period p101 (see reference...) Figure 3 The value of ) is used as a diagnostic parameter. The generation unit 3 may also set the period p101 to, for example, a period specified by the user's operation of the operating device 82. Alternatively, the period p101 may be determined by the period determination unit 42 based on the characteristics of the waveform of the second input value. The characteristics of the waveform of the second input value may be, for example, the amplitude, frequency, or average value per unit time of the second input value. Alternatively, the period p101 may be determined by the period determination unit 42 to be a period corresponding to one cycle of the second input value.

[0100] In other words, the aforementioned "characteristic quantity A (refer to)" Figure 4A ")" can be the average value of the current during the characteristic period (period p7), or it can be a characteristic quantity (in this case, the average value) of the current during a portion of the characteristic period (period p101).

[0101] (5.6.2) Decision-making department during the period

[0102] The period determination unit 42 has the function of determining the period used in degradation diagnosis from the input values. The validity of this function can be switched, for example, by the user's operation of the operating device 82. When this function is invalid, the period used in degradation diagnosis is determined by the user's operation of the operating device 82. The extraction unit 31 extracts the value of the period determined by the period determination unit 42 or by the user's operation from the input values ​​as the extracted value.

[0103] The period determination unit 42, for example, sets the period of a feature exhibiting a specified characteristic in the input value as the period to be used in the degradation diagnosis. Information on which period to use in the degradation diagnosis is stored in the storage unit 53. The period determination unit 42 determines the period to be used in the degradation diagnosis by referring to this information. Furthermore, this information can be updated by the user's operation of the operating device 82.

[0104] When the user decides the period to be used in the degradation diagnosis, it has the advantage of reflecting the user's insights in the degradation diagnosis. It is conceivable that the appropriate period for degradation diagnosis varies depending on the server system 7's setup environment and usage conditions. By allowing the user to decide the period used in degradation diagnosis, the accuracy of the degradation diagnosis can be improved.

[0105] Furthermore, when the period determination unit 42 determines the period to be used in the degradation diagnosis, it has the advantage of saving the user the time of determining the period.

[0106] (5.6.3) Presentation Section

[0107] The presentation unit 47 has three or more second data D2 (here, D2) generated by the trend generation unit 34 (second generation unit 3B). Figures 4A to 4C The three functions shown (presentation steps) compare each other. The presentation unit 47 determines the trend of change for each second data point D2 by analyzing the direction and rate of change (increase, decrease, or stagnation) between adjacent first data points D1 (plotted points). The "trend of change" referred to here is assumed to be a trend correlated with the progression of degradation. That is, it refers to... Figures 4A to 4C The trend of monotonically changing in one direction during the period from time point t1 to time point t7. "One direction" is assumed to be a monotonically decreasing direction, but depending on the type of diagnostic parameter, it may sometimes be a monotonically increasing direction. Figure 4A and Figure 4B Both feature quantities A and B in the model monotonically decrease during the period from time point t1 to time point t7, showing the same trend. Furthermore, even if one feature quantity A monotonically decreases during the period from time point t1 to time point t7, while the other monotonically increases during the same period, the same trend (a trend correlated with the progression of degradation) is still observed. However, Figure 4C The characteristic quantity C in the equation does not change in one direction during the period from time point t1 to time point t7. In other words, although... Figure 4C The second data point, D2, shows a decreasing trend, but compared to... Figure 4A and Figure 4B Unlike the second data point D2, there is a period (time points t2 to t3) where the increasing trend is temporarily affected by noise, etc. In other words, Figure 4C The second data point, D2, contains intervals that are not correlated with the progression of degradation. Presenting users with second data point D2 that includes such intervals due to noise or other factors that are not correlated with the progression of degradation may mislead the diagnosis of degradation.

[0108] Therefore, the presentation unit 47 determines whether there exists a specific second data D20 that exhibits a different trend of change than the other second data D2 (refer to...). Figure 4C For example, if more than half of the three or more second data D2 show a monotonically decreasing trend, while less than half (e.g., one) of the second data D2 show a different trend, the presentation unit 47 determines that the second data D2 is a specific second data D20.

[0109] The presentation unit 47 assumes that when it is determined that the changing trends of the three second data D2 are all the same and there is no specific second data D20, it presents the three second data D2 without performing "specific processing". The presentation unit 47 outputs the three second data D2 to the display device 81 via the output unit 51, and presents the three second data D2 from the display device 81 (screen display).

[0110] On the other hand, in the case of a specific second data D20 that exhibits a different trend of change than other second data D2, the presentation unit 47 performs specific processing related to object data D10 to present the specific second data D20 (presentation step), where object data D10 is the first data D1 that is the cause of the different trend of change. Figure 4C The specific second data point D20 shown here exhibits a temporary increasing trend within a certain interval (time points t2 to t3). The presentation unit 47 determines that the first data point D1 at time point t3 is the object data D10 that causes the different changing trends. The presentation unit 47 can also determine that the first data point D1 before and after the first data point D1 at time point t3 is also the object data D10.

[0111] Specific processing includes at least one of the following: non-presentation of object data D10, correction of object data D10, and notification regarding object data D10.

[0112] The presentation unit 47 outputs the specific second data D20, after undergoing specific processing, to the display device 81 via the output unit 51, and presents the specific second data D20 through a screen display on the display device 81. The display device 81 displays the specific second data D20, for example, as follows: Figure 4C The graph shows a broken line graph of the data. Users can visually confirm the progress of degradation by viewing the specific second data point D20 displayed on the screen.

[0113] Furthermore, the presentation unit 47 presents the specific second data D20 in a manner that includes the first data D1 generated by the first generation unit 3A at a certain time point (here, time point t7, which is the current time point), and the first data D1 generated by the first generation unit 3A before a certain time point (time point t7). Specifically, as Figure 4C As shown, the presentation unit 47 presents the specific second data D20 as seven first data D1s including time points t1 to t7. Therefore, the user can confirm the progress of degradation up to time point t7 by presenting the specific second data D20.

[0114] Preferably, the presentation unit 47 presents not only the specific second data D20, but also other second data D2. That is, preferably, the presentation unit 47 also presents at least one of three or more second data D2, other than the specific second data D20 (here, the two second data D2 of feature A and feature B). The display device 81 displays, for example, the two second data D2 of feature A and feature B as follows: Figure 4A and Figure 4B The graph shows a line graph of the data. The "presentation" of the data here is not limited to screen display, but can include sound output, etc. For example, notifications regarding object data D10 can also be delivered via sound output. Preferably, the second data D2, other than the specific second data D20, is displayed on the same screen as the specific second data D20, but this is not particularly limited, and they can be displayed on different screens.

[0115] The non-presentation processing, correction processing, and notification processing will be explained below. The presentation unit 47 can perform specific processing only when the temporary increase in the monotonic decrease of the feature quantity is above a threshold. Additionally, the presentation unit 47 can also perform specific processing only when the temporary decrease in the monotonic increase of the feature quantity is above a threshold.

[0116] [Non-rendering processing]

[0117] For example, in cases where a specific process includes non-presentation processing related to the non-presentation of object data D10, the presentation unit 47 prevents the display device 81 from displaying the screen of object data D10. Figure 4CFor example, the presentation unit 47 prevents the display device 81 from displaying the first data D1 (object data D10) at time point t3 in a specific second data D20. Specifically, regarding the specific second data D20, the presentation unit 47 sets the line data from time point t2 to time point t4, including the first data D1 (plotting point) at time point t3, to non-display (blank), and displays the line data from time points t1 to t2 and time point t4 onwards. In this way, the display of object data D10, which is likely to be affected by noise, is prevented, thus reducing the likelihood of misleading the diagnosis of degradation.

[0118] [Correction Processing]

[0119] For example, in cases where a specific process includes correction processing related to the correction of object data D10, the presentation unit 47 corrects the object data D10 based on the variation trend of at least one of the three or more second data D2s other than the specific second data D20, using the correction unit 43. The presentation unit 47 then presents the corrected object data D10. Here, the presentation unit 47 presents (displays) the specific second data D20, including the corrected object data D10, from the display device 81.

[0120] The corrected object data D10 is the data to be presented by the presentation unit 47. During the degradation diagnosis performed by the diagnosis unit 46, either the object data D10 before correction or the corrected object data D10 can be used.

[0121] The correction unit 43 performs correction processing related to the object data D10 according to instructions from the presentation unit 47. Figure 4C For example, the correction unit 43 corrects the first data D1 (object data D10) at time point t3 in a specific second data D20.

[0122] Here, the presentation unit 47, through the correction unit 43, corrects the object data D10 based on the previous trend of change of the object data D10 in the specific second data D20, and presents the corrected object data D10. Figure 4C For example, the correction unit 43 corrects the object data D10 at time point t3 based on two first data D1 from time points t1 to t2 before time point t3, and the monotonically decreasing rate of change (slope) of these data. Therefore, the reliability related to the correction of the object data D10 is improved. In this embodiment, the correction unit 43 estimates the true first data D1X at time point t3 (refer to...) based not only on the two first data D1 from time points t1 to t2 and their rate of change, but also on multiple first data D1 from time point t4 onwards and their rate of change. Figure 4CThe correction unit 43 compares the actual broken-line data K1 between time points t2 and t4, including the estimated first data D1X (refer to...). Figure 4C Interpolate using the dashed line.

[0123] The correction unit 43 can interpolate the piecewise linear data K1 based on the correlation data. The correlation data is information related to the correlation between the type of the first data D1 (diagnostic parameter), the value of the first data D1, and the degradation progress of the servo system 7, and the correlation data is stored in the storage unit 53. The correlation data can be information prepared based on verification results such as simulation results, and is stored as a data table or formula.

[0124] Preferably, the presentation unit 47 corrects the object data D10 using an approximation curve. That is, it is preferable to determine the true first data D1X at time point t3 using an approximation curve. In this case, the reliability related to the correction of the object data D10 is improved.

[0125] In this way, object data D10 that is likely to be affected by noise and other factors is corrected and presented, thus making it less likely to mislead the diagnosis of degradation.

[0126] When the presentation unit 47 displays specific second data D20 from the display device 81, it is preferable to display the corrected object data D10 in a display mode that can be distinguished from other first data D1. Distinguishing display modes include, for example, color, line type, etc. For example, such as... Figure 4C As shown, the presentation unit 47 can display the corrected object data D10 (first data D1X) using hollow plotted dots, and display other first data D1 using black plotted dots. Additionally, as... Figure 4C As shown, the presentation unit 47 can display the actual broken line data K1 between time points t2 and t4, which includes the first data D1X, using red dashed lines, and display the other first data using black solid lines. By displaying the corrected object data D10 in a way that can be distinguished from the other first data D1, the user can easily confirm visually that the object data D10 is the corrected data.

[0127] [Notification Processing]

[0128] For example, in cases where specific processing includes notification processing related to object data D10, when the presentation unit 47 displays specific second data D20 on the screen from the display device 81, it displays a warning message indicating that the specific second data D20 exhibits a different trend of change than other second data D2. The warning message may contain, for example, a string such as "There is data whose trend of change differs from that of other data." Preferably, the warning message is displayed on the same screen as the specific second data D20, but this is not particularly limited, and it may be displayed on different screens. Furthermore, the notification of the warning message is not limited to screen display; it may also be delivered by outputting sound from a speaker. Because of the warning message, the user can easily understand that there is object data D10 that is highly likely to be affected by noise, etc. Therefore, it is less likely to mislead the diagnosis of degradation.

[0129] In cases where specific processing includes notification processing and non-presentation processing, the warning message may contain data such as "Due to the existence of data with a different trend than other data, it has been set to not be displayed." Additionally, in cases where specific processing includes both notification processing and correction processing, the warning message may contain data such as "Due to the existence of data with a different trend than other data, data correction has been performed."

[0130] In this embodiment, the user may also make appropriate settings changes regarding which of the following processes—non-presentation processing, correction processing, and notification processing—is included in a particular processing, using the operating device 82.

[0131] In this way, according to this embodiment, when there is a specific second data D20 exhibiting different changing trends, specific processing related to the object data D10 that is the cause of the different changing trends is performed to present the specific second data D20. Therefore, users are less likely to misunderstand the object data D10, which is likely to be affected by noise, as real data. As a result, the data processing system 1 has the advantage of not easily causing misleading results in degradation diagnosis.

[0132] (5.6.4) Reliability determination and estimation departments

[0133] The reliability determination unit 44 assigns information related to the reliability of the diagnostic parameters (first data D1) in the degradation diagnosis of the servo system 7 to the diagnostic parameters (first data D1). The diagnostic parameters mentioned here can be input values ​​acquired by the acquisition unit 2, or generated values ​​generated by the generation unit 3 based on the input values. Regarding reliability, the stronger the correlation between the diagnostic parameters and the degradation degree of the servo system 7, the higher the reliability should be set.

[0134] The reliability determination unit 44 has the function of determining the reliability based on the user's operation of the operating device 82, and the function of automatically determining the reliability. First, the former will be explained.

[0135] like Figure 2 As shown, diagnostic parameters are displayed on the display device 81. The user specifies the reliability of the diagnostic parameters by operating the operating device 82. The receiving unit 52 receives a specified signal output from the operating device 82 based on the user's operation of the operating device 82. The specified signal contains information about the reliability specified by the user. When the receiving unit 52 receives the specified signal, the reliability determination unit 44 determines the reliability to the value specified by the user's operation of the operating device 82.

[0136] Furthermore, when the display device 81 displays multiple diagnostic parameters (including multiple first data D1 and second data D2), the reliability of the multiple diagnostic parameters can be specified individually by the user operating the operation device 82.

[0137] Next, the function of the reliability determination unit 44 in automatically determining reliability will be explained. Here, the reliability determination unit 44 has the function of automatically determining not only the reliability of a single diagnostic parameter (first data D1), but also the reliability of a second data D2 including multiple diagnostic parameters (hereinafter, sometimes referred to as "overall reliability"). In particular, the reliability determination unit 44 has the function of automatically determining the overall reliability of a specific second data D20 that exhibits a different trend of change than other second data D2s. The reliability determination unit 44 determines the reliability (overall reliability) related to the trend of change of the specific second data D20 based on the trend of change of reference data whose characteristic quantity type is the same as that of the specific second data D20. The "reference data" referred to here are diagnostic parameters generated in the past, or diagnostic parameters related to other devices. Specifically, the "reference data" are one or more first data D1s or second data D2s generated in the past with respect to a servo motor different from the servo motor 72 of interest. However, if the characteristic value of a specific second data point D20 is the average current value, then the characteristic value of the reference data is also the average current value. The reference data is stored in the storage unit 53. The reference data can be stored as a data table or a formula.

[0138] Furthermore, in this embodiment, the reliability determination unit 44 uses a learned model generated through machine learning to determine the reliability of the diagnostic parameters and the overall reliability. The learned model can be generated by the learning unit 45, or it can be generated by an external device of the data processing system 1 and provided to the data processing system 1.

[0139] Learned models include, for example, classifiers that utilize learned neural networks. Learned neural networks can include, for example, CNNs (Convolutional Neural Networks) or BNNs (Bayesian Neural Networks). Learned models can be implemented by mounting the learned neural network on an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or a FPGA (Field-Programmable Gate Array).

[0140] When the user determines the reliability of the diagnostic parameters, it has the advantage of being able to reflect the user's insights in the reliability value. It is conceivable that the appropriate value for the reliability of the diagnostic parameters varies depending on the setup environment and usage conditions of the servo system 7. By allowing the user to determine the reliability of the diagnostic parameters, the reliability can be set to an appropriate value.

[0141] Furthermore, when the reliability is determined by the decision unit 42, it has the advantage of saving the user time in determining the reliability of diagnostic parameters.

[0142] Once the reliability of the diagnostic parameters is determined, the reliability determination unit 44 outputs the diagnostic parameters and related information about their reliability to the presentation device via the output unit 51. The presentation device displays the diagnostic parameters and their reliability. In this embodiment, the display device 81 functions as the presentation device. The display device 81 displays the diagnostic parameters and their reliability.

[0143] Furthermore, the reliability determination unit 44 also determines the overall reliability of the specific second data D20. When the specific second data D20 is displayed on the screen from the display device 81, the presentation unit 47 displays information related to reliability (overall reliability). The reliability determination unit 44 automatically determines not only the overall reliability of the specific second data D20, but also the overall reliability of other second data D2s. When the second data D2 is displayed on the screen from the display device 81, the presentation unit 47 displays information related to overall reliability. Users can easily understand the level of reliability of the specific second data D20 by viewing the overall reliability information displayed on the screen. Therefore, it is less likely to mislead deterioration diagnosis.

[0144] exist Figure 5 The image illustrates, schematically, the display of a display device 81 that includes an overall reliability display. As an example, Figure 5 Showing through Figure 4A The description includes the second data point D2 of characteristic quantity A and its overall reliability of "0.8". In Figure 5 In this context, time point t12 is set as the current time point (current). That is, the first data point D1 at time point t12 shows the latest actual data, and the first data point D1 at time points before time point t12 shows past actual data. The display device 81 uses a range of "0" to "1.0" to show the overall reliability, but there is no particular limitation on this; the overall reliability can also be shown as a percentage range of "0%" to "100%".

[0145] Here, the first data D1 at a time point after time point t12 is not actual data, but predicted data related to the first data D1. The presentation unit 47 of this embodiment presents the specific second data D20 in a manner that includes the first data D1 generated by the first generation unit 3A at a certain time point (time point t12), and the predicted data related to the first data D1 in the future after a certain time point (time point t12).

[0146] Specifically, the estimation unit 48 estimates the future first data D1 based on instructions from the presentation unit 47. The estimation unit 48 estimates the first data D1 at time points after time point t12, for example, based on the first data D1 generated up to a certain time point (time point t12) and its trend, as well as the aforementioned baseline data or correlation data. Furthermore, it is preferable that the presentation unit 47 also presents other second data D2 besides the specific second data D2 in a manner that includes predicted data related to the future first data D1 after a certain time point (time point t12).

[0147] Because a specific second data point D20 is presented in such a way that it includes a future first data point D1, the user can use the presented specific second data point D20 to confirm the predicted future deterioration progress from a certain point in time.

[0148] (5.6.5) Academic Department

[0149] The learning unit 45 generates learned models (first learned model and second learned model). The first learned model takes diagnostic parameters (first data D1) as input and outputs the reliability of the diagnostic parameters. The second learned model takes second data D2, which includes multiple diagnostic parameters, as input and outputs the overall reliability of second data D2.

[0150] The operating device 82 sends a specified signal containing information about the reliability (label) of specific diagnostic parameters and the overall reliability (label) of the second data D2, based on the user's operation. The learning unit 45 uses the specified signal as training data to perform machine learning and generate a learned model. Furthermore, the learning unit 45 can also relearn the learned model.

[0151] (5.6.6) Diagnostic Department

[0152] The diagnostic unit 46 performs a degradation diagnosis on the servo system 7 based on diagnostic parameters. The diagnostic parameters can be either the generated value produced by the generation unit 3 or the input value obtained by the acquisition unit 2. In this embodiment, the case where the diagnostic unit 46 uses the generated value produced by the generation unit 3 as the diagnostic parameter will be described as an example.

[0153] In addition to being specified (selected) by the user through operation of the operating device 82, the diagnostic parameters used in the deterioration diagnosis can also be automatically determined by the diagnostic unit 46. First, the case where the diagnostic parameters are specified by the user will be explained.

[0154] Multiple diagnostic parameters are displayed on the display device 81 (see reference). Figures 4A to 4C The user operates the operating device 82 to specify which of the multiple diagnostic parameters to use in the degradation diagnosis. The operating device 82 then outputs a specification signal containing the user's specified information.

[0155] The receiving unit 52 receives a specified signal output from the operating device 82 based on the user's operation of the operating device 82. When the receiving unit 52 receives the specified signal, the diagnostic unit 46 performs a degradation diagnosis of the servo system 7 based on the diagnostic parameters specified by the user's operation of the operating device 82.

[0156] The display device 81 displays the reliability of each of the multiple diagnostic parameters. The user can refer to the reliability to select the diagnostic parameter to be used in the degradation diagnosis from the multiple diagnostic parameters.

[0157] Figure 2The diagnostic parameters in period p1, period p2, ..., period p16 are respectively equivalent to the extracted values ​​extracted by the extraction unit 31, and therefore can be candidates for diagnostic parameters used in degradation diagnosis. Therefore, the operation of specifying diagnostic parameters used in degradation diagnosis includes specifying one or more of the multiple periods p1 to p16. The output unit 51 outputs recommendation information to the display device 81, and the display device 81 displays the recommendation information. In this way, the output unit 51 functions as a display output unit that outputs recommendation information to the display device 81. The recommendation information is information related to whether or not to recommend a specific period among the multiple periods p1 to p16. In this embodiment, the recommendation information is reliability. That is, a reliability is assigned to each of the multiple periods p1 to p16. Regarding a certain period among the multiple periods p1 to p16, a higher reliability means that the period is more recommended, and a lower reliability means that the period is less recommended.

[0158] When the diagnostic unit 46 automatically determines the diagnostic parameters to be used in the degradation diagnosis, the diagnostic unit 46, for example, sets the diagnostic parameter with the highest reliability among a plurality of diagnostic parameters as the diagnostic parameter to be used in the degradation diagnosis.

[0159] Information relating to the types of diagnostic parameters, the values ​​of the diagnostic parameters, and the degree of degradation of the servo system 7 is stored in the storage unit 53. For example, this information is stored as a data table or formula. The diagnostic unit 46 uses this information to perform degradation diagnosis of the servo system 7.

[0160] The diagnostic unit 46 is configured to determine the degree of degradation of object OB1 related to the corresponding feature quantity for each of three or more second data D2.

[0161] For example, the diagnostic unit 46 uses the average current value, obtained by averaging the amplitude of the current supplied to the servo motor 72 over time, as the diagnostic parameter (first data D1) in each second data D2. The smaller the absolute value of the average current value, the greater the degree of degradation diagnosed by the diagnostic unit 46.

[0162] Furthermore, for example, the diagnostic unit 46 uses the average torque, obtained by averaging the torque of the servo motor 72 over time, as a diagnostic parameter in each of the second data points D2. The smaller the average torque, the greater the degradation level diagnosed by the diagnostic unit 46.

[0163] Additionally, for example, the diagnostic unit 46 uses principal components—values ​​generated through principal component analysis of position sensor readings, as well as other similar data—as diagnostic parameters in each second data point D2. The smaller or larger the principal component, the greater the degradation level diagnosed by the diagnostic unit 46. The user or the diagnostic unit 46 can select the principal components (e.g., the first and second principal components generated through principal component analysis) that have a strong correlation with the degradation level of the servo system 7, and use them in the degradation diagnosis.

[0164] To further improve the accuracy of degradation diagnosis, the diagnostic unit 46 can also use a learned model generated through machine learning to perform degradation diagnosis. The learned model is generated by machine learning using a set of diagnostic parameters and degradation degree (label) as training data.

[0165] The diagnostic unit 46 outputs the degradation level as a diagnostic result.

[0166] The output unit 51 functions as a presentation output unit that outputs the diagnostic results of the diagnostic unit 46 to the presentation device. The presentation device is a device for presenting information, such as through images, sounds, or a combination thereof. In this embodiment, the display device 81 functions as the presentation device.

[0167] Alternatively, a determination corresponding to the degree of degradation can be displayed on the display device 81. In other words, the presentation unit 47 can also display three or more second data points D2 from the display device 81 in a manner that allows visual confirmation of the degree of degradation determined by the diagnostic unit 46. For example, as Figure 5 As shown, a first threshold Th1 and a second threshold Th2 are set (first threshold Th1 > second threshold Th2). The diagnostic unit 46 determines the degradation level as "Good," "Caution," and "Warning" based on the first threshold Th1 and the second threshold Th2. It is not limited to determining the degradation level into three levels; it can also have two or more levels. When the feature value is above the first threshold Th1, a "Good" degradation level determination is displayed. Figure 5 In the data, data up to time point t11 ​​is classified as "good," represented by a solid green line, for example, as the second data point D2. When the feature value is less than the first threshold Th1 and greater than the second threshold Th2, a degradation level of "attention" is displayed. Figure 5 In the data, from time point t11 ​​to time point t13, a "Caution" condition is indicated, represented by a yellow dashed line (e.g., the second data point D2). When the feature value is less than the second threshold Th2, a "Warning" condition is displayed to indicate degradation. Figure 5 In the data, after time point t13, a "warning" is issued, indicated by a red underline representing the second data point, D2. Furthermore, in... Figure 5In the diagram, after time point t12, the first future data D1 estimated by the estimation unit 48 is displayed. The diagnostic unit 46 also includes the estimated first future data D1 in the diagram and displays it in a way that shows three levels of degradation.

[0168] Because three or more second data points D2 are displayed in a way that allows for visual confirmation of the degree of degradation, users can easily understand the degree of degradation of object OB1 by viewing the three or more second data points D2 displayed on the screen.

[0169] (5.7) Storage Section

[0170] The storage unit 53 is, for example, ROM (Read Only Memory), RAM (Random Access Memory), or EEPROM (Electrically Erasable Programmable Read Only Memory). The storage unit 53 stores information used in the data processing system 1. For example, the storage unit 53 stores information about predetermined features of the input values ​​that enable the partitioning unit 41 to divide the input values ​​into multiple periods according to each feature. Additionally, the storage unit 53 stores a learned model used in the reliability determination unit 44. Furthermore, as described above, the storage unit 53 stores reference data and correlation data, etc.

[0171] (6) Display device

[0172] The display device 81 includes a display. The display device 81 displays information corresponding to that received from the output unit 51. The display device 81 displays waveforms of diagnostic parameters, the reliability of the diagnostic parameters, and the degree of degradation as a diagnostic result from the diagnostic unit 46. Additionally, the display device 81 displays setting information for the data processing system 1.

[0173] As described above, the display device 81 functions as a display device for presenting information. That is, the display device 81 is a display device for displaying waveforms and reliability of diagnostic parameters.

[0174] (7) Operating device

[0175] The operating device 82 includes, for example, one or more of a keyboard, a touchpad, and buttons. The operating device 82 is used in conjunction with the display device 81. The user inputs information by operating the operating device 82 while referring to the information displayed on the display device 81.

[0176] The operating device 82 can also be integrated with the display device 81. For example, a touch panel can be formed by the touchpad of the operating device 82 and the display of the display device 81.

[0177] (8) Deterioration diagnosis

[0178] Reference Figure 6 This section describes a series of procedures for diagnosing the degradation of the servo system 7 using the data processing system 1. Furthermore, Figure 6 The flowchart shown is merely one example of the degradation diagnosis process involved in this disclosure, and the order of processing may be changed as appropriate, or processing may be added or omitted as appropriate.

[0179] The acquisition unit 2 acquires multiple input values ​​from at least one of the upper-level controller 62 and the servo amplifier 71 and the sensor 61 (step ST1).

[0180] Next, the output unit 51 outputs multiple input values ​​and multiple reliability values ​​corresponding to the multiple input values ​​to the display device 81. The display device 81 displays the multiple input values ​​and multiple reliability values ​​(step ST2). In addition, the display device 81 divides the input values ​​into multiple periods p1 to p15 for display.

[0181] The user operates the operating device 82 to select one or more input values ​​from multiple input values ​​for use in degradation diagnosis (step ST3).

[0182] Next, the user selects a period for the degradation diagnosis based on the selected input value. When the user selects at least one of the multiple periods p1 to p15 (step ST4: "Yes"), the extraction unit 31 extracts the value of the selected period from the input values ​​to generate an extracted value (step ST5). The user-selected period can be applied to all input values ​​among the multiple input values, or a period can be selected individually for each input value.

[0183] The generation unit 3 performs statistical processing on the extracted values ​​(step ST6). Specifically, the statistics unit 32 of the generation unit 3 generates statistics based on the extracted values, and the statistical analysis unit 33 generates principal components based on the extracted values.

[0184] The diagnostic unit 46 performs a degradation diagnosis of the servo system 7 based on at least one of the extracted values ​​extracted by the extraction unit 31, the statistics generated by the statistics unit 32, and the principal components generated by the statistical analysis unit 33 (step ST7).

[0185] The correction unit 43 compares multiple second data D2s and determines whether a specific second data D20 that needs correction is included (step ST8). If it is determined that the specific second data D20 is included, the correction unit 43 corrects the specific second data D20 (step ST9). If it is determined that the specific second data D20 is not included, step ST9 is omitted.

[0186] Display device 81 displays the diagnostic results of diagnostic unit 46 (step ST10). For example... Figure 5 As shown, the display device 81 displays each second data D2 in a manner that allows visual confirmation of the degree of degradation determined by the diagnostic unit 46, along with the reliability (overall reliability). If a specific second data D20 has been corrected through step ST9, the corrected specific second data D20 is displayed.

[0187] (Modified Example)

[0188] The following are examples of variations of the implementation method. These variations can also be implemented by appropriate combinations.

[0189] The statistical processing in the statistics section 32 and the statistical analysis section 33 can also be performed before the extraction processing in the extraction section 31.

[0190] In data processing system 1, statistical processing is not a necessary process.

[0191] Alternatively, the statistics unit 32 and the statistical analysis unit 33 may be located outside the data processing system 1. The acquisition unit 2 may also acquire at least one of the statistics generated by the statistics unit 32 and the principal components generated by the statistical analysis unit 33.

[0192] The extraction unit 31 may also be located outside the data processing system 1. The acquisition unit 2 may also acquire the extracted value from the extraction unit 31.

[0193] In degradation diagnosis, the extraction process of extraction unit 31 is not always necessary. For example, the diagnosis unit 46 can also perform degradation diagnosis based on input values, statistics, or the values ​​of principal components over the entire period.

[0194] Data processing system 1 does not necessarily need to have a diagnostic unit 46. Alternatively, an external structure of data processing system 1 can replace the diagnostic unit 46 to perform degradation diagnosis. Or, a person can perform degradation diagnosis by viewing diagnostic parameters displayed on display device 81.

[0195] An accelerometer or a temperature sensor can also be used as sensor 61. Furthermore, when multiple servo systems 7 are used synchronously with each other, a sensor that detects the status of other servo systems 7 can also be used as sensor 61. For example, in the case of multi-axis control using multiple servo systems 7, the operating states of the multiple servo systems 7 may affect each other; therefore, the detection results of the status of other servo systems 7 can be used in the degradation diagnosis of servo system 7.

[0196] The diagnostic unit 46 can also output a signal indicating whether or not there is degradation instead of outputting the degree of degradation as a diagnostic result.

[0197] The device for presenting the diagnostic results of the diagnostic unit 46 is not limited to the display device 81. For example, the presentation device may also be a sound output device that presents the diagnostic results by sound.

[0198] The presentation device is not necessarily a display device 81 that displays the reliability of the diagnostic parameters together with the waveform of the diagnostic parameters. The presentation device may also present the reliability of the diagnostic parameters together with the labels (names, etc.) of the diagnostic parameters through sound or the like.

[0199] The division unit 41 can also divide the input value into multiple periods based on the characteristics of the waveform of the input value by comparing model data representing the specified characteristics of the input value with the input value.

[0200] The correction unit 43 is not limited to correcting only the first data D1 (object data D10) at time point t3, but can also correct the first data D1 before and after time point t3.

[0201] The warning message displayed by the presentation unit 47 is not limited to data containing strings such as "There is data whose trend of change is different from that of other data." Warning messages may also include graphics (e.g., icons), symbols, numbers, and other data in addition to string data.

[0202] The data processing system 1 of this disclosure includes a computer system. The computer system has a processor and memory as its main hardware components. At least a portion of the functions of the data processing system 1 of this disclosure are implemented by the processor executing a program recorded in the computer system's memory. The program can be pre-recorded in the computer system's memory, provided via electrical communication lines, or provided via a non-transitory recording medium such as a memory card, optical disc, or hard disk drive readable by the computer system. The processor of the computer system is composed of one or more electronic circuits, including semiconductor integrated circuits (ICs) or large-scale integrated circuits (LSIs). The ICs or LSIs referred to herein are named differently depending on the degree of integration, including integrated circuits called system LSIs, VLSIs (Very Large Scale Integration), or ULSIs (Ultra Large Scale Integration). Furthermore, FPGAs (Field-Programmable Gate Arrays) programmed after LSI manufacturing, or logic devices capable of reconstructing the internal bonding relationships or circuit partitioning within an LSI, can also be used as processors. Multiple electronic circuits can be integrated onto a single chip or distributed across multiple chips. Multiple chips can be integrated into a single device or distributed across multiple devices. The computer system described herein includes a microcontroller having one or more processors and one or more memories. Therefore, a microcontroller also consists of one or more electronic circuits, including semiconductor integrated circuits or large-scale integrated circuits.

[0203] Furthermore, integrating multiple functions of data processing system 1 into a single device is not a necessary structural requirement for data processing system 1; the structural elements of data processing system 1 can also be distributed across multiple devices. Moreover, at least some functions of data processing system 1, such as a portion of the functions of processing unit 4, can be implemented via the cloud (cloud computing).

[0204] Conversely, in this embodiment, functions distributed across multiple devices can be integrated into one device. For example, functions distributed across the data processing system 1, the display device 81, and the operation device 82 can also be integrated into one device.

[0205] (Summarize)

[0206] Based on the implementation methods described above, the following methods are disclosed.

[0207] The data processing system (1) involved in the first method is used for degradation diagnosis of at least one object (OB1) in the load (73) and the servo motor (72) in the servo system (7). The servo system (7) includes a load (73), a servo amplifier (71), and a servo motor (72) that provides power to the load (73) according to the control of the servo amplifier (71). The data processing system (1) includes an acquisition unit (2), a first generation unit (3A), a second generation unit (3B), and a presentation unit (47). The acquisition unit (2) acquires at least one signal from the control signal used in the control of the servo system (7) and the detection signal output from the sensor (61) that detects the state of the servo system (7). The first generation unit (3A) generates first data (D1) related to three or more characteristic quantities based on a predetermined region in the signal waveform of the at least one signal. The second generation unit (3B) generates three or more second data points (D2), which are time-series data representing the degradation progress of the object (OB1), and each represents the change trend of the first data point (D1) related to the three or more feature quantities over time. The presentation unit (47) compares the three or more second data points (D2) with each other. Moreover, in the case of a specific second data point (D20) that exhibits a different change trend than the other second data points (D2), the presentation unit (47) performs specific processing related to the object data (D10) to present the specific second data point (D20), which is the first data point (D1) that is the cause of the different change trend. The specific processing includes at least one of the following: non-presentation of the object data (D10), correction of the object data (D10), and notification about the object data (D10).

[0208] According to the above method, in the case of specific second data (D20) exhibiting different trends of change, specific processing related to the object data (D10) that is the cause of the different trends of change is performed to present the specific second data (D20). Therefore, users are less likely to misunderstand object data (D10) that is likely to be affected by noise, etc., as real data. As a result, the data processing system (1) has the advantage of not easily causing misleading degradation diagnosis.

[0209] Regarding the data processing system (1) involved in the second method, in the first method, the presentation unit (47) presents specific second data (D20) by displaying a screen from the display device (81).

[0210] According to the above method, users can visually confirm the progress of degradation by using specific second data (D20) displayed on the screen.

[0211] Regarding the data processing system (1) involved in the third method, in the first or second method, the presentation unit (47) presents the specific second data (D20) in a manner that includes the first data (D1) generated by the first generation unit (3A) at a certain point in time and the first data (D1) generated by the first generation unit (3A) before a certain point in time.

[0212] Using the method described above, users can confirm the progress of degradation up to a certain point in time by presenting specific second data (D20).

[0213] Regarding the data processing system (1) involved in the fourth method, in any of the methods from the first to the third method, the presentation unit (47) presents the specific second data (D20) in a manner that includes the first data (D1) generated by the first generation unit (3A) at a certain point in time and the prediction data related to the first data (D1) in the future after a certain point in time.

[0214] Using the method described above, users can confirm the future deterioration progress predicted from a certain point in time by presenting specific second data (D20).

[0215] Regarding the data processing system (1) involved in the fifth method, in any of the first to fourth methods, the presentation unit (47) also presents at least one of the three or more second data (D2) other than the specific second data (D20).

[0216] According to the above method, users can visually confirm the progress of degradation by using the specific second data (D20) displayed on the screen and the second data (D2) other than the specific second data (D20).

[0217] Regarding the data processing system (1) involved in the sixth method, in any of the methods 1 to 5, the specific processing includes processing related to the non-presentation of the object data (D10). The presentation unit (47) prevents the display device (81) from displaying the object data (D10).

[0218] By using the above method, the display of object data (D10) that is likely to be affected by noise and other factors is prevented, thus making it less likely to mislead the diagnosis of degradation.

[0219] Regarding the data processing system (1) involved in the seventh method, in any of the methods from the first to the sixth method, the specific processing includes processing related to the correction of the object data (D10). The presentation unit (47) corrects the object data (D10) based on the changing trend of at least one of the three or more second data (D2) other than the specific second data (D20), and presents the corrected object data (D10).

[0220] By correcting and presenting object data (D10) that is likely to be affected by noise, etc., it is less likely to mislead the diagnosis of degradation.

[0221] Regarding the data processing system (1) involved in the eighth method, in any of the methods from the first to the seventh method, the specific processing includes processing related to the correction of the object data (D10). The presentation unit (47) corrects the object data (D10) based on the previous change trend of the object data (D10) in the specific second data (D20) and presents the corrected object data (D10).

[0222] According to the above method, the reliability related to the correction of object data (D10) is improved.

[0223] Regarding the data processing system (1) involved in the 9th method, in the 7th or 8th method, when the presentation unit (47) displays specific second data (D20) from the display device (81), it displays the corrected object data (D10) in a display mode that can be distinguished from other first data (D1).

[0224] Using the method described above, users can easily visually confirm that the object data (D10) displayed on the screen is the corrected data.

[0225] Regarding the data processing system (1) involved in the 10th method, in any of the 7th to 9th methods, the presentation unit (47) corrects the object data (D10) by means of an approximate curve.

[0226] According to the above method, the reliability related to the correction of object data (D10) is improved.

[0227] Regarding the data processing system (1) involved in the 11th method, in any of the 1st to 10th methods, the specific processing includes the processing of notifications regarding object data (D10). When the presentation unit (47) displays specific second data (D20) on the screen from the display device (81), it displays a warning message indicating that the specific second data (D20) exhibits a different trend of change than other second data (D2).

[0228] Using the method described above, users can easily understand the presence of object data (D10) that is likely to be affected by noise or other factors through the warning information displayed on the screen. Therefore, it is less likely to mislead the diagnosis of degradation.

[0229] The data processing system (1) involved in the 12th method further includes a reliability determination unit (44) in any of the 1st to 11th methods. The reliability determination unit (44) determines the reliability related to the change trend of the specific second data (D20) based on the change trend of reference data whose type of characteristic quantity is the same as that of the specific second data (D20). When the specific second data (D20) is displayed on the screen from the display device (81), the presentation unit (47) displays information related to reliability on the screen.

[0230] Using the method described above, users can easily understand the reliability level of a specific second data point (D20) by viewing the reliability information displayed on the screen. Therefore, it is less likely to mislead deterioration diagnosis.

[0231] The data processing system (1) involved in the 13th method further includes a diagnostic unit (46) in any of the 1st to 12th methods. The diagnostic unit (46) determines the degree of degradation of the object (OB1) related to the corresponding feature quantity for each of the three or more second data (D2). The presentation unit (47) displays the three or more second data (D2) from the display device (81) in a manner that allows the degree of degradation determined by the diagnostic unit (46) to be visually confirmed.

[0232] Using the method described above, users can easily understand the degradation level of an object (OB1) by viewing more than three second data points (D2) displayed on the screen.

[0233] The data processing method involved in the 14th method relates to the degradation diagnosis of at least one object (OB1) in the load (73) and servo motor (72) of the servo system (7). The servo system (7) includes a load (73), a servo amplifier (71), and a servo motor (72) that provides power to the load (73) according to the control of the servo amplifier (71). The data processing method includes an acquisition step, a first generation step, a second generation step, and a presentation step. In the acquisition step, at least one signal is acquired, including a control signal used in the control of the servo system (7) and a detection signal output from a sensor (61) that detects the state of the servo system (7). In the first generation step, first data (D1) related to three or more characteristic quantities is generated based on a defined region in the signal waveform of the at least one signal. In the second generation step, three or more second data (D2) are generated, which are time series data representing the degradation progress of the object (OB1), and each represents the change trend of the first data (D1) related to the three or more characteristic quantities over time. In the presentation step, three or more second data points (D2) are compared with each other. Furthermore, in the presentation step, if a specific second data point (D20) exhibits a different trend of change than the other second data points (D2), specific processing related to the object data (D10) is implemented to present that specific second data point (D20), which is the first data point (D1) that causes the different trend of change. The specific processing includes at least one of the following: non-presentation of the object data (D10), correction of the object data (D10), and notification regarding the object data (D10).

[0234] Based on the above approach, a data processing method that is less likely to mislead degradation diagnosis can be provided.

[0235] The program involved in Method 15 is a program used to cause one or more processors to execute the data processing method in Method 14.

[0236] Based on the above method, a function that is less likely to mislead the diagnosis of degradation can be provided.

[0237] The structures involved in methods 2 to 13 are not necessary for the data processing system (1) and can be appropriately omitted.

[0238] Industrial availability

[0239] This disclosure can improve the accuracy of degradation diagnosis by making it less likely to mislead the diagnosis of servo system degradation, and can also improve the efficiency of equipment maintenance and inspection, thus being useful in industry.

[0240] Explanation of reference numerals in the attached figures

[0241] 1: Data processing system; 2: Acquisition unit; 3A: First generation unit; 3B: Second generation unit; 44: Reliability determination unit; 46: Diagnostic unit; 47: Presentation unit; 61: Sensor; 7: Servo system; 71: Servo amplifier; 72: Servo motor; 73: Load; 81: Display device; D1, D1X: First data; D10: Object data; D2: Second data; D20: Specific second data; OB1: Object; ti: Start point; tf: End point.

Claims

1. A data processing system relating to degradation diagnosis of at least one of the load and the servo motor in a servo system comprising a load, a servo amplifier, and a servo motor that powers the load according to the control of the servo amplifier, the data processing system comprising: The acquisition unit acquires at least one of a control signal used in the control of the servo system and a detection signal output from a sensor that detects the state of the servo system. The first generation unit generates first data related to three or more feature quantities based on a predetermined region in the signal waveform of the at least one signal. The second generation unit generates three or more second data points, which are time series data representing the degradation progress of at least one of the load and the servo motor, and respectively represent the change trend of the first data related to the three or more feature quantities over time. The presentation unit compares the three or more second data with each other, and determines the second data that shows a different trend from the other second data as a specific second data based on the correlation or consistency of the changing trends between the second data. The presentation unit performs specific processing related to the object data to present the specific second data. The object data is the first data that is the reason why the specific second data shows a different changing trend. as well as The reliability determination unit determines the reliability related to the changing trend of the specific second data based on the changing trend of benchmark data whose types of feature quantities are the same as those of the specific second data. The specific processing includes processing related to at least one of the following: non-presentation of the object data, correction of the object data, and notification regarding the object data. The presentation unit presents the specific second data in a manner that includes the first data generated by the first generation unit at a certain point in time and prediction data related to the first data in the future after the certain point in time, and when the specific second data is displayed on the screen from the display device, information related to the reliability is displayed on the screen.

2. The data processing system according to claim 1, wherein, The presentation unit presents the specific second data by displaying a screen from the display device.

3. The data processing system according to claim 1, wherein, The presentation unit also presents at least one of the three or more second data, excluding the specific second data.

4. The data processing system according to claim 1, wherein, The specific processing includes processing related to the non-presentation of the object data. The presentation unit prevents the display device from displaying the object data.

5. The data processing system according to claim 1, wherein, The specific processing includes processing related to the correction of the object data. The presentation unit corrects the object data based on the change trend of at least one of the three or more second data, excluding the specific second data, and presents the corrected object data.

6. The data processing system according to claim 1, wherein, The specific processing includes processing related to the correction of the object data. The presentation unit corrects the object data based on the previous trend of change of the object data in the specific second data, and presents the corrected object data.

7. The data processing system according to claim 5, wherein, When the display unit displays the specific second data from the display device, it displays the corrected object data in a display mode that can be distinguished from the other first data.

8. The data processing system according to claim 5, wherein, The presentation unit corrects the object data using an approximate curve.

9. The data processing system according to claim 1, wherein, The specific processing includes the processing of notifications regarding the object data. When the display unit displays the specific second data on the screen from the display device, it displays a warning message indicating that the specific second data shows a different trend of change than the other second data.

10. The data processing system according to any one of claims 1 to 9, wherein, It also includes a diagnostic unit that, for each of the three or more second data points, determines the degree of degradation of the object related to the corresponding feature quantity. The presentation unit displays the three or more second data points from the display device in a manner that allows visual confirmation of the degree of degradation determined by the diagnostic unit.

11. A data processing method relating to degradation diagnosis of at least one of the load and the servo motor in a servo system comprising a load, a servo amplifier, and a servo motor that powers the load according to the control of the servo amplifier, wherein in the data processing method, Acquire at least one of the control signals used in the control of the servo system and the detection signals output from the sensors that detect the state of the servo system. Based on a defined region in the signal waveform of the at least one signal, first data related to three or more feature quantities is generated. Generate three or more second data points, which are time-series data representing the degradation progression of at least one of the load and the servo motor, respectively representing the time-varying trend of the first data related to the three or more characteristic quantities. By comparing the three or more second data points with each other, and based on the correlation or consistency of the changing trends among the second data points, the second data point exhibiting a different changing trend from the other second data points is identified as a specific second data point. Specific processing related to the object data is then performed to present the specific second data point, where the object data is the first data point that causes the specific second data point to exhibit a different changing trend. The specific processing includes at least one of the following: non-presentation of the object data, correction of the object data, and notification regarding the object data. The reliability related to the change trend of the specific second data is determined based on the change trend of the benchmark data whose feature quantities are the same as those of the specific second data. The specific second data is presented in a manner that includes the first data generated at a certain point in time and the predicted data related to the first data in the future after the certain point in time, and when the specific second data is displayed on a screen from a display device, information related to the reliability is displayed on a screen.

12. A program product for causing one or more processors to execute the data processing method according to claim 11.

Images