Information processing method and device, control program, storage medium, method for manufacturing product, and method for obtaining learning data

Abstract

The present invention discloses an information processing method and device, a control program, a storage medium, a method for manufacturing a product, and a method for acquiring learning data. The information processing method includes causing an information processing device to display a first image, on which a plurality of partial time series data of a physical quantity of a state of a mechanical device are displayed; causing the information processing device to display a second image, on which a plurality of partial time series data are displayed at intervals different from the intervals at which the plurality of partial time series data are displayed on the first image; and causing the information processing device to display a first mark marking the first partial time series data and a second mark marking the second partial time series data, the first partial time series data being a predetermined piece of partial time series data among the plurality of partial time series data displayed on the first image, and the second partial time series data being a piece of partial time series data among the plurality of partial time series data displayed on the second image and corresponding to the first partial time series data.

Description

Technical Field

[0001] The present disclosure relates to an information processing method and an information processing device. Background Art

[0002] The operating state of a mechanical device may change from moment to moment depending on, for example, changes in the states of its constituent components. In the following description, an operating state within a permissible range based on the intended use of the mechanical device is referred to as a normal state, and an operating state outside such a permissible range is referred to as a fault state. A mechanical device in a fault state may cause problems. For example, if a manufacturing machine is in a fault state, the manufacturing machine may produce defective products or stop a production line due to a malfunction.

[0003] In order to suppress the occurrence of a fault state as much as possible, generally, for example, a maintenance operation is performed (regularly or irregularly) on the manufacturing machine even if the manufacturing machine continuously repeats the same operation. An improvement in preventive safety can be achieved by shortening the intervals between maintenance operations. However, if the frequency of maintenance operations is excessively increased, the operating rate of the manufacturing machine is reduced because the manufacturing machine must be stopped from performing its normal operations during the maintenance operations. Therefore, it is desirable to be able to estimate the moment when a fault state is likely to occur in the machine, for example, when the machine is in a normal state. Detection of the moment when a fault state is likely to occur (prediction of the occurrence of a fault) can make it possible to avoid an excessive reduction in the operating rate by performing the maintenance operation on the machine at the time indicated by the detected moment.

[0004] As a method for predicting the moment of occurrence of a fault, it is known to prepare in advance a post-learning model generated by machine learning of the state of a mechanical device and to evaluate the state of the mechanical device at the time of evaluation by using the post-learning model. In order to improve the prediction accuracy, it is important to construct a post-learning model suitable for predicting faults. For such a construction, it is important to prepare learning data (training data) used when generating a fault prediction model of the mechanical device by machine learning. In order to determine whether the extracted data is suitable as learning data, a detailed analysis of the data is required, such as inspection of the waveform and comparison between the waveforms.

[0005] For example, Japanese Patent Laid-Open No. 2013-232061 discloses a trend chart display system. In Japanese Patent Laid-Open No. 2013-232061, a first area, a second area, and a third area are provided. In the first area, time-series data is displayed according to the passage of time. In the second area, time-series data in a specific time period selected by a user in the first area is displayed in an enlarged view. In the third area, time-series data corresponding to the specific time period is displayed in a table form. Comparison between multiple time-series data is performed by comparing the tabular data in the third area, which has been displayed synchronously with a cursor representing a specific time point in the second area selected by the user, with data at another time point. Summary of the invention

[0006] Various embodiments of the present disclosure provide an information processing method, which includes: causing an information processing device to display a first image, on which a plurality of partial timing data of physical quantities regarding a state of a mechanical device are displayed; causing the information processing device to display a second image, on which the plurality of partial timing data are displayed at intervals different from the intervals at which the plurality of partial timing data are displayed on the first image; and causing the information processing device to display a first mark for marking first partial timing data and a second mark for marking second partial timing data, wherein the first partial timing data is a predetermined piece of partial timing data among the plurality of partial timing data displayed on the first image, and the second partial timing data is a piece of partial timing data among the plurality of partial timing data displayed on the second image and corresponds to the first partial timing data.

[0007] Further features of the present disclosure will become apparent from the following description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a schematic functional block diagram describing functional blocks included in a time series data display device according to an embodiment.

[0009] Figure 2 is a schematic diagram showing an example hardware configuration of a time series data display device according to an embodiment.

[0010] Figure 3 is a flowchart describing a control method according to an embodiment.

[0011] Figure 4A It is a diagram showing an example of time series data collected by the time series data display device.

[0012] Figure 4B is a diagram showing an example of event data collected by the time series data display device.

[0013] Figure 5 It is a graph showing a plurality of time-series data collected from a mechanical device for one repetitive operation.

[0014] Fig. 6A is a diagram representing a plurality of pieces of time-series data collected when a repetitive operation is continuously performed.

[0015] Figure 6B It is a diagram that shows multiple time series data collected over a long period of time in a compressed manner along the time axis.

[0016] Figure 7 is a diagram showing extracted partial time-series data aligned on a linear scale (ie, an absolute time axis) in which time is set as an index.

[0017] Figure 8 It is a diagram showing extracted partial time series data aligned on a linear scale in which the number of pieces of data is set as an index.

[0018] Fig. 9 is a diagram showing a display screen according to the embodiment.

[0019] Fig.10 is a diagram showing a display screen according to the embodiment.

[0020] Fig.11 is a diagram showing a display screen according to the embodiment.

[0021] Fig.12 is a diagram showing a display screen according to the embodiment.

[0022] Fig.13 is a diagram showing a display screen according to the embodiment.

[0023] Fig.14 is a diagram showing a display screen according to the embodiment.

[0024] Fig.15 is a diagram showing a robot apparatus according to an embodiment.

[0025] Fig.16 is a diagram showing a display screen according to the embodiment. DETAILED DESCRIPTION

[0026] Generally, in order to manage the operating state of a mechanical device, various parameters (physical quantities) in the mechanical device are measured and a very large amount of time series data is acquired. In order to construct a post-learning model suitable for predicting a fault in a mechanical device, it is necessary to appropriately extract data from the large amount of acquired data and perform detailed data analysis (such as inspection and comparison of waveforms) to determine whether the data can be used as learning data.

[0027] However, in the case of an industrial robot deployed on a production line, because the frequency of occurrence of failures is low, it is necessary to perform the collection of multiple time series data over a long period of time. Multiple time series data are collected to manage the operating status of the mechanical device. Therefore, the number of measurement parameters is large, the sampling rate needs to be high for detailed analysis of waveforms, for example, and the amount of multiple data collected becomes very large. Therefore, in the case of extracting data about failures that occur irregularly from multiple data collected over a long period of time at a high sampling rate, the data display method in the related art imposes a large workload on the staff and reduces the efficiency and accuracy of the work.

[0028] In Japanese Patent Laid-Open No. 2013-232061, a cursor that moves synchronously with each other in a trend graph for a specific period and a table representing data corresponding to the trend graph is displayed. However, in the case where a plurality of time series data collected over a long period are displayed in a graph form, the amount of the time series data is very large, and therefore it is necessary to display it in an enlarged view. Therefore, like the data display method in the related art, this method complicates the inspection and comparison of the detailed behavior of the plurality of time series data.

[0029] There is a need for an information processing method and an information processing apparatus with which a worker can easily perform inspection and comparison of a plurality of partial data optionally selected from among a plurality of collected time-series data.

[0030] An information processing method and an information processing device according to an embodiment of the present disclosure will be described with reference to the accompanying drawings. In the drawings to be referred to in the following description of the embodiments, elements denoted by the same reference numerals have the same functions unless otherwise described.

[0031] First embodiment

[0032] Figure 1 is a schematic diagram for describing functional blocks included in an information processing apparatus according to an embodiment. Although functional elements necessary for describing the features of this embodiment are shown in FIG. Figure 1 , but the illustration of general functional elements that are not directly related to the problem-solving principle of the present disclosure is omitted. Figure 1 Each functional element shown in is functionally conceptual and does not necessarily have to be physically configured as shown. For example, the specific configuration regarding the distribution and integration of each functional block is not limited to the example shown, and all or part of it can be functionally or physically distributed or integrated through optional units according to the usage conditions, etc.

[0033] like Figure 1 As shown in , a time series data display device 100 serving as an information processing device according to the embodiment is communicably connected to a mechanical device 10 as a measurement target.

[0034] Examples of the mechanical device 10 include various industrial devices, such as industrial robots and manufacturing devices installed on a production line. The mechanical device 10 includes various sensors 11 for measuring physical quantities regarding its state. For example, in the case where the mechanical device 10 is a multi-jointed robot, a sensor for measuring the current value of a motor for driving a joint, an angle sensor of the joint, and a sensor for measuring speed, vibration, or sound may be provided. However, these are merely examples, and appropriate types and numbers of sensors may be provided as the sensors 11 at appropriate locations depending on the type of the mechanical device 10, the purpose of use, and the like. As the sensor 11, various sensors such as a force sensor, a torque sensor, a vibration sensor, a sound sensor, an image pickup sensor, a distance sensor, a temperature sensor, a humidity sensor, a flow sensor, a pH sensor, a pressure sensor, a viscosity sensor, and a gas sensor may be used. Although for the sake of convenience of explanation, the following description will be given in detail. Figure 1 Only a single sensor 11 is shown in FIG. 1 , but a plurality of sensors capable of communicating with the time series data display device 100 are generally provided.

[0035] The mechanical device 10 is communicably connected to a time series data display device 100 serving as an information processing device in a wired or wireless manner. The time series data display device 100 can obtain data measured by the sensor 11 through communication. The functional blocks included in the time series data display device 100 will be described in sequence below. The time series data display device 100 includes a control unit 110, a storage unit 120, a display unit 130, and an input unit 140.

[0036] The control unit 110 includes a plurality of functional blocks, and these functional blocks are configured by, for example, a central processing unit (CPU) of the timing data display device 100 reading and executing a control program stored in, for example, a storage device or a non-transitory storage medium. Alternatively, a part or all of the functional blocks may be configured by hardware such as an application-specific integrated circuit (ASIC) included in the timing data display device 100.

[0037] The storage unit 120 includes a time series data storage section 121, an event data storage section 122, an extraction data storage section 123, a coupling data storage section 124, a display mark storage section 125, and an image information storage section 126. Each of these sections included in the storage unit 120 is configured by being appropriately allocated to a storage area of ​​a storage device such as a hard disk drive, a random access memory (RAM), or a read-only memory (ROM). The storage unit 120 is a data storage unit that stores a plurality of pieces of data of various types required to generate an image on which the time series data can be easily seen.

[0038] The display unit 130 and the input unit 140 are user interfaces included in the time series data display device 100. As the display unit 130, a display device such as a liquid crystal display or an organic electroluminescent (EL) display is used. As the input unit 140, an input device such as a keyboard, a jog dial, a mouse, a pointing device, or a sound input device is used.

[0039] The data collection part 111 included in the control unit 110 acquires the time series data and event data of the mechanical device from the mechanical device 10, and stores the time series data and the event data in the time series data storage part 121 and the event data storage part 122, respectively. The data collection part 111 may also be referred to as a data acquisition part.

[0040] The data collection part 111 collects a plurality of pieces of time series data of physical quantities regarding the state of the mechanical device 10, such as current, speed, pressure, vibration, sound, or temperature of each part measured by the sensor 11 in the mechanical device 10, and stores them in the time series data storage part 121. Alternatively, the data collection part 111 may calculate a maximum value, a minimum value, an average value, an integral value, a value obtained by converting into a frequency domain using an integral, a differential value, or a quadratic differential value in each predetermined period from the measured value of the sensor 11, and store it in the time series data storage part 121.

[0041] The data collection section 111 collects a plurality of pieces of event data on events occurring at the mechanical device 10, and stores them in the event data storage section 122. A predetermined state of the mechanical device 10 is set as an event, and a plurality of pieces of information on, for example, the time when the event has occurred are collected and stored in the event data storage section 122. For example, in the case where the stop state of the mechanical device 10 that continuously performs a repetitive operation (a cyclic operation) in a normal state is set as an event, the date of occurrence of the stop state is stored in the event data storage section 122.

[0042] Failure or maintenance as a cause of a downtime state generally occurs at irregular or long intervals. The information processing apparatus according to the embodiment is suitable for handling such events that occur discretely or irregularly.

[0043] The data extraction part 112 extracts partial time series data about an event from a plurality of time series data stored in the time series data storage part 121 based on the event data stored in the event data storage part 122, and stores the extracted partial time series data in the extracted data storage part 123. The data extraction part 112 may also be referred to as a data extraction part. For example, the data extraction part 112 may generate an image in which the extracted partial time series data is placed on a linear scale in which time is set as an index, and store the image in the extracted data storage part 123.

[0044] For example, in a case where the extraction condition (predetermined condition) is the stoppage of the mechanical device 10 , data on the date of occurrence of the stoppage of the mechanical device 10 is read from the event data storage portion 122 as event data.

[0045] Based on the event data, for example, the measurement values ​​of the sensor 11 collected in one operation cycle before the mechanical device 10 has stopped are extracted and stored in the extracted data storage part 123 as partial time series data. Alternatively, the maximum value, minimum value, average value, integrated value, value obtained by converting into the frequency domain using integration, differential value or quadratic differential value in each predetermined period calculated from the measurement values ​​obtained in one operation before the mechanical device 10 has stopped can be extracted from the time series data storage part 121. The extracted values ​​can be stored in the extracted data storage part 123 as partial time series data. According to the needs of the staff (operator), the generated image can be displayed on the display unit 130 or printed by a printer (not shown).

[0046] A case where one type of event data is stored in the event data storage section 122 has been described, but there is a case where multiple types of pieces of event data are stored in the event data storage section 122. In this case, the operator can select a predetermined event from among the multiple types of pieces of event data via the input unit 140, and the data extraction section 112 can extract partial time series data about the selected predetermined event and store the extracted partial time series data in the extracted data storage section 123. Alternatively, a predetermined event selected from among the multiple types of pieces of event data can be registered in advance, and partial time series data about the registered predetermined event can be automatically extracted and stored in the extracted data storage section 123.

[0047] The data coupling part 113 generates a diagram in which a plurality of pieces of partial time series data about an event are arranged based on the partial time series data stored in the extracted data storage part 123. For example, the data coupling part 113 generates a diagram in which a plurality of pieces of partial time series data about an event are placed or coupled adjacent to each other along a horizontal axis representing the number of pieces of data, and stores the diagram in the coupled data storage part 124. The generated diagram may be displayed on the display unit 130 or printed by a printer (not shown) according to the needs of the staff (operator).

[0048] The display mark generating part 114 generates an image by superimposing a display mark that enables easy identification of the selected optional partial timing data on the image stored in the extracted data storage part 123 or the coupled data storage part 124. For example, a display mark may be superimposed in a rectangular area so that the entirety of the selected partial timing data is identifiable. In the case where it is necessary to know the position of the selected partial timing data, the display mark may be superimposed as a point on the selected partial timing data. The image superimposed with the display mark is stored in the display mark storage part 125. At this time, information about the selected partial timing data may be stored together with the image. Examples of display marks include a mouse cursor, a mouse pointer, and an area displayed by a dragging operation of a mouse.

[0049] The editing section 115 edits the image generated by the data extracting section 112 or the data coupling section 113 to allow the operator to conveniently use the image (e.g., to more easily understand the information) at the time of execution of the optional operation, and stores the edited image in the image information storage section 126. The display mark generating section 114 may also be referred to as an image editing section or an editing section.

[0050] Next, we will Figure 2 An example hardware configuration of a time series data display device according to an embodiment is schematically shown in FIG. Figure 2 As shown in , the timing data display device may include personal computer (PC) hardware, which includes a CPU 1601 as a main controller, a ROM 1602 as a storage unit, and a RAM 1603. ROM 1602 can store information such as a processing program for executing the information processing method to be described below. When the information processing method is executed, RAM 1603 is used as a work area of, for example, CPU 1601. External storage device 1606 is connected to PC hardware. External storage device 1606 is composed of, for example, a hard disk drive (HDD), a solid state device (SSD), and an external storage device of another system installed thereon via a network.

[0051] The control program executed by the CPU 1601 to provide the information processing apparatus or information processing method according to the embodiment can be stored in a storage unit such as an external storage device 1606 constituted by a HDD or SSD or an electrically erasable programmable ROM (EEPROM) area of ​​the ROM 1602. In this case, the processing program executed by the CPU 1601 to provide the information processing method (for example, a method of displaying timing data) is supplied to each of the above-mentioned storage units via the network interface 1607, and can be updated to another new program. Alternatively, the processing program executed by the CPU 1601 to provide the information processing method can be supplied to each of the above-mentioned storage units via various storage media (such as magnetic disks, optical disks, and flash memory) and their drive devices, and its content can be updated. Various storage media, storage units, or storage devices storing the program that the CPU 1601 can execute to implement the process of the information processing method constitute a computer-readable recording medium for the information processing method or information processing apparatus according to the embodiment of the present disclosure.

[0052] Figure 1 The sensor 11 shown in FIG. is connected to the CPU 1601. Although Figure 2 For simpler explanation, the sensor 11 is shown as being directly connected to the CPU 1601, but the sensor 11 may be connected to the CPU 1601 via, for example, IEEE 488 (so-called general purpose interface bus (GPIB)). The sensor 11 may be communicatively connected to the CPU 1601 via a network interface 1607 and a network 1608.

[0053] The network interface 1607 may be configured by using, for example, a communication standard for wired communication such as IEEE 802.3 or a communication standard for wireless communication such as IEEE 802.11 or 802.15. The CPU 1601 may communicate with the external devices 1104 and 1121 via the network interface 1607. For example, in the case where the target for which the time series data is displayed is an industrial robot, each of the external devices 1104 and 1121 may be an overall control device such as a programmable logic controller (PLC) or a sequencer, a management server, etc., which is deployed to control or manage the industrial robot.

[0054] exist Figure 2 In the example shown in Figure 1 The operation unit 1604 corresponding to the input unit 140 shown in FIG. Figure 1A display unit 1605 corresponding to the display unit 130 shown in FIG. 1 is connected to the CPU 1601 as a user interface (UI) device. The operation unit 1604 may be composed of a terminal such as a handheld terminal, a device such as a keyboard, a jog dial, a mouse, a pointing device, a sound input device, or a control terminal including them. The display unit 1605 may be any device as long as information about the processing performed by the data extraction part 112 and the data coupling part 113 can be displayed on its display screen, and may be, for example, a liquid crystal display device.

[0055] Next, we will refer to Figure 3 The flowchart shown in describes an information processing method (a method of displaying time series data) performed by the time series data display device 100. Figure 3 An example process performed by the time series data display device is shown. Figure 4A and 4B 2 is a diagram showing examples of various data collected by the time series data display device 100 . Figure 4A is a diagram showing an example of time series data, and Figure 4B is a diagram showing an example of event data.

[0056] In step S101 , the time series data display device 100 collects a plurality of time series data and a plurality of event data from the mechanical device 10 and the sensor 11 . Figure 4A An example of time series data collected by the time series data display device 100 is shown. This time series data is obtained by periodically sampling and measuring the drive current of the industrial robot included in the mechanical device 10. The data collection part 111 in the time series data display device 100 collects a plurality of time series data from the sensor 11 in the mechanical device 10 and stores them in the time series data storage part 121.

[0057] Here, the plurality of pieces of time series data to be collected will be described in more detail. Figure 5 The timing data of one cycle operation when the industrial robot included in the mechanical device 10 is normally operated is shown in the form of a current waveform diagram. Fig. 6A and 6B As shown in the image, Figure 5 Multiple current waveforms shown in . Fig. 6A Multiple pieces of time series data collected when the industrial robot continuously performs cyclic operations are shown in the form of current waveforms. Fig. 6A It is obvious that there is a waveform SPW having a certain amplitude in the diagram. Figure 6B is with Fig. 6A The diagram shown in FIG. 1 shows multiple time series data collected over a long period of time in a more compressed manner than in the time axis direction. Figure 6BIt is obvious that there are two waveforms SPW with specific amplitudes in the diagram. Figure 6B The images shown in perform detailed inspection and comparison of specific waveforms as the waveform for each cycle operation is deformed in the time axis direction.

[0058] Next, Figure 4B An example of event data collected by the time series data display device 100 is shown. These multiple event data are the times when the downtime of the industrial robot included in the mechanical device 10 set as an event has occurred. In this example, downtime caused by maintenance operations performed regularly or irregularly and downtime caused by failures that occur irregularly are set as events. For example, in parallel with the collection of multiple time series data, the data collection unit 111 receives control information from a control unit for managing the operation of the mechanical device 10 to collect multiple event data, and stores the collected multiple event data in the event data storage part 122.

[0059] Return to reference Figure 3 In step S102, the data extraction part 112 extracts part of the time series data about the scheduled event from the multiple time series data stored in the time series data storage part 121. The scheduled event means an event that the staff (operator) has optionally selected from the multiple event data stored in the event data storage part 122, but can be automatically selected by the control unit 110.

[0060] For example, based on Figure 4B The event data shown in Figure 4A Partial time series data about a predetermined event is extracted from the multiple time series data shown in . Specifically, the time series data about the operation of a cycle before the time point when the selected predetermined event has occurred (the shutdown of the industrial robot) is extracted as partial time series data. This is just an example, and for example, time series data of a predetermined number of operation cycles separated from the time of the occurrence of the predetermined event can be extracted, or multiple time series data in multiple continuous operation cycles can be extracted as a single partial time series data. Alternatively, the time series data in the operation cycle itself in which the predetermined event has occurred can be extracted as partial time series data. The extracted partial time series data is stored in the extracted data storage part 123 together with the time information about the partial time series data.

[0061] Here, it is assumed that the extracted partial time series data is placed on a linear scale (i.e., an absolute time axis) with time being set as an index. Figure 7 On the display screen W schematically shown in FIG. 1 , most of the time series data during the continuous operation is not extracted and therefore not shown, and only the waveform of part of the time series data about the event is shown in the form of a graph. Figure 6BCompared with the diagram shown in , the redundancy is significantly reduced. However, in the case where a plurality of time series data have been collected for a long period of time, it is difficult to check the details of each waveform of the partial time series data on the display screen W because the waveform is compressed and deformed in the time axis direction. If the time axis direction is enlarged in order to easily observe the shape of the waveform, then because the plurality of partial time series data are spaced apart from each other at irregular intervals, a plurality of waveforms to be compared with each other may protrude from the screen.

[0062] In this embodiment, in step S103, the data coupling part 113 serving as a processing part couples multiple pieces of partial time series data stored in the extracted data storage part 123, and stores the result of the coupling in the coupled data storage part 124. That is, the data coupling part 113 generates an image (coupled data) on which the distance between multiple pieces of information (for example, diagrams) about each extracted partial time series data is set to be smaller than the distance between multiple pieces of information placed on a linear scale in which time is set as an indicator. The data coupling part 113 places multiple pieces of information (for example, diagrams) about adjacent multiple pieces of partial time series data so that they are coupled to each other or separated by a predetermined interval (short interval). For example, in Figure 7 In the embodiment, image processing is performed so that the distance between the waveforms of the pieces of partial time-series data in the horizontal axis direction is set to zero or a predetermined small distance.

[0063] In step S104, a graph is displayed as an image on the display unit 130 using the extracted data stored in the extracted data storage section 123. At this time, as assumed above, the extracted partial time series data is placed on a linear scale (i.e., an absolute time axis) in which time is set as an index and displayed.

[0064] Subsequently, in step S105, a diagram is displayed as an image on the display unit 130 using the coupling data stored in the coupling data storage part 124. At this time, in order to facilitate the observation or comparison of the waveform, the image can be appropriately enlarged in the horizontal axis direction. It is expected that the index (scale) of the diagram on the horizontal axis is not the absolute time, but the number of samples, the number of operation cycles, or the number of waveforms of the original measurement data. The reason is that when the absolute time is set as the index (scale) on the horizontal axis, the value of the index jumps discontinuously at the boundaries between a plurality of partial timing data separated from each other at irregular intervals, and the staff cannot obtain intuitive understanding.

[0065] In step S105, the generated image is displayed using the display unit 130, but the generated image may be transmitted to another display device different from the time series data display device 100 so that the display device displays the image, or may be transmitted to a printer so that the printer prints the image. That is, the output method of the generated image can be selected for the convenience of the staff (operator).

[0066] Figure 8 An example of an image displayed on the display screen W of the display unit 130 in step S105 is shown. The waveforms of multiple pieces of partial time series data about an event are coupled to be adjacent to each other in the horizontal axis direction and displayed. That is, the shutdown of the industrial robot is set as event data, and the partial time series data corresponding to each event is extracted from the multiple pieces of time series data obtained by monitoring the current value of the industrial robot, and a diagram on which the multiple pieces of partial time series data extracted are coupled is displayed. Therefore, since only the multiple pieces of partial time series data when an event occurs are coupled and displayed, the staff (operator) can very easily perform inspection and comparison of the diagram about the occurrence of the event.

[0067] Fig. 9 An example of an image displayed on the display screen W of the display unit 130 in steps S104 and S105 is shown. The upper image is an image generated in step S104, on which multiple pieces of extracted partial time series data are placed on a linear scale with time set as an indicator. The lower image is an image generated in step S105, on which multiple pieces of coupled partial time series data are placed on a horizontal axis with the number of samples of the partial time series data set as an indicator. In the upper right corner of the screen W, the content of the event data serving as the extraction condition (predetermined condition) and an indication of which type of time series data of a physical quantity is displayed (in Fig. 9 is the current value).

[0068] Then, in step S106, Fig. 9 As shown in FIG. 1 , a plurality of pieces of partial time-series data stored in the extracted data storage part 123 and the coupled data storage part 124 are displayed on the display screen W of the display unit 130. At this time, a plurality of pieces of data are displayed so that selectable partial time-series data in the image can be selected.

[0069] In step S107, the display mark generation section 114 serving as a processing section generates a display mark. The display mark is generated to easily identify the selectable partial sequential data selected on the image displayed on the display screen W of the display unit 130. The display mark is superimposed on the image displayed on the display screen W of the display unit 130. Information about the partial sequential data selected by the staff (operator) using the display mark is stored in the display mark storage section 125. The display mark superimposed on the image by the display mark generation section 114 can have various shapes, such as a line shape, an arrow shape, a circular shape, a square shape, a star shape, a finger shape, and a shape for displaying an area when a range is selected, provided that the staff (operator) can easily perform work (operation) using these marks or easily identify these marks.

[0070] Fig.10 An example of an image superimposed with the display mark 200 which has been generated by the display mark generation section 114 when the selectable selection of a part of the time-series data is made on the image displayed on the display screen W of the display unit 130 in step S107 is shown. Fig.10 In the embodiment, the display mark 200 superimposed on the image is rectangular in shape to allow the staff to easily identify the waveform of the selected partial timing data in one cycle. The rectangular display mark 200 is placed so that the start point and the end point of one cycle of the selected partial timing data are accommodated on the display mark 200. The display mark 200 is transparently displayed to allow the staff to check the selected waveform in one cycle.

[0071] Subsequently, in step S108, the editing section 115 serving as a processing section refers to the data on the selected selectable partial sequential data stored in the display mark storage section 125. In synchronization with the display mark 200 generated by the display mark generation section 114, a display mark 201 for highlighting the corresponding partial sequential data is displayed on another image (upper diagram) to allow the staff to easily recognize the data. The image is edited so that the information on the selected partial sequential data is displayed, and is stored in the image information storage section 126.

[0072] Fig.11An image that has been subjected to the editing process of the editing section 115 in step S108 is shown. The upper graph (a graph in which a plurality of pieces of partial time series data are placed on a linear scale with time set as an index) is generated in step S104, and the lower graph (a graph with a horizontal axis with the number of samples of partial time series data set as an index) is generated in step S105. When selectable partial time series data is selected on the lower graph in step S106, a display mark 200 is superimposed on the lower graph in step S107 to allow the worker to easily recognize one cycle of the selected partial time series data.

[0073] In step S108 , in synchronization with the display mark 200 for the selected partial time series data, a display mark 201 shaped like an inverted triangle is displayed above the data corresponding to the selected partial time series data on the upper diagram to allow the worker to easily identify the corresponding data.

[0074] In addition, the time of occurrence of the selected partial time series data and information about the event data when the partial time series data is extracted in step S102 are displayed. The information content icon 301 indicates that the event associated with the selected partial time series data is "failure shutdown" and has occurred or acquired on "5 / 14 / 2017 (May 14, 2017)". The information content icon 300 represents "peak maximum value: 50", which is information about the maximum peak value of the waveform in the area of ​​the display mark 200, and is superimposed on the lower diagram superimposed with the display mark 200 in step S107. The information content icon 300 represents the maximum peak value of the current value in this embodiment, but can represent the minimum peak value of the current value, the current value at the starting point, or the current value at the end point. A graphical user interface can be provided to allow the staff to appropriately set the display content of the information content icon 300. For example, by clicking or double-clicking the content of the information content icon 300, a drop-down menu 400 is displayed. In the drop-down menu 400, the information (such as the peak minimum value) that the staff wants to display is displayed and appropriately set by the staff.

[0075] Therefore, according to this embodiment, when the staff performs the check of the date and frequency of occurrence of a predetermined event or the check and comparison of the detailed behavior of the extracted multiple pieces of partial time series data, the staff can perform it without selecting a specific period again. This makes the staff's operation easier. Since the detailed information about the partial time series data is highlighted, it is easier to perform the check and comparison of the details of the data.

[0076] Second embodiment

[0077] In the above embodiment, a single piece of partial timing data is selected, but multiple pieces of partial timing data can be selected. This will be described in detail below. The following will describe and illustrate the configuration of the hardware and control system that are different from the first embodiment. In addition, parts similar to the above embodiments are regarded as having similar configurations and functions, and their detailed descriptions are omitted.

[0078] Fig.12 114 is a diagram showing a display screen W in this embodiment. Display control of the display screen W is performed by the display mark generating section 114 and the editing section 115. Figure 3 is selected in step S106 in the process and is displayed on the display screen W of the display unit 130. In the lower diagram, the partial time series data in the 6th cycle and the partial time series data in the 22nd cycle are selected. The display mark 200 is superimposed on the partial time series data in the 6th cycle, and the display mark 202 is superimposed on the partial time series data in the 22nd cycle. As in the above embodiment, the display mark 200 is placed so that the start point and the end point of the partial time series data in the 6th cycle are accommodated on the display mark 200, and the display mark 202 is placed so that the start point and the end point of the partial time series data in the 22nd cycle are accommodated on the display mark 202.

[0079] In order to highlight the partial timing data on the upper diagram corresponding to the partial timing data in the 6th cycle on the lower diagram, a display mark 201 shaped like an inverted triangle is displayed. In order to highlight the partial timing data on the upper diagram corresponding to the partial timing data in the 22nd cycle on the lower diagram, a display mark 203 shaped like an inverted triangle is displayed.

[0080] In order to easily recognize the relationship between these display marks, linear display marks 204 and 205 are displayed. The linear display mark 204 indicates the relationship between the display marks 200 and 201. The linear display mark 205 indicates the relationship between the display marks 202 and 203.

[0081] The information content icon 301 indicates that the event associated with the selected portion of the timing data is "failure shutdown" and has occurred or been obtained on "5 / 14 / 2017 (May 14, 2017)". The information content icon 303 similarly indicates that the event associated with the selected portion of the timing data is "failure shutdown" and has occurred or been obtained on "3 / 15 / 2018 (March 15, 2018)". The information content icon 300 represents "peak maximum value: 50", which is information about the maximum peak value of the waveform in the 6th cycle in the area of ​​the display mark 200, and is superimposed on the lower diagram. The information content icon 302 similarly represents "peak maximum value: 46", which is information about the maximum peak value of the waveform in the 22nd cycle in the area of ​​the display mark 202 on the lower diagram. As in the above embodiment, the information content icons 300 and 302 can represent the minimum peak value of the current value. A graphical user interface can be provided to allow the staff to appropriately set the display content of the information content icons 300 and 302.

[0082] In addition, an arrow-shaped display mark 206 representing the timing relationship between the waveform selected in the 6th cycle and the waveform selected in the 22nd cycle is displayed, and an information content icon 304 representing how far these waveforms are separated in time is displayed on the display mark 206. The information content icon 304 indicates that the waveform in the 6th cycle and the waveform in the 22nd cycle are separated from each other in time by "315 days". This is expressed in days in this embodiment, but can be expressed in seconds, minutes, hours, weeks, months or years. In this case as well, a graphical user interface can be provided to allow the staff to appropriately set the display content of the information content icon. For example, by clicking or double-clicking the content of the information content icon 304, a drop-down menu 401 is displayed. Various timing intervals are displayed in the drop-down menu 401, and the staff appropriately sets one of them.

[0083] In this embodiment, the display mark 206 and the information content icon 304 are displayed between the multiple pieces of partial time series data on the upper diagram, but can be displayed between the multiple pieces of partial time series data on the lower diagram. In this embodiment, the information content icon 304 is superimposed on the display mark 206, but can be displayed at an appropriate position on the display screen W other than the position of the display mark 206.

[0084] Therefore, according to this embodiment, the inspection and comparison of the detailed behavior of the waveforms of the selected multiple partial timing data can be easily performed. The date of occurrence of the event and the period between the selected multiple partial timing data can be easily understood. When the staff performs the inspection of the date and frequency of occurrence of the predetermined event or the inspection and comparison of the detailed behavior of the extracted multiple partial timing data, the staff can perform it without selecting a specific period again. This makes the operation of the staff easier. When multiple partial timing data are selected, the inspection and comparison of the detailed behavior of the waveform can be easily performed using the lower diagram and the upper diagram representing the corresponding relationship between these selected multiple partial timing data. These diagrams also indicate how far the multiple selected waveforms are separated in time. This can help the comparison between multiple data. This embodiment and this modification can be combined with the above embodiment and the above modification.

[0085] Third embodiment

[0086] Next, the situation of amplifying, observing and comparing the single waveform on the lower diagram will be described in detail. The following will be a description and explanation of the configuration of the hardware and control system different from the above embodiment. In addition, parts similar to the above embodiment are regarded as having similar configurations and functions, and their detailed description is omitted.

[0087] Fig.13 105 shows an example of a display screen W according to this embodiment. Display control of the display screen W is performed by the display mark generating section 114 and the editing section 115. When a graph is displayed on the display unit 130 using the coupling data stored in the coupling data storing section 124 in step S105, in order to facilitate observation or comparison of waveforms, Fig.13 Therefore, the entirety of the coupling data is not accommodated on the display screen W of the display unit 130, and only the waveforms in 12 cycles are displayed in this embodiment ( Fig.13 ), while in the above embodiment, the waveform in 24 cycles can be displayed ( Figures 9 to 12 ).

[0088] In this embodiment, scroll bar 402, button 403, arrow 404 and 405 are displayed to allow the staff to scroll the lower diagram in a predetermined direction and observe the lower diagram. By moving button 403 to the right side of the paper or clicking arrow 405, the waveform in the 25th cycle can be displayed. By moving button 403 to the left side of the paper or clicking arrow 404, the waveform in the 12th cycle can be displayed. Utilizing scroll bar 402, button 403 and arrows 404 and 405, invisible waveforms can be displayed on the lower diagram. This results in easy observation and comparison of waveforms.

[0089] By selecting a waveform different from the currently selected waveform on the upper graph, automatic scrolling of the lower graph may be performed. Fig.14 Shows Fig.13 A display screen W in which the display state has been changed by automatic scrolling of the lower diagram.

[0090] Fig.14 Shown in Fig.13 4 shows a display screen W after the display state in has been changed to the state when the waveform in the 6th cycle represented by the display mark 201 on the upper diagram is selected. When the waveform in the 6th cycle represented by the display mark 201 is selected, the button 403 automatically moves and displays the waveform in the 6th cycle on the lower diagram. Together with this, the display mark 200 is superimposed on the waveform in the 6th cycle on the lower diagram. As in the above embodiment, the information content icons 300 and 302 can represent the minimum peak value of the current value. A graphical user interface can be provided to allow the staff to appropriately set the display content of the information content icons 300 and 302.

[0091] Therefore, according to this embodiment, it is possible to easily perform the inspection and comparison of the detailed behavior of the waveforms of the selected multiple pieces of partial timing data. Since, for example, a scroll bar is used when comparing between multiple waveforms or the lower diagram automatically moves in response to the selection of the waveform on the upper diagram, the staff can perform the comparison without selecting a specific period again. This results in easy operation. This embodiment and this modification can be combined with the above various embodiments and the above various modifications.

[0092] In this embodiment, a scroll bar for scrolling the lower diagram is displayed, but a scroll bar for scrolling the upper diagram may be displayed.

[0093] Fourth embodiment

[0094] Example of connecting the time series data display device to the robot

[0095] Fig.15 A case where the time-series data display device 100 according to the above embodiment is connected to a six-axis articulated robot serving as an example of the mechanical device 10 is shown.

[0096] The links 500, 501, 502, 503, 504, 505 and 506 of the six-axis multi-joint robot are serially interconnected through six rotary joints J1, J2, J3, J4, J5 and J6. The six-axis multi-joint robot includes, for example, a sensor for measuring the rotation speed of the motor of each rotary joint, a sensor for measuring the rotation angle of the joint, a torque sensor, a sensor for measuring the motor current and a pressure sensor for measuring the pressure of the air used to drive the actuator.

[0097] For example, the robotic hand 510 may be removably attached to a distal link as an actuator.

[0098] The time series data display device 100 according to the embodiment is communicably connected to the six-axis articulated robot. The time series data display device 100 collects a plurality of time series data on physical quantities of the state of the robot and event data on events occurring at the robot.

[0099] The six-axis articulated robot repeatedly performs operations such as assembling components and manufacturing products. An operator can input instructions to the time series data display device 100 via the input unit 140 to cause the time series data display device 100 to generate, display, and print images.

[0100] For example, when the six-axis multi-articulated robot performs a process for grasping a predetermined workpiece and assembling the predetermined workpiece to another workpiece to manufacture a product, an image in which a diagram of partial timing data about a predetermined event (e.g., a failure) is coupled can be generated and displayed on the display unit 130. Such a display allows the operator to easily check the history of the robot about the predetermined event and determine whether the robot can continue to manufacture the product. That is, by connecting a timing data display device according to an embodiment of the present disclosure to a manufacturing device such as a robot so that the timing data display device displays partial timing data, the manufacture of the product can be performed while preventing the occurrence of downtime due to a failure in advance.

[0101] Fig.16 Another example of a display screen W according to an embodiment is shown. In this example, in order to allow a staff member (operator) to easily visually identify the boundaries between multiple pieces of partial time series data, multiple pieces of partial time series data (diagrams) are coupled and placed so that adjacent pieces of partial time series data are separated by a predetermined short interval (the lower diagram in the above embodiment). An information tag representing information about the content of the event is added to each diagram. In this example, a display tag representing a shutdown in a normal state (e.g., maintenance) and a display tag representing a shutdown in an abnormal state (e.g., a fault) are set, associated with each diagram, and displayed as a label representing a subclassification of the shutdown event. Above each of the labels, a check box (icon) for selecting a waveform is displayed, which is to be used as learning data for generating a fault prediction model. The labels and check boxes can be displayed in response to an instruction from a staff member (operator) input via the input unit 140, or can be automatically displayed by a control program.

[0102] Therefore, the operator can generate training data (learning data) for constructing a post-learning model for predicting a failure of a robot using the time series data display device 100. The operator can select a predetermined event from among the multiple event data acquired by the time series data display device 100, and cause the time series data display device 100 to extract part of the time series data from among the multiple time series data of various physical quantities and display an image on which, for example, comparison between diagrams can be easily performed.

[0103] use Fig.16 By checking the check boxes shown in , the operator can easily mark the data determined to be suitable as learning materials for machine learning and construct training data (learning data). This embodiment and this modification can be combined with the above various embodiments and the above various modifications.

[0104] In the above example, multiple pieces of partial time series data of one type of physical quantity such as "current value" are extracted and arranged along the horizontal axis as a diagram on a single screen, but another example may be adopted. For example, if diagrams of multiple pieces of partial time series data of multiple types of physical quantities can be displayed on the same screen, the staff (operator) can easily determine the correlation between different types of physical quantities of the event and conveniently use the diagram to extract learning data for generating a fault prediction model. Fig.16 The display screen W shown in can be used in the above various embodiments.

[0105] The present invention is not limited to the above embodiments, and many modifications of the above embodiments may be made without departing from the spirit, scope or technical concept of the present invention.

[0106] Other embodiments

[0107] For example, in the embodiments of the present disclosure, it is not necessary to display a diagram of a physical quantity related to one type of event. Figure 3 In step S102 of the flowchart in FIG. 1 , multiple types of events are set as extraction conditions (predetermined conditions). In step S103, a diagram is generated in which multiple pieces of partial time series data of the extracted physical quantity of each of the multiple types of predetermined events are coupled along the horizontal axis. Such a diagram can be arranged and displayed on the same screen in step S104. The operator can conveniently use the diagram to determine whether there is a correlation between multiple types of events in the case of physical quantities.

[0108] In the above various embodiments, partial timing data is extracted based on predetermined conditions, and most of the timing data during continuous operation is not displayed on the upper diagram on the display screen W. However, the original timing data (original waveform and original data) during continuous operation can be displayed as long as the redundancy of the timing data is reduced to a certain extent. In this case as well, the inspection and comparison of the detailed behaviors of multiple pieces of partial timing data can be easily performed using display marks that move synchronously with each other.

[0109] Various embodiments of the present disclosure may also be implemented by supplying a program that implements one or more functions of the embodiment to a system or device via a network or storage medium and causing one or more processors in a computer of the system or device to read out and execute the program. In addition, some embodiments of the present disclosure may also be implemented by a circuit (e.g., an application-specific integrated circuit (ASIC)) that implements one or more functions of the embodiment. A control program that can execute an information processing method or display method according to an embodiment and a computer-readable non-temporary recording medium that stores the control program are included in the embodiments of the present disclosure.

[0110] In the above embodiment, a six-axis articulated robot has been described as an example of the mechanical device 10, but the mechanical device 10 does not necessarily have to be a six-axis articulated robot. For example, a machine that can automatically perform extension, stretching, vertical movement, lateral movement, rotation operation or a combination thereof based on information stored in a storage device provided in the control device can be used as the mechanical device 10.

[0111] According to various embodiments of the present disclosure, a worker can easily perform inspection and comparison of a plurality of partial data optionally selected from among a plurality of collected time series data.

[0112] The embodiments of the present disclosure may also be implemented by reading out and executing computer executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be more completely referred to as a 'non-transitory computer-readable storage medium') to perform one or more functions of the above-mentioned embodiments and / or a computer of a system or device including one or more circuits (e.g., an application-specific integrated circuit (ASIC)) for performing one or more functions of the above-mentioned embodiments, and by a computer of the system or device, for example, reading out and executing computer executable instructions from a storage medium to perform one or more functions of the above-mentioned embodiments and / or controlling one or more circuits to perform one or more functions of the above-mentioned embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessing unit (MPU)), and may include a network of separate computers or separate processors to read out and execute computer executable instructions. Computer executable instructions may be provided to the computer, for example, from a network or a storage medium. The storage medium may include, for example, a hard disk, a random access memory (RAM), a read-only memory (ROM), a storage device of a distributed computing system, an optical disk (such as a compact disk (CD), a digital versatile disk (DVD), or a Blu-ray disk (BD)) TM ), one or more of flash memory devices, memory cards, etc.

[0113] The embodiments of the present invention may also be implemented by providing software (program) for performing the functions of the above-described embodiments to a system or device via a network or various storage media, and a computer or a central processing unit (CPU) or a microprocessing unit (MPU) of the system or device reads and executes the program.

[0114] Although example embodiments have been described, it is to be understood that the invention is not limited to the disclosed example embodiments.The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. An information processing method, the information processing method comprising: causing the information processing device to display a first image on which a plurality of partial time-series data of a physical quantity regarding a state of the mechanical device are displayed; causing the information processing apparatus to display a second image, the plurality of pieces of partial time-series data being displayed on the second image at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image; as well as causing the information processing device to display a first mark marking first partial time series data and a second mark marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, When the first partial time series data displayed on the first image is selected while the second partial time series data corresponding to the first partial time series data is not displayed on the second image, the information processing device updates the second image so that the second partial time series data is displayed on the second image. 2 . The information processing method according to claim 1 , wherein the information processing device displays the plurality of pieces of partial time-series data on the second image at intervals shorter than intervals at which the plurality of pieces of partial time-series data are displayed on the first image. 3 . The information processing method according to claim 1 , wherein the information processing device displays the first mark and the second mark when the first portion of the time series data or the second portion of the time series data is selected. 4 . The information processing method according to claim 1 , wherein the information processing apparatus displays a third mark indicating a relationship between the first mark and the second mark. 5 . The information processing method according to claim 1 , wherein the information processing apparatus displays the second portion of time-series data by scrolling the second image in a predetermined direction.

6. The information processing method according to claim 1, wherein: When a plurality of pieces of first partial time series data or a plurality of pieces of second partial time series data are selected, the information processing apparatus displays a fourth mark indicating a time series relationship between the plurality of pieces of first partial time series data or the plurality of pieces of second partial time series data. 7 . The information processing method according to claim 1 , wherein the information processing device displays the second mark as a first point and a second point surrounding the selected second portion of the time series data. 8 . The information processing method according to claim 1 , wherein the information processing apparatus displays a second icon representing a physical quantity of the second portion of time-series data marked by the second mark.

9. The information processing method according to claim 1, Some of the time series data are extracted from multiple time series data based on predetermined conditions, and The information processing device displays the content of the predetermined condition or the date regarding the first portion of the time series data or the second portion of the time series data that has been selected.

10. An information processing method, the information processing method comprising: causing the information processing device to display a first image on which a plurality of partial time-series data of a physical quantity regarding a state of the mechanical device are displayed; causing the information processing apparatus to display a second image, the plurality of pieces of partial time-series data being displayed on the second image at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image; as well as causing the information processing device to display a first mark marking first partial time series data and a second mark marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, The information processing device displays a scroll bar for scrolling the first image or the second image. 11 . The information processing method according to claim 1 , wherein the information processing apparatus displays a rectangle as the second mark. 12 . The information processing method according to claim 1 , wherein the information processing apparatus displays the second mark transparently. 13 . The information processing method according to claim 1 , wherein the information processing device displays an inverted triangle as the first mark.

14. The information processing method according to claim 1, wherein: On the first image, the information processing device arranges and displays the plurality of pieces of partial time-series data on a linear scale in which time is set as an index. 15 . The information processing method according to claim 1 , wherein the information processing device is coupled to and displays the plurality of pieces of partial time-series data on the second image. 16 . The information processing method according to claim 1 , wherein the information processing apparatus displays a third icon for setting a normal state or an abnormal state for each of the plurality of pieces of partial time series data. The information processing method according to claim 16 , wherein the third icon is a check box.

18. An information processing method, the information processing method comprising: causing the information processing device to display a first image on which a plurality of partial time-series data of a physical quantity regarding a state of the mechanical device are displayed; causing the information processing apparatus to display a second image, the plurality of pieces of partial time-series data being displayed on the second image at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image; as well as causing the information processing device to display a first mark marking first partial time series data and a second mark marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, Part of the time series data is sensor data from sensors provided in the mechanical device.

19. The information processing method according to claim 1, wherein the partial time-series data on the second image is displayed in an enlarged view compared with the partial time-series data on the first image. 20 . A computer-readable non-transitory recording medium recording a program, wherein a computer executes the program to perform the information processing method according to claim 1 .

21. An information processing device, the information processing device being configured to display, a first image on which a plurality of partial time-series data of physical quantities regarding the state of the mechanical device are displayed, a second image on which the plurality of pieces of partial time-series data are displayed at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image, and a first mark for marking first partial time series data and a second mark for marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, When the first partial time series data displayed on the first image is selected while the second partial time series data corresponding to the first partial time series data is not displayed on the second image, the information processing device updates the second image so that the second partial time series data is displayed on the second image.

22. A method for manufacturing a product, the method comprising: causing the information processing apparatus according to claim 21 to display the first image and the second image; controlling a mechanical device based on the first image and the second image; as well as The mechanical device is caused to manufacture a product.

23. A method of acquiring learning data, the method comprising causing the information processing device according to claim 21 to acquire learning data, the learning data being used to generate a post-learning model for prediction of a failure of a mechanical device.

24. An information processing device, the information processing device being configured to display, a first image on which a plurality of partial time-series data of physical quantities regarding the state of the mechanical device are displayed, a second image on which the plurality of pieces of partial time-series data are displayed at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image, and a first mark for marking first partial time series data and a second mark for marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, The information processing device displays a scroll bar for scrolling the first image or the second image.

25. A method for manufacturing a product, the method comprising: causing the information processing apparatus according to claim 24 to display the first image and the second image; controlling a mechanical device based on the first image and the second image; as well as The mechanical device is caused to manufacture a product. 26 . A method of acquiring learning data, the method comprising causing the information processing device according to claim 24 to acquire learning data, the learning data being used to generate a post-learning model for prediction of a failure of a mechanical device.

27. An information processing device, the information processing device being configured to display, a first image on which a plurality of partial time-series data of physical quantities regarding the state of the mechanical device are displayed, a second image on which the plurality of pieces of partial time-series data are displayed at intervals different from intervals at which the plurality of pieces of partial time-series data are displayed on the first image, and a first mark for marking first partial time series data and a second mark for marking second partial time series data, wherein the first partial time series data is a predetermined piece of partial time series data among the plurality of pieces of partial time series data displayed on the first image, and the second partial time series data is a piece of partial time series data among the plurality of pieces of partial time series data displayed on the second image and corresponds to the first partial time series data, Part of the time series data is sensor data from sensors provided in the mechanical device.

28. A method for manufacturing a product, the method comprising: causing the information processing apparatus according to claim 27 to display the first image and the second image; controlling a mechanical device based on the first image and the second image; as well as The mechanical device is caused to manufacture a product.

29. A method of acquiring learning data, the method comprising causing the information processing device according to claim 27 to acquire learning data, the learning data being used to generate a post-learning model for prediction of a failure of a mechanical device.

Images