Information processing method and apparatus, recording medium, method of manufacturing product, method of acquiring learning data, display method and apparatus

Abstract

Information processing method and apparatus, recording medium, method of manufacturing product, method of acquiring learning data, display method and apparatus. A display apparatus includes a processing portion. The display apparatus is configured to display a physical quantity related to a state of a machine apparatus. The processing portion is configured to display an image in which a plurality of partial time-series data segments extracted from time-series data related to the physical quantity are arranged, in a state in which time information related to a time at which the plurality of partial time-series data segments have been acquired is provided in the image.

Description

Technical Field

[0001] This invention relates to information processing methods, information processing devices, etc. Background Technology

[0002] The operating state of a machine can change gradually, for example, due to changes in the state of its components. When the machine's operating state is within the permissible range set for its intended use, it is in its normal state. Conversely, when the machine's operating state is outside the permissible range, it is in a faulty state. For example, if the machine is a production machine and operates in a faulty state, it will cause problems such as producing defective products or halting the production line.

[0003] To prevent malfunctions as much as possible, maintenance work is typically performed on machinery (such as production machines) periodically or irregularly, even when the machines repeat the same operations. Shorter intervals between maintenance operations are effective in increasing preventative safety. However, if the frequency of maintenance is excessively increased, the operating rate of the production machine will decrease because the machine stops during maintenance. Therefore, it is preferable to detect production machines that are in normal condition but are about to malfunction. This is because if the arrival of a malfunction can be detected (predicted), maintenance work can be performed on the production machine at the time of detection (prediction). As a result, excessive reduction in operating rate can be prevented.

[0004] In known methods for predicting failures, machine learning is performed and a learning model is pre-created. The learning model learns the state of the machine; and in evaluation, the state of the machine is assessed using the learning model. To increase the accuracy of predictions, it is important to create a learning model suitable for predicting failures. For this reason, it is important to prepare learning data (training data) for the failure prediction model of the machine created through machine learning. To determine whether the extracted data is suitable for use as training data, it is necessary to perform detailed data analysis, such as waveform examination and comparison.

[0005] For example, in the data analysis method described in Japanese Patent Application Publication No. 2013-8234, multiple partial time-series data pieces are extracted from time-series data in which physical quantities of a production machine and measurement times are correlated. These multiple partial time-series data pieces are plotted on a single graph having an axis representing the elapsed time from a predetermined reference time. The user then shifts each of the plotted partial time-series data pieces along the time axis, such that the plotted partial time-series data pieces have a common reference point. Through this operation, the user compares the multiple partial time-series data pieces with each other. Summary of the Invention

[0006] According to a first aspect of the invention, an information processing method includes acquiring time-series data of physical quantities related to the state of a machine device by an information processing apparatus, extracting a plurality of partial time-series data segments from the time-series data by the information processing apparatus, and displaying an image in which the plurality of partial time-series data segments are arranged while time information is provided, the time information being related to the time at which the plurality of partial time-series data segments were acquired.

[0007] According to a second aspect of the invention, an information processing apparatus includes a processing section. The processing section is configured to acquire time-series data of physical quantities related to the state of a machine device, extract a plurality of partial time-series data segments from the time-series data, and display an image in which the plurality of partial time-series data segments are arranged, wherein time information is provided and is related to the time at which the plurality of partial time-series data segments have been acquired.

[0008] According to a third aspect of the invention, a method for displaying a physical quantity related to the state of a machine device includes displaying an image arranged with a plurality of partial time series data segments extracted from time series data related to the physical quantity while time information is provided, the time information being related to the time at which the plurality of partial time series data segments were acquired.

[0009] According to a fourth aspect of the invention, a display device is configured to display a physical quantity related to the state of a machine device. The display device includes a processing unit. The processing unit is configured to display, in a state where time information is provided, an image arranged with multiple partial time-series data segments extracted from time-series data related to the physical quantity, the time information being related to the time at which the multiple partial time-series data segments were acquired.

[0010] Further features of the invention will become clear from the following description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0011] Figure 1 This is a schematic functional block diagram illustrating the functional blocks of the time series data display device in the embodiment.

[0012] Figure 2 This is a diagram illustrating an example of the hardware configuration of a time-series data display device according to an embodiment.

[0013] Figure 3 This is a flowchart illustrating the control method of an embodiment.

[0014] Figure 4A This is a diagram illustrating an example of time series data collected by a time series data display device.

[0015] Figure 4B This is a diagram illustrating an example of event data collected by a time-series data display device.

[0016] Figure 5 This is a diagram illustrating an example of time-series data from a repetitive operation collected from a machine.

[0017] Figure 6A This is a diagram illustrating an example of time-series data collected while continuously performing repetitive operations.

[0018] Figure 6B It is a diagram showing time series data collected over a long period of time and compressed along the time axis.

[0019] Figure 7 This is an example of multiple extracted time series data segments located and displayed on a linear scale (i.e., an absolute time axis) that represents time as an index.

[0020] Figure 8 An example of a display image of an embodiment is shown.

[0021] Figure 9A An example of a display image of an embodiment obtained in the case of a stoppage caused by a fault is shown.

[0022] Figure 9B An example of information about stored events is shown.

[0023] Figure 10 Another example of a display image of an embodiment is shown.

[0024] Figure 11 Another example of the display image is shown.

[0025] Figure 12 This is a diagram illustrating an example of a time-series data display device connected to a six-axis articulated robot, as described in one embodiment.

[0026] Figure 13 An example of an image obtained after the editing process of an embodiment has been performed is shown.

[0027] Figure 14 Another example of an image obtained after the editing process of the embodiment has been performed is shown.

[0028] Figure 15 Another example of an image obtained after the editing process of the already performed embodiment is shown.

[0029] Figure 16A An example of an index added in the editor is shown.

[0030] Figure 16B This shows another example of an index added in the editor.

[0031] Figure 17 Another example of an image obtained after the editing process of the already performed embodiment is shown.

[0032] Figure 18 Another example of an image obtained after the editing process of the already performed embodiment is shown.

[0033] Figure 19 Another example of an image obtained after the editing process of the already performed embodiment is shown.

[0034] Figure 20 Another example of an image obtained after the editing process of the already performed embodiment is shown. Detailed Implementation

[0035] Generally, measurements are performed on machinery to obtain various parameters (physical quantities) to manage the operating status of the machinery. Therefore, a large amount of time-series data is acquired. To create a learning model suitable for predicting machinery failures, it is necessary to appropriately extract multiple data segments from the acquired large amount of data and perform detailed analysis (such as waveform inspection and comparison) to determine whether the extracted data is suitable for use as learning data.

[0036] However, because machinery (such as industrial robots installed on production lines) generally has a low failure rate, it is necessary to collect time-series data over long periods. Since the time-series data to be collected is used to manage the operational status of the machinery, there are many measurement parameters, and the sampling rate is set high to analyze waveforms in detail. As a result, the amount of data collected becomes enormous. Therefore, in situations where fault-related and irregularly occurring data segments need to be extracted from data collected over long periods at high sampling rates for comparisons, traditional data display methods place a heavy burden on workers, thus reducing work efficiency and accuracy.

[0037] In the simplest method, time series data is displayed on a single plot with a horizontal axis representing the measurement time. However, in this case, multiple fault-related data segments will be irregularly scattered along the long time axis, meaning these segments may not necessarily be displayed on the plot. If the time series data is compressed along the time axis to display multiple data segments on the plot, the waveform displayed on the plot will be distorted and lose its characteristics, even if the time series data was measured at a high sampling rate. As a result, it becomes difficult to inspect and compare waveforms. Furthermore, to analyze the waveforms in detail, the operator must perform operations (such as partially magnifying the waveform) themselves. Consequently, a significant amount of time is spent performing data analysis.

[0038] In the technology described in Japanese Patent Application Publication No. 2013-8234, multiple partial time series data segments to be added to a comparison chart are selected and extracted from a large amount of acquired time series data. The extracted partial time series data segments are then provided with elapsed times and displayed on the comparison chart such that one is displayed on top of another, and the extracted multiple time series data segments are in phase with each other on the elapsed time axis. Because the multiple partial time series data segments are located on the comparison chart so that they are in phase with each other on the elapsed time axis, the operator can compare the multiple partial time series data segments with each other. However, the operator's operation is cumbersome.

[0039] For this reason, it is desirable to realize information processing methods and information processing apparatuses that simplify the operations required to extract multiple partial data segments from time series data for inspection and comparison of the extracted multiple partial data segments.

[0040] The information processing method and information processing apparatus of the present invention will now be described with reference to the accompanying drawings.

[0041] Note that in the accompanying drawings referenced in the following embodiments, components given the same reference numerals have the same function, unless otherwise specified.

[0042] Figure 1 This is a schematic diagram illustrating the configuration of functional blocks of the information processing apparatus in an embodiment. Note that, in Figure 1 In this document, function blocks represent functional elements necessary to describe the features of an embodiment. Therefore, other function blocks that are commonly used and not directly related to the principles of the problem solved by this invention are not shown. Furthermore, since... Figure 1 The functional elements are conceptually shown to make their function understandable; therefore, the elements may not necessarily be physically present as described above. Figure 1 The functional blocks are connected to each other as shown. For example, the specific configuration of the functional blocks being distributed or unified is not limited to the example shown in the figure, and depending on the usage state, etc., some or all of the functional blocks may be distributed or unified in a predetermined unit, either functionally or physically.

[0043] like Figure 1 As shown, the time series data display device 100, which is used as an information processing device in an embodiment, is communicatively connected to the machine device 10 to be measured.

[0044] Machine device 10 is one of various industrial devices such as industrial robots and production devices deployed in production lines. Machine device 10 has various sensors 11 deployed for measuring physical quantities related to the state of machine device 10. For example, if machine device 10 is a jointed robot, then machine device 10 may have sensors for measuring, for example, the current value of the motor driving the joints, sensors for measuring the angle of the joints, and sensors for measuring speed, vibration, and sound. Note that since the above sensors are merely examples, appropriate types and numbers of sensors can be deployed in appropriate locations as sensors 11 depending on the type and purpose of machine device 10. Examples of sensors 11 may include force sensors, torque sensors, vibration sensors, sound sensors, image sensors, distance sensors, temperature sensors, humidity sensors, flow sensors, pH sensors, pressure sensors, viscosity sensors, and gas sensors. Note that, although for ease of illustration... Figure 1 A single sensor 11 is shown, but multiple sensors are typically deployed to enable communication with the time series data display device 100.

[0045] Machine device 10 is wirelessly or via wired connection to time series data display device 100, enabling machine device 100 to communicate with time series data display device 100, which functions as an information processing device. Therefore, time series data display device 100 can acquire data measured by sensor 11 through communication. The functional blocks of time series data display device 100 will be described sequentially below. Time series data display device 100 includes a control section 110, a storage section 120, a display section 130, and an input section 140.

[0046] The control section 110 includes multiple functional blocks, which are implemented by the CPU of the time series data display device 100 reading and executing control programs stored in, for example, a storage device or a non-transitory recording medium. In another case, some or all of the functional blocks can be implemented by hardware components (such as ASICs) included in the time series data display device 100.

[0047] Storage section 120 includes a time-series data storage section 121, an event data storage section 122, an extraction data storage section 123, a join data storage section 124, and an image information storage section 125. These sections of storage section 120 are appropriately allocated to storage areas of storage devices (such as hard disk drives, RAM, or ROM). Storage section 120 is a data storage section that stores the various types of data necessary to create images that allow users to easily view time-series data.

[0048] Display section 130 and input section 140 are user interfaces of time-series data display device 100. Display section 130 may include display devices such as liquid crystal displays or organic light-emitting diode displays. Input section 140 may include input devices such as keyboards, slow dials, mice, pointing devices, or voice input devices.

[0049] The data collection section 111 of the control section 110 acquires time-series data and event data related to the machine device 10 from the machine device 10; and stores the time-series data in the time-series data storage section 121 and the event data in the event data storage section 122. The data collection section 111 may be referred to as the data acquisition section.

[0050] The data collection section 111 collects time-series data and stores it in the time-series data storage section 121. The time-series data represents physical quantities related to the state of the machine device and measured by sensors 11 of the machine device 10, such as current, speed, pressure, vibration, sound, and temperature of each part. Alternatively, the data collection section 111 may acquire measurements from the sensors 11, calculate values ​​(such as maximum, minimum, average, integral, values ​​obtained by integration in the frequency domain, derivatives, or second derivatives) from the measurements in predetermined time periods, and store the resulting values ​​in the time-series data storage section 121.

[0051] Furthermore, the data collection section 111 collects event data related to events that have occurred in the machine device and stores the event data in the event data storage section 122. Events are set when the machine device has a predetermined state. For example, the data collection section 111 collects information about the time of an event as event data and stores the time information in the event data storage section 122. For example, if the event is a stop state of a machine device that typically performs repetitive operations (cyclic operations), then the data collection section 111 stores the date and time of the stop state in the event data storage section 122. Events causing a stop state in the machine device (such as malfunctions or maintenance) generally occur irregularly and at long intervals. Therefore, the information processing apparatus of the embodiment is suitable for handling such events that occur discretely and irregularly in time.

[0052] Depending on the event data stored in the event data storage section 122, the data extraction section 112 extracts a portion of the time series data related to the event from the time series data stored in the time series data storage section 121; and stores the portion of the time series data in the extraction data storage section 123.

[0053] For example, if the extraction condition is the stopping of the machine, then the data extraction section 112 reads data about the date and time of the machine stopping from the event data storage section 122 as event data. Depending on the event data, the data extraction section 112 extracts the measurements collected by sensors during the operating cycle prior to the machine stopping cycle; and stores the measurements as partial time series data in the extraction data storage section 123. In another case, the data extraction section 112 extracts values ​​calculated from measurements obtained during a predetermined time in the operating cycle prior to the machine stopping cycle from the time series data storage section 121, such as maximum, minimum, average, integral, values ​​obtained by performing integration in the frequency domain, derivative, or second derivative values. The data extraction section 112 then stores this value as partial time series data in the extraction data storage section 123.

[0054] Note that although the processing has been described for event data stored in event data storage section 122 and corresponding to a single type of event, there may be cases where event data storage section 122 stores event data related to multiple types of events. In this case, the operator can select one type of event from multiple types of events via input section 140; and data extraction section 112 extracts a partial time series data segment related to the selected type of event and stores the extracted partial time series data segment in extraction data storage section 123. In another case, an event of one type can be pre-registered from multiple types of events. In this case, a partial time series data segment related to the registered type of event can be automatically extracted and stored in extraction data storage section 123.

[0055] The data combining section 113 uses multiple partial time-series data fragments stored in the extraction data storage section 123 and creates a diagram in which the multiple partial time-series data fragments related to an event of a certain type are aligned. The data combining section 113 may be referred to as an image forming section or a processing section. For example, the data combining section 113 creates a diagram in which multiple partial time-series data fragments related to an event of a certain type are combined with each other or arranged close to each other on a horizontal axis representing the number of data fragments, etc.; and stores the combined data in the combining data storage section 124. The created image can be displayed on the display section 130 or printed using a printing device (not shown) if the worker (operator) needs to do so.

[0056] The editing section 114 edits the image created by the data combining section 113 and stores the edited image in the image information storage section 125. Specifically, the editing section 114 edits the image so that the edited image is convenient for the operator to perform work (e.g., makes it easy for the operator to understand the information). The editing section 1144 may be referred to as an image editing section or an editing part.

[0057] Specific examples of editing will be described later with reference to the accompanying drawings. For example, an image may be edited to easily identify each of multiple combined partial time-series data segments, show the attributes of each of the multiple combined partial time-series data segments, or show grouping of partial time-series data. For example, a portion of the image may be segmented or colored. Furthermore, monochrome gradations or textures may be added to the image; indexes, labels, or markers may be added to the image.

[0058] The edited image can be displayed on the display section 130 or printed using a printing device (not shown) if the worker (operator) needs to do so.

[0059] Figure 2 An example of the hardware configuration of the time-series data display device of an embodiment is illustrated schematically. For example... Figure 2 As shown, the time-series data display device includes PC hardware, which includes a CPU 1601 serving as the main control unit, and ROM 1602 and RAM 1603 serving as storage devices. ROM 1602 stores information (such as a processing program) implementing the information processing methods described later. RAM 1603 serves as the working area of ​​the CPU 1601, for example, when the CPU 1601 executes the information processing methods. Furthermore, the PC hardware is connected to an external storage device 1606. External storage device 1606 may be an HDD, SSD, or another network-installed system's external storage device.

[0060] The processing program of the CPU 1601 implementing the information processing apparatus and information processing method of the embodiment is stored in an external storage device 1606, which may be an HDD or an SSD, or in a storage portion (such as an EEPROM area) of ROM 1602. In this case, the processing program of the CPU 1601 implementing the information processing method (e.g., a time-series data display method) can be supplied to the aforementioned storage device or storage portion via a network interface 1607, and can be updated with a new program. In another case, the processing program of the CPU 1601 implementing the information processing method can be supplied to the aforementioned storage device or storage portion via one of various storage media (such as a disk, optical disk, flash memory) and its driving device; and can be updated. The storage medium, storage portion, or storage device storing the processing program of the CPU 1601 implementing the information processing method is a computer-readable recording medium for the information processing method or information processing apparatus of the present invention.

[0061] CPU 1601 is connected to sensor 11, which is in Figure 1 As shown in [the image]. Figure 2 For simplicity, sensor 11 is shown directly connected to CPU 1601. However, sensor 11 may also be connected to CPU 1601 via, for example, IEEE 488 (so-called GPIB). In another case, sensor 11 may be communicatively connected to CPU 1601 via network interface 1607 and network 1608.

[0062] Network interface 1607 can conform to wired communication standards such as IEEE 802.3, or wireless communication standards such as IEEE 802.11 or IEEE 802.15. CPU 1601 communicates with external devices 1104 and 1121 via network interface 1607. For example, in the case of displaying time-series data from an industrial robot, external devices 1104 and 1121 can be a general control unit and management server (such as a PLC and sequencer) deployed to control and manage the industrial robot.

[0063] exist Figure 2 In the example shown, as a user interface device (UI device), and Figure 1 The operation section 1604 corresponding to the input section 140 and the display device 1605 corresponding to the display section 130 are connected to the CPU 1601. The operation section 1604 can be a terminal such as a handheld terminal, or a device such as a keyboard, slow dial, mouse, pointing device, or voice input device (the operation section 1604 can be a control terminal including the above devices). The display device 1605 can be any device, as long as it can display information related to the processing performed by the data extraction section 112, data combining section 113, etc., on its display screen. For example, the display device 1605 can be a liquid crystal display device.

[0064] Next, refer to Figure 3 The flowchart will describe the information processing method (time series data display method) performed by the time series data display device 100. Figure 3 An example of the process performed by the time series data display device 100 is shown.

[0065] In step S101, the time series data display device 100 collects time series data and event data from the machine device 100.

[0066] Figure 4A An example of time-series data collected by the time-series data display device 100 is shown. This example is a series of data segments measured by periodically sampling the drive current of an industrial robot included in the machine device 10. The data collection section 111 of the time-series data display device 100 collects such multiple time-series data segments from the sensors 11 of the machine device 10 and stores the data in the time-series data storage section 121.

[0067] The time-series data collected by data collection section 111 will be described in more detail below. Figure 5 A diagram showing the current waveform obtained from time-series data of one cycle of normal operation of an industrial robot included in machine device 10 is shown. Figure 6A A diagram showing the current waveform obtained from time-series data collected during the continuous cyclical operation of an industrial robot is presented. Figure 6A The diagram includes a waveform SPW, whose amplitude differs from the other waveforms. Figure 6B It shows time series data collected over a long period of time and compared with... Figure 6A The time series data shown is displayed in a graph that is more compressed than it would be along the time axis. Figure 6B As shown in the diagram, there are two SPW waveforms, whose amplitudes differ from the other waveforms. However, because the waveforms of the cyclic operation are compressed along the time axis, it is impossible to perform a detailed examination and comparison of the waveforms.

[0068] Figure 4B An example of event data collected by the time-series data display device 100 is shown. The event is defined as a stop of an industrial robot in the machine unit 10, and the event data is recorded as the time the event occurred. In this example, the event is a robot stop caused by maintenance work performed periodically or irregularly, or a robot stop caused by an irregular robot malfunction. The data collection section 111 collects event data while collecting time-series data by receiving control information from the control section that manages the operation of the machine unit 10, and stores the event data in the event data storage section 122.

[0069] Return to Figure 3 In step S102, the data extraction unit 112 extracts a portion of the time series data related to the event from the time series data stored in the time series data storage unit 121. The event is freely selected by the worker (operator) from the event data stored in the event data storage unit 122. However, the event can be automatically selected by the control unit 110.

[0070] For example, data extraction section 112 from Figure 4A Time series data extraction and from Figure 4BThe event data is selected as a partial time series data segment related to the selected event. Specifically, the data extraction section 112 extracts time series data segments contained in the period preceding the period in which the selected event occurs (i.e., the industrial robot stops) as partial time series data. Note that the above extraction is an example. For example, the data extraction section 112 may extract time series data segments contained in the period preceding the period in which the selected event occurs by a predetermined number of operating periods as partial time series data. In another case, the data extraction section 112 may extract multiple time series data segments contained in multiple consecutive operating periods as partial time series data. In yet another case, the data extraction section 112 may extract time series data segments contained in the period in which the selected event occurs itself as partial time series data. The extracted partial time series data segments, together with the time information associated with the extracted partial time series data segments, are stored in the extraction data storage section 123.

[0071] Incidentally, assume that the extracted partial time series data segments are arranged on a linear scale that represents time as an index (i.e., an absolute time axis). Figure 7 The display screen W is shown schematically. In the diagram, because most of the time series data in the continuous operation was not extracted, the multiple unextracted time series data segments are not plotted; instead, only the waveform of a portion of the time series data related to one type of event is shown. Therefore, with... Figure 6B Compared to the previous diagram, redundancy is significantly reduced. However, if time-series data is collected over a long period, the waveforms of multiple partial time-series data segments will be compressed and distorted along the time axis on the display screen W. Therefore, it is impossible to examine the waveform details. If the waveform is extended along the time axis for easier observation and comparison of multiple partial time-series data segments, the waveform may extend beyond the display screen. This is because the waveforms of multiple partial time-series data segments are separated from each other and positioned at irregular intervals.

[0072] Therefore, in the embodiment, in step S103, the data combining section 113, which serves as the processing section, combines multiple partial time-series data segments stored in the extraction data storage section 123, and stores the combined data in the combining data storage section 124. That is, compared to the case where the multiple extracted partial time-series data segments are arranged on a linear scale that represents time as an index, the data combining section 113 creates an image (combined data) in which the multiple extracted partial time-series data segments (e.g., diagrams) are arranged closer to each other. Specifically, the data combining section 113 arranges the multiple partial time-series data segments (e.g., diagrams) such that one partial time-series data segment is combined with an adjacent partial time-series data segment, or one partial time-series data segment is deployed adjacent to another partial time-series data segment, with short gaps inserted between them. For example, the data combining section 113 performs image processing, such that... Figure 7 The distance between the waveform of one partial time series data segment and the waveform of an adjacent partial time series data segment in the horizontal axis direction has a zero value or a predetermined small value. In this way, the data combining portion 113 makes the distance between the waveforms shorter.

[0073] In step S104, the time series data display device 100 displays a graph on the display section 130 using the combined data stored in the combined data storage section 124. If necessary, the graph can be extended in the horizontal axis direction to facilitate waveform observation and comparison. Preferably, the index (scale) of the horizontal axis of the graph is not absolute time, but rather the number of samples of the original measurement data, the number of operation cycles, etc. As described above, multiple partial time series data segments that are originally separated from each other and positioned at irregular intervals are deployed adjacent to each other. Therefore, if the index (scale) of the horizontal axis in the graph is absolute time, the index value will jump discontinuously at the boundary between one partial time series data segment and another, making it difficult for the operator to intuitively and easily understand the graph.

[0074] Note that in step S104, the time series data display device 100 may not display the created image on the display portion 130. Instead, the time series data display device 100 may send the image to another display device other than the time series data display device 100 and have that other display device display the image, or it may send the image to a printing device and have that printing device print the image. That is, the time series data display device 100 can choose the method of outputting the created image according to the convenience of the worker (operator).

[0075] Figure 8 An image displayed on the display screen W of the display section 130 in step S104 is shown as an example. Figure 8 In this diagram, a partial time-series data segment associated with one type of event is combined with another partial time-series data segment along the horizontal axis so that they are adjacent to each other. That is, the event data corresponds to the stopping of the industrial robot; partial time-series data segments are extracted for each event from the time-series data obtained by monitoring the current values ​​of the industrial robot; and multiple partial time-series data segments are combined with each other in the diagram. Therefore, the diagram only shows multiple partial time-series data segments that are associated with the occurrence of the event and combined with each other. Thus, the worker (operator) can easily perform checks and comparisons on the waveforms (diagrams) associated with the occurrence of the event.

[0076] For example, if the event (stop) is caused by an inspection performed on a machine in normal operation, then the waveform of a portion of the time series data segment will become similar to... Figure 5 The waveforms are similar. Figure 5 The waveform is the waveform of one operating cycle of a machine device in normal condition. Therefore, in Figure 8 In the illustrated embodiment, the worker (operator) can easily check the similarity of the waveforms. If the event (stop) is caused by a malfunction of the machine, then the waveforms of some time-series data segments become anomalous, like... Figure 8 As shown in ABN1 or ABN2, these waveforms are dissimilar to normal waveforms. Therefore, such anomalous waveforms, dissimilar to normal waveforms, can be easily identified and compared with other waveforms related to the event. Consequently, workers (operators) can easily extract learning data for creating fault prediction models.

[0077] Figure 8 Examples of extraction conditions (predetermined events) in step S102 include both stops caused by inspection of a machine in normal condition and stops caused by a malfunction of the machine. However, the worker can change the extraction conditions (predetermined events) of step S102 according to the purpose of the work. For example, if the worker expects to perform comparisons only on waveforms related to stops caused by malfunctions and to study the correlation between the cause of the malfunction and the waveforms, then the worker can set the stop caused by the malfunction as the event used as the extraction condition for step S102.

[0078] As an example, Figure 9A The image shown illustrates a display obtained by setting a stop caused by a fault as an event. In the image, a waveform from one partial time series data segment associated with the event is combined with another waveform from another partial time series data segment so that they are adjacent to each other along the horizontal axis. In this example, the index of the horizontal axis is the number of operating cycles, and the diagram provides vertical lines at the points where one waveform is combined with another to make the boundaries between events easily identifiable. Figure 9B Detailed information related to the events stored in the event data storage section 122 is shown. Figure 9A In China, regarding Figure 9B The detailed information of the events shown is illustrated in association with the corresponding waveforms of multiple partial time series data segments. Therefore, the worker (operator) can easily understand from the waveforms displayed on the screen and the detailed information about the events that, as an indication of a malfunction, the maximum value of the waveform peaks abnormally increases when the machine malfunctions and stops due to excessive motor load. Furthermore, the worker (operator) can easily understand that, as an indication of a malfunction, the number of peaks observed in an operating cycle increases when the machine malfunctions and stops due to brake failure. Therefore, by examining in detail the events used to extract partial time series data, the worker (operator) can easily understand the characteristics of each partial time series data segment extracted using the corresponding events. Therefore, the worker (operator) can easily determine whether partial time series data segments can be used as learning data for machine learning. Thus, the worker (operator) can efficiently and easily extract learning data for creating fault prediction models.

[0079] Furthermore, to increase worker (operator) efficiency, in addition to combining waveforms of multiple partial time-series data segments and event-related details, input areas where workers (operators) can write information can be deployed in the image. For example, checkboxes, drop-down menus, icons, etc., can be displayed in the image for workers (operators) to extract waveforms as learning data. In another case, boxes can be deployed in the image for workers (operators) to write comments or memos.

[0080] Figure 10Another example of the display image of the embodiment is shown. In this example, one partial time series data segment (plot) is deployed adjacent to another partial time series data segment (plot), with a predetermined short gap inserted between them, so that the worker (operator) can easily visually identify the boundary between the two partial time series data segments. Furthermore, each plot is provided with a label indicating information about the event. In this example, the label indicates the subcategory of the machine stoppage (event). Specifically, each label indicates a stoppage of the machine in a normal state (e.g., a stoppage caused by inspection) or a stoppage of the machine in an abnormal state (e.g., a stoppage caused by a malfunction). The label is displayed in the image as a label associated with the corresponding plot. Above each label, a checkbox is displayed to determine whether the corresponding waveform should be used as learning data for creating a fault prediction model. The labels and checkboxes can be displayed by the worker (operator) instructing the time series data display device 100 via input section 140, or they can be displayed automatically by the control program.

[0081] In the example above, multiple partial time-series data segments related to a single type of physical quantity (such as current value) are extracted; and the plots of these multiple partial time-series data segments are displayed adjacent to each other on the horizontal axis. However, the plot displayed on a single screen may not be related to multiple partial time-series data segments associated with a single type of physical quantity. That is, plots related to multiple partial time-series data segments associated with multiple types of physical quantities can be displayed on the same screen. In this case, the plot is convenient for extracting learning data for creating a fault prediction model because the worker (operator) can easily determine the correlation between different types of physical quantities related to the event.

[0082] Figure 11 Another example of a display image of an embodiment is shown. In this example, in Figure 3In step S102 of the flowchart, multiple partial time-series data segments of current and pressure related to the event of device shutdown are extracted. Then, in step S103, for each of the current and pressure values, the extracted multiple partial time-series data segments are combined with each other. In step S104, the current value plot and the pressure plot are deployed vertically, such that the event in the current value plot is phase-synchronized with the event in the pressure plot in the horizontal axis direction. As a result, it can be understood that if an abnormal waveform causing an excessively high current peak appears, then an abnormal waveform causing an excessively low pressure peak appears. Therefore, the operator can easily understand that the event causes a high correlation between current and pressure. Furthermore, it can be understood that even if an abnormal waveform that increases the number of peaks in an operating cycle appears, the corresponding pressure waveform remains normal. Therefore, the operator can understand that the event causes a low correlation between current and pressure. As described above, the plot only shows multiple partial time-series data segments related to the occurrence of the event and combined with each other. Therefore, the operator can easily perform checks and comparisons on the plots related to the occurrence of the event. Therefore, workers (operators) can efficiently and easily extract learning data for creating fault prediction models.

[0083] As mentioned above, with, for example Figure 6B Compared to the previous illustration, the image displayed in step S104 increases the worker's efficiency. Furthermore, the time-series data display device of this embodiment also includes an editing section 114 for further image editing.

[0084] Return to reference Figure 3 The flowchart shows that in step S105, the editing section 114 performs editing processing on the image (combined data) stored in the combined data storage section 124, and stores the edited image in the image information storage section 125. That is, the editing section 114 edits the image to facilitate the worker's work and stores the edited image in the image information storage section 125. Using this operation, the worker can display the edited image on the display device at any time (e.g., when the worker is creating training data for machine learning), or can print or re-edit the image.

[0085] Figure 13The image IG1, obtained after editing by editing section 114 in step S105, is shown. In image IG1, the plot created in step S103 (which has a horizontal axis representing the number of periods, and where multiple partial time-series data segments related only to predetermined events are combined with each other) is supplemented with information (time information) INF1 regarding the time (year and month) when the predetermined events occurred. The time information INF1 serves as a label. Furthermore, the image is edited to provide boundary lines (dotted lines SC1) between adjacent months to allow workers to easily understand the information. If multiple predetermined events occur within a single month, the year and month information INF1 is displayed as labels (not for each event, but for each month) to allow workers to easily understand the plot.

[0086] Next, an example of a specific data processing method will be described. Editing section 114 divides the plot created in step S103 by simply combining multiple partial time-series data segments into partial plots, using the year and month of the predetermined event as the unit; and adds information INF1 to each of the partial plots. Then, editing section 114 again combines the partial plots with each other, and provides boundary lines (dotted lines SC1) at the boundaries between one year and month and another. Since this is an example, it can be created using different data processing methods. Figure 13 The image shown is an example of this. When editing is performed in step S105, the editing section 114 can cause the display section 130 to display images and information related to the editing, and the operator can input commands to the editing section 114 via the input section 140.

[0087] In step S106, the time series display device 100 causes the display section 130 to display the edited image stored in the image information storage section 125. Step S106 can be performed at any time (e.g., when a worker creates training data for machine learning).

[0088] Note that in step S106, the time series data display device 100 may choose not to display the edited image on display section 130. Instead, the time series data display device 100 may send the edited image to another display device other than the time series data display device 100 and have that other display device display the edited image, or it may send the edited image to a printing device and have the printing device print the edited image. That is, the time series data display device 100 can choose the method of outputting the edited image according to the convenience of the worker (operator).

[0089] Images edited in this way allow workers to easily identify the year and month in which the scheduled events occur, the number of scheduled events extracted in each month (i.e., whether the number is large or small in each month), and the regularity of the months in which the scheduled events occur.

[0090] The information displayed as labels through editing is not limited to year and month information INF1. For example, Figure 14 This shows that, except for the image IG1 (which has already been executed) Figure 13 The image IG2 is obtained after editing processes other than those performed on the image.

[0091] As in image IG1, editing section 114 displays year and month information INF1 and boundary lines (dotted lines SC1) in image IG2. Furthermore, editing section 114 adds information INF2 about the date of the scheduled event to image IG2. The day information INF2 is a label.

[0092] Images edited in this way allow workers to easily understand how many days a scheduled event occurs, or whether a scheduled event tends to occur during a specific period of the month (e.g., whether a scheduled event tends to occur at the end of the month).

[0093] It's important to note that the information added to an image during editing is not limited to information about the year, month, and day. For example, the information could represent the number of a cycle in which a predetermined event occurs (the cycle number is relative to the start setting of a continuous operation).

[0094] Furthermore, the editing processes performed by the editing section 114 are not limited to adding indexes, labels, tags, etc. That is, in order to easily identify each of the multiple combined partial time series data segments, show the attributes of each of the multiple combined partial time series data segments, or show the grouping of partial time series data, the image can be edited using another method. For example, color or monochrome gradients or textures representing information can be added to the image.

[0095] exist Figure 13 In the example shown, information about the year and month of the scheduled event is displayed as a label (Information INF1) using text. However, different editing processes can be performed. For example, Figure 15 This shows that, except for the image IG1 (which has already been executed) Figure 13 The image IG3 is obtained after editing processes other than those performed on the image.

[0096] To illustrate information about the month in which the scheduled event will occur, editing section 114 provides a corresponding monochrome gradient hue to the background portion BG1 of the illustration image for the month. For example, as shown in image IG3, the relationship between the month and the monochrome gradient is set such that the hue gradually darkens as time progresses from the beginning to the end of the year. As a result, the image allows workers to easily and intuitively understand the relationship between each part of the illustration and the corresponding time period of the year.

[0097] Furthermore, for the convenience of workers, image IG3 is indexed with MGD1, which serves as a scale indicating the relationship between months and monochrome gradients. Note that the index is not limited to... Figure 15 The example shown. For example, an index could be... Figure 16A The index shown or Figure 16B The index shown.

[0098] It should be noted that the information expressed using monochrome gradients, etc., is not limited to year and month information. Furthermore, the editing processes performed to express information are not limited to those used to provide monochrome gradients. For example, editing processes can provide different colors, different types of textures, or combinations thereof. In this case, it is preferable to display an index (such as a color chart or texture chart) corresponding to the processing in the image instead of index MGD1.

[0099] Figure 15 The image IG3 shown contains comment information COMT provided by the worker in steps S103, S105, or S106. In one of the steps, for example, the worker can input the comment information COMT via the input section 140 while the display section 130 displays the image and other information.

[0100] Figure 17 As an example, image IG4 is shown after different editing processes have been performed. In this example, to express information about the month in which a predetermined event occurred, a graphic identifying the corresponding month is provided. Specifically, an arrow VEC representing the length of a month is provided as a graphic representing a time period. Note that the graphic provided in the image is not limited to arrows and can be any graphic, as long as the information expressed by the graphic is easily visually recognizable and intuitively understood by the worker.

[0101] The arrow VEC is provided with a monochrome gradient hue set for the corresponding month. Furthermore, it is similar to the image IG3 (…). Figure 15 The image IG4 is supplemented with an index MGD1 indicating the relationship between each month and the corresponding monochrome gradient hue provided to arrow VEC. Therefore, the image allows workers to easily and intuitively understand the relationship between each part of the diagram and the corresponding time period of the year.

[0102] Figure 18 As an example, image IG5 is shown after different editing processes have been performed. In this example, the image was edited so that even-numbered months where the scheduled event occurs are grouped separately from odd-numbered months where the scheduled event occurs, and months where the scheduled event does not occur are easily identifiable. Specifically, in Figure 18 In the example, the background portions of even-numbered months in the diagram are colored gray, and the background portions of odd-numbered months are colored white. Furthermore, the background portions of months in which the predetermined event (i.e., the shutdown of machinery) did not occur are spaced apart from adjacent diagrams and colored light gray. Additionally, for the convenience of the worker, the edited content is displayed as COMT2 in image IG5. Therefore, the image allows the worker to easily and intuitively understand the relationship between each part of the diagram and the corresponding time period of the year.

[0103] Figure 19 As an example, image IG6 is shown after different editing processes have been performed. In this example, as... Figure 15 As shown in the example, the background portion BG1 of each month in the illustrated image is provided with a corresponding monochrome gradient tone. Furthermore, information about attributes related to a predetermined event is added to the image. In the illustration, the predetermined event is the shutdown of the machine, and multiple data segments associated with the predetermined event are extracted and combined with each other. Incidentally, the shutdown of the machine is caused by one of various factors, including periodic inspections, malfunctions, and operational stoppages. Therefore, in Figure 19 In the example, to easily and visually identify the parts of a series of images related to periodic inspections, a marker INF3 is provided in the image to indicate that the part is related to periodic inspections. Furthermore, for the convenience of the worker, a marker definition information MGD4 and a comment box COMT3 are deployed in the image. The comment box COMT3 is a box for the worker to write information about the scheduled event. Therefore, the image allows the worker to easily identify the parts related to the stop caused by periodic inspections in a series of images. In this example, the worker can easily see how much the waveform obtained in the operation cycle just before the stop caused by the periodic inspection has changed from the waveform obtained in the normal state of the machine. Furthermore, the worker can also see the ratio of periodic inspections to the total stoppage of the machine. Therefore, using these information fragments, for example, the worker can easily determine whether the interval of periodic inspections is appropriate.

[0104] The information added to the image that is related to the attributes of the scheduled event is not limited to information about periodic checks. For example, information related to faults can be added to the image.

[0105] exist Figure 20In the image IG7 shown, to easily and visually identify the fault-related portions of a series of plots, marker INF4 and marker definition information MGD5 are added to the image. Marker INF4 indicates that the portion is fault-related. Therefore, the image allows the operator to easily identify portions related to fault-induced stops within a series of plot images. In this example, the operator can easily observe the intervals of fault-induced stops, the medium- to long-term trends of increased or decreased fault occurrences, the ratio of fault-induced stops to total machine stops, etc. Furthermore, the operator can easily identify two types of waveforms obtained during the operating cycle immediately preceding the fault-induced stop. That is, in one type, the maximum value of the waveform peaks is unusually high; and in the other type, the number of peaks observed during the operating cycle increases.

[0106] Example of a connection between a time-series data display device and a robot

[0107] Figure 12 An example of a time-series data display device 100 of an embodiment is shown connected to a six-axis articulated robot, which is an example of a machine device 10.

[0108] The links 200 to 206 of the six-axis articulated robot are linked in series with each other via six rotary joints J1 to J6. The six-axis articulated robot includes sensors that measure the rotational speed of the motors of the corresponding rotary joints, sensors that measure the rotational angle of the corresponding joints, torque sensors, sensors that measure the current of the corresponding motors, and pressure sensors that measure the air pressure driving the actuators. Actuators (such as robot hands 210) can be detachably attached to the distal links.

[0109] The six-axis articulated robot is communicatively connected to the time-series data display device 100 of this embodiment. The time-series data display device 100 collects time-series data of physical quantities related to the robot's state, as well as event data related to events that have occurred within the robot.

[0110] For example, a six-axis articulated robot repeatedly performs operations to assemble components into a product. An operator can instruct a time-series data display device 100 via input section 140, and cause the time-series data display device 100 to form an image that can be displayed or printed.

[0111] For example, when a six-axis articulated robot performs operations for manufacturing a product, an image can be formed by combining multiple partial time-series data segments associated with selected events (e.g., malfunctions) and displayed on display portion 130. Since the displayed image allows the operator to easily review the robot's history related to the events, the operator can determine, for example, whether to allow the robot to continue manufacturing the product. Therefore, by utilizing the time-series data display device 100 of the present invention, which is connected to a manufacturing apparatus (such as a robot) and displays partial time-series data, product manufacturing can be carried out while preventing stoppages caused by malfunctions of the manufacturing apparatus.

[0112] Furthermore, the operator can use the time series data display device 100 to create training data (learning data) for building a learning model to predict robot malfunctions. The operator can select events from the event data acquired by the time series data display device 100, causing the device to extract multiple partial time series data segments related to various types of physical quantities, and displaying the images on a graph that the operator can easily perform comparisons, etc. For example, if using... Figure 10 The checkboxes shown allow the operator to easily set flags for data segments they have determined are suitable for machine learning training. Therefore, the operator can easily create training data (learning data).

[0113] Furthermore, although this embodiment has described a case in which the machine device 10 is an example six-axis articulated robot, the present disclosure is not limited thereto. For example, the machine device 10 may be a machine device that can automatically perform expansion and contraction, bending and stretching, up and down movement, left and right movement, pivoting, or combinations thereof based on information stored in a storage device of a control device.

[0114] It should be noted that the present invention is not limited to the above embodiments, and various modifications can be made within the technical concept of the present invention.

[0115] For example, embodiments of the invention are not limited to diagrams of physical quantities associated with a single type of event. For example, in Figure 3 In step S102 of the flowchart, multiple types of events can be set as extraction conditions. Then, in step S103, for each of the multiple types of events, multiple partial time-series data segments of the physical quantity can be extracted, and a diagram in which the multiple partial time-series data segments are combined with each other along the horizontal axis can be formed. In step S104, the diagram can be displayed adjacent to each other in a single screen. The diagram is convenient for operators to study the correlation between different types of events for the physical quantity.

[0116] Other embodiments

[0117] Embodiments of the present invention can also be implemented by a computer of a system or apparatus that reads and executes computer-executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be more fully referred to as a 'non-transitory computer-readable storage medium') to perform one or more functions of the above embodiments and / or includes one or more circuits (e.g., application-specific integrated circuits (ASICs)) for performing one or more functions of the above embodiments, and by a method performed by a computer of the system or apparatus by, for example, reading and executing computer-executable instructions from the storage medium to perform one or more functions of the above embodiments and / or controlling one or more circuits to perform one or more functions of the above embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessor unit (MPU)) and may include separate computers or networks of separate processors to read and execute computer-executable instructions. The computer-executable instructions may be provided to the computer, for example, from a network or storage medium. The storage medium may include, for example, a hard disk, random access memory (RAM), read-only memory (ROM), storage devices for distributed computing systems, optical discs (such as CDs, DVDs, or Blu-ray discs). TM One or more of the following: flash memory devices, memory cards, etc.

[0118] The embodiments of the present invention can also be implemented by providing software (programs) that perform the functions of the above embodiments to a system or device via a network or various storage media, and the computer or central processing unit (CPU) or microprocessor unit (MPU) of the system or device reads out and executes the program.

[0119] While the invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. The scope of the following claims is to be given the broadest interpretation in order to cover all such modifications and equivalent structures and functions.

Claims

1. An information processing method comprising: acquiring, by an information processing apparatus, time series data of a physical quantity related to a state of a machine apparatus; extracting, by the information processing apparatus, a plurality of partial time series data segments from the time series data; displaying an image in which each of the plurality of partial time series data segments is arranged closer to each other than in a case where the plurality of partial time series data segments are arranged in the time series data before the extracting; and displaying the image with time information related to a time at which the plurality of partial time series data segments have been acquired.

2. The information processing method according to claim 1, wherein The plurality of partial time series data segments are extracted depending on event data related to an event occurring in the machine apparatus.

3. The information processing method according to claim 1, wherein The time series data from which the plurality of partial time series data segments have not been extracted is located on a linear scale in which time is represented as an index.

4. The information processing method according to claim 1, wherein The image is displayed on a display portion.

5. The information processing method according to claim 1, wherein The image contains a graph that represents the physical quantity, in combination with each other, and in relation to the plurality of partial time series data segments.

6. The information processing method according to claim 1, wherein The image contains a graph that represents the physical quantity and is arranged separately from each other in relation to the plurality of partial time series data segments, respectively.

7. The information processing method according to claim 1, wherein The image contains information about a predetermined event.

8. The information processing method according to claim 1, wherein The information processing apparatus acquires time series data related to a plurality of types of physical quantities, extracts the plurality of partial time series data segments related to the plurality of types of physical quantities from the time series data, and displays an image in which information about the plurality of partial time series data segments is arranged for each of the plurality of types of physical quantities.

9. The information processing method according to claim 1, wherein The information processing apparatus acquires event data related to a plurality of types of events occurring in the machine apparatus, extracts the plurality of partial time series data segments related to at least two types of events selected from the plurality of types of events, and displays an image in which information about the plurality of partial time series data segments related to the at least two types of events is arranged.

10. The information processing method according to claim 1, wherein The image contains an input area in which an operator writes information.

11. The information processing method according to claim 1, further comprising setting a manner in which the time information is displayed.

12. The information processing method according to claim 1, wherein The time information is displayed in the image by using a single color gradient, a color, or a texture.

13. The information processing method according to claim 12, wherein The time information is displayed in the image in a background portion of the plurality of partial time series data segments.

14. The information processing method according to claim 12, wherein The time information is displayed for each month in which the plurality of partial time series data segments have been acquired by using different single color gradients, different colors, or different textures.

15. The information processing method according to claim 12, wherein The time information is displayed so that a hue of a single color gradient gradually increases as time progresses from the beginning of a year toward the end of the year.

16. The information processing method according to claim 1, wherein A color of a background portion of a partial time series data segment extracted from time series data acquired in an even month is made different from a color of a background portion of a partial time series data segment extracted from time series data acquired in an odd month.

17. The information processing method according to claim 16, wherein Backgrounds of partial time-series data pieces acquired in one of even months and odd months are colored in gray, and backgrounds of partial time-series data pieces acquired in the other of even months and odd months are colored in white.

18. The information processing method according to claim 2, wherein If the event does not occur in a month, a gap corresponding to the month is formed between partial time-series data pieces extracted from the time-series data, and the gap is colored with a color different from a color of a background portion of a partial time-series data piece acquired in a month in which the event occurs.

19. The information processing method according to claim 1, wherein The time information is displayed in the image by using a character and / or a figure.

20. A computer-readable non-transitory recording medium storing a program causing a computer to execute the information processing method according to any one of claims 1 to 19.

21. An information processing apparatus comprising a processing portion, wherein, The processing portion is configured to acquire time-series data of a physical quantity related to a state of a machine device; extract a plurality of partial time-series data pieces from the time-series data; display an image in which each of the plurality of partial time-series data pieces is arranged closer to each other than in a case where the plurality of partial time-series data pieces are arranged in the time-series data before the extraction; and display the image with time information related to a time at which the plurality of partial time-series data pieces have been acquired.

22. The information processing apparatus according to claim 21, wherein When the plurality of partial time-series data pieces are arranged in the image, the processing portion arranges the plurality of partial time-series data pieces such that a distance between one of the plurality of partial time-series data pieces and another of the plurality of partial time-series data pieces is smaller than a distance between the one of the plurality of partial time-series data pieces before the extraction and the another of the plurality of partial time-series data pieces before the extraction.

23. The information processing apparatus according to claim 21, further comprising a display portion configured to display the image.

24. A method of manufacturing a product, comprising: acquiring, by the information processing apparatus according to any one of claims 21 to 23, the time-series data acquired when the machine device performs an operation for manufacturing a product; and displaying, by the information processing apparatus according to any one of claims 21 to 23, the image.

25. A method of acquiring learning data, comprising: displaying, by the information processing apparatus according to claim 21, the image for an operator to acquire learning data for creating a learning model that predicts a failure of the machine device.

26. A display method of a physical quantity related to a state of a machine device, the display method comprising: acquiring time-series data of a physical quantity related to a state of a machine device; extracting a plurality of partial time-series data pieces from the time-series data; displaying an image in which each of the plurality of partial time-series data pieces is arranged closer to each other than in a case where the plurality of partial time-series data pieces are arranged in the time-series data before the extraction; and displaying the image with time information related to a time at which the plurality of partial time-series data pieces have been acquired.

27. A display device configured to display a physical quantity related to a state of a machine device, the display device comprising: a processing portion configured to: acquire time-series data of a physical quantity related to a state of a machine device; extract a plurality of partial time-series data pieces from the time-series data; display an image in which each of the plurality of partial time-series data pieces is arranged closer to each other than in a case where the plurality of partial time-series data pieces are arranged in the time-series data before the extraction; and display the image with time information related to a time at which the plurality of partial time-series data pieces have been acquired.

28. The information processing method according to claim 2, wherein The information processing device displays information of the event corresponding to a waveform of partial time-series data.

29. The information processing method according to claim 2, wherein The information processing device displays a label for each of partial time-series data, the label indicating whether the event is in a normal state or an abnormal state.

Images