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

Abstract

Information processing method and apparatus, display method and apparatus, recording medium, product manufacturing method, and learning data acquisition method are disclosed. A display apparatus for displaying a physical quantity related to a state of a machine apparatus includes a processing portion. The processing portion is configured to display an image such that a distance between one of a plurality of extracted partial time-series data pieces extracted from time-series data of the physical quantity and another of the plurality of extracted partial time-series data pieces is smaller than a distance between the one of the plurality of partial time-series data pieces before extraction and the another of the plurality of partial time-series data pieces before extraction.

Description

TECHNICAL FIELD

[0001] The present application relates to an information processing method, an information processing apparatus, and the like. BACKGROUND

[0002] An operating state of a machine device can gradually change, for example, due to a change in a state of a component of the machine device. When the operating state of the machine device is within an allowable range set for a use purpose of the machine device, the machine device is in its normal state. In contrast, when the operating state of the machine device is outside the allowable range, the machine device is in a failure state. For example, if the machine device is a production machine and operates in the failure state, the production machine will cause troubles such as manufacturing of defective products or stop of a production line.

[0003] In order to prevent the failure state as much as possible, it is common to perform a maintenance work on a machine device such as a production machine periodically or aperiodically even if the machine device repeats the same operation. In order to increase a preventive safety, it is effective to make an interval of performing the maintenance work shorter. However, if the frequency of the maintenance work is excessively increased, the operating rate of the production machine will decrease because the production machine is stopped during the maintenance work. Therefore, it is preferable to detect a state of the production machine which is in its normal state but will soon have a failure state. This is because if the arrival of the failure state can be detected (predicted), the maintenance work can be performed on the production machine at a point of time when the arrival of the failure state is detected (predicted). As a result, the operating rate can be inhibited from being excessively decreased.

[0004] In a known method of predicting the occurrence of a failure, machine learning is performed and a learning model is created in advance. The learning model has learned a state of a machine device; and in an evaluation, the state of the machine device is evaluated by using the learning model. In order to increase an accuracy of the prediction, it is important to create a learning model suitable for predicting a failure. For this reason, it is important to prepare learning data (training data) for a failure prediction model of the machine device created by the machine learning. In order to determine whether or not the extracted data is suitable for the learning data, it is necessary to perform a detailed data analysis such as an inspection and comparison of waveforms.

[0005] For example, in a data analysis method described in Japanese Patent Application Publication No. 2013-8234, a plurality of partial time series data segments are extracted from time series data in which physical quantities of a production machine and measurement times are associated with each other. The plurality of partial time series data segments are plotted on a single graph having an axis representing time elapsed from a predetermined reference time. Then, a user shifts each of the plotted plurality of partial time series data segments in an elapsed time axis direction so that the plotted plurality of partial time series data segments have a common reference point. By this operation, the user compares the plurality of partial time series data segments with each other. SUMMARY

[0006] According to a first aspect of the present application, an information processing method includes acquiring, by an information processing apparatus, time series data of a physical quantity related to a state of a machine device; extracting, by the information processing apparatus, a plurality of partial time series data segments from the time series data; and displaying, by the information processing apparatus, an image such that a distance between one of the plurality of extracted partial time series data segments and another of the plurality of extracted partial time series data segments is smaller than a distance between the one of the plurality of partial time series data segments before extraction and the another of the plurality of partial time series data segments before extraction.

[0007] According to a second aspect of the present application, an information processing apparatus includes a processing portion. 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 segments from the time series data; and display an image such that a distance between one of the plurality of extracted partial time series data segments and another of the plurality of extracted partial time series data segments is smaller than a distance between the one of the plurality of partial time series data segments before extraction and the another of the plurality of partial time series data segments before extraction.

[0008] According to a third aspect of the present application, a display method of a physical quantity related to a state of a machine device includes displaying an image such that a distance between one of a plurality of extracted partial time series data segments extracted from time series data of the physical quantity and another of the plurality of extracted partial time series data segments is smaller than a distance between the one of the plurality of partial time series data segments before extraction and the another of the plurality of partial time series data segments before extraction.

[0009] According to a fourth aspect of the present application, a display apparatus for a physical quantity related to a state of a machine device includes a processing portion. The processing portion is configured to display an image such that a distance between one of a plurality of extracted partial time series data segments extracted from time series data of the physical quantity and another of the plurality of extracted partial time series data segments is smaller than a distance between the one of the plurality of partial time series data segments before extraction and the another of the plurality of partial time series data segments before extraction.

[0010] Further features of the present application will become apparent from the following description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a schematic functional block diagram for showing functional blocks of a time series data display device of an embodiment.

[0012] Figure 2 is a diagram schematically showing one example of a hardware configuration of a time series data display device of an embodiment.

[0013] Figure 3 is a flowchart for showing a control method of an embodiment.

[0014] Figure 4A is a diagram showing one example of time series data collected by a time series data display device.

[0015] Figure 4B is a diagram showing one example of event data collected by a time series data display device.

[0016] Figure 5 is a diagram showing an example of time series data of one of repetitive operations collected from a machine device.

[0017] Figure 6A is a diagram showing an example of time series data collected while a repetitive operation is continuously performed.

[0018] Figure 6B is a diagram showing time series data collected over a long period of time and displayed compressed in a time axis direction.

[0019] Figure 7 is an example in which extracted multiple partial time series data segments are located on and displayed on a linear scale in which time is expressed as an index (i.e., an absolute time axis).

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

[0021] Figure 9A One example of a display image of an embodiment obtained in a case where an event is a stop caused by a failure is shown.

[0022] Figure 9B One example of information on stored events is shown.

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

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

[0025] Figure 12is a diagram showing an example in which a time series data display device embodying an embodiment is connected to a six-axis articulated robot. DETAILED DESCRIPTION

[0026] Generally, measurements are performed on a machine device to acquire various parameters (physical quantities) to manage the operation state of the machine device. Thus, a large amount of time series data is acquired. In order to create a learning model suitable for predicting a failure of the machine device, it is necessary to appropriately extract a plurality of data segments from the large amount of data that has been acquired, and to perform detailed analysis work (such as inspection and comparison of waveforms) to determine whether the extracted data is suitable for learning data.

[0027] However, since a machine device such as an industrial robot installed in a production line generally has a low frequency of failure, it is necessary to collect time series data for a long period of time. Since the time series data to be collected is data for managing the operation state of the machine device, there are many measurement parameters of the data, and the sampling rate is set high to analyze waveforms in detail. As a result, the amount of data collected becomes enormous. Thus, in such a case where data segments related to a failure and occurring irregularly are to be extracted from data collected at a high sampling rate for a long period of time to perform comparison and the like, the conventional data display method places a high burden on the worker, thereby reducing the efficiency and accuracy of work.

[0028] In the simplest method, time series data is displayed on a single graph having a horizontal axis representing measurement time. However, in this case, since a plurality of partial data segments related to a failure will be irregularly scattered on a long time axis, the plurality of partial data segments related to a failure can not necessarily be displayed on the screen. If the time series data is compressed in the time axis direction to display a plurality of partial data segments on the screen, even if the time series data is measured at a high sampling rate, the waveforms displayed in the graph will be distorted and lose characteristics. As a result, it becomes difficult to inspect and compare waveforms. Furthermore, in order to analyze waveforms in detail, the operator must perform operations such as partial enlargement of waveforms by himself or herself. As a result, a large amount of time is spent to perform data analysis work.

[0029] In the technology described in Japanese Patent Application Publication No. 2013-8234, a plurality of partial time series data segments to be added to a comparative graph are selected and extracted from a large amount of time series data that has been acquired. The extracted plurality of partial time series data segments are then provided with elapsed time, and displayed on the comparative graph so that one is displayed on top of the other, and the extracted plurality of time series data segments are in phase with each other on an elapsed time axis. Since the plurality of partial time series data segments are located on the comparative graph so as to be in phase with each other on the elapsed time axis, a worker can compare the plurality of partial time series data segments with each other. However, the operation of the worker is troublesome.

[0030] For this reason, an information processing method and an information processing apparatus that realize simplification of operations required when extracting a plurality of partial data segments from time series data collected at a high sampling rate over a long period of time, and when performing data analysis work such as inspection and comparison of waveforms have been desired.

[0031] Next, an information processing method and an information processing apparatus of an embodiment of the present application will be described with reference to the accompanying drawings.

[0032] Note that, in the accompanying drawings referred to in the following embodiments, components given the same reference numeral have the same function unless otherwise indicated.

[0033] Figure 1 is a schematic diagram for showing a configuration of functional blocks of the information processing apparatus of the embodiment. Note that, in Figure 1 , the functional blocks represent functional elements necessary to describe features of the embodiment. Therefore, other functional blocks that are generally used and not directly related to the problem-solving principle of the present application are not shown. Furthermore, since the functional elements of Figure 1 are conceptually shown so that the function of the elements can be understood, the elements can not necessarily be physically connected to each other as shown in Figure 1 . For example, the specific configuration of the functional blocks being dispersed or unified is not limited to the example shown in the drawing, and a part or all of the functional blocks can be functionally or physically dispersed or unified in a predetermined unit according to the usage state or the like.

[0034] As shown in Figure 1 , a time series data display apparatus 100 that serves as the information processing apparatus of the embodiment is communicably connected with a machine apparatus 10 to be measured.

[0035] The machine device 10 is one of various industrial devices such as an industrial robot and a production device deployed in a production line. The machine device 10 has various sensors 11 deployed for measuring physical quantities related to the state of the machine device 10. For example, if the machine device 10 is a multi-joint robot, the machine device 10 can have, for example, a sensor for measuring the current value of a motor driving a joint, a sensor for measuring the angle of a joint, and a sensor for measuring speed, vibration, and sound. Note that since the above-described sensors are merely examples, an appropriate type and an appropriate number of sensors can be deployed at appropriate locations as the sensors 11 depending on the type of the machine device 10 and the use of the machine device 10. Examples of the sensors 11 can include a force sensor, a torque sensor, a vibration sensor, a sound sensor, an image 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. Note that although the sensors 11 are shown as being provided on the machine device 10, the sensors 11 can be provided on a device other than the machine device 10. For example, the sensors 11 can be provided on a device such as a sensor device or a sensor network device that is connected to the machine device 10 via a wired or wireless network. Figure 1 A single sensor 11 is shown, but a plurality of sensors are typically deployed so as to be able to communicate with the time series data display device 100.

[0036] The machine device 10 is connected to the time series data display device 100 wirelessly or via an electric wire, so that the machine device 10 can communicate with the time series data display device 100 serving as an information processing device. Thus, the time series data display device 100 can acquire data measured by the sensors 11 through communication. Hereinafter, functional blocks of the time series data display device 100 will be described in an order. The time series data display device 100 includes a control portion 110, a storage portion 120, a display portion 130, and an input portion 140.

[0037] The control portion 110 includes a plurality of functional blocks, which are realized by a CPU of the time series data display device 100 reading and executing a control program stored in, for example, a storage device or a non-transitory recording medium. In another case, part or all of the functional blocks can be realized by a hardware component such as an ASIC included in the time series data display device 100.

[0038] The storage portion 120 includes a time series data storage portion 121, an event data storage portion 122, an extracted data storage portion 123, and a join data storage portion 124. These portions of the storage portion 120 are appropriately allocated to storage areas of a storage device such as a hard disk drive, a RAM, or a ROM. The storage portion 120 is a data storage portion that stores various types of data necessary for creating an image that allows a user to easily view time series data.

[0039] The display section 130 and the input section 140 are a user interface of the time series data display device 100. The display section 130 can include a display device such as a liquid crystal display or an organic electroluminescence display. The input section 140 can include an input device such as a keyboard, a slow dial, a mouse, a pointing device, or a voice input device.

[0040] 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 can be referred to as a data acquisition section.

[0041] The data collection section 111 collects time series data and stores the time series data in the time series data storage section 121. The time series data represents a physical quantity related to a state of the machine device and measured by the sensor 11 of the machine device 10, such as a current, a speed, a pressure, a vibration, a sound, and a temperature of each section. In another case, the data collection section 111 can acquire a measured value from the sensor 11, calculate a value (such as a maximum value, a minimum value, an average value, an integrated value, a value obtained by performing integration in a frequency domain, a differential value, or a second differential value) from the measured value in a predetermined each time period, and store the resulting value in the time series data storage section 121.

[0042] Further, the data collection section 111 collects event data related to an event that has occurred in the machine device and stores the event data in the event data storage section 122. An event is set when the machine device has a predetermined state. For example, the data collection section 111 collects information on a time at which an event occurs 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 the machine device that normally performs a repetitive operation (a cycle operation), the data collection section 111 stores a date and a time at which the stop state occurs in the event data storage section 122. Events of the machine device that cause the stop state, such as a failure or maintenance, are generally irregular and occur at long intervals. Therefore, the information processing device of the embodiment is suitable for handling such events that occur discretely in time and irregularly.

[0043] The data extraction section 112 extracts, from the time series data stored in the time series data storage section 121, a partial time series data piece related to the event depending on the event data stored in the event data storage section 122; and stores the partial time series data piece in the extracted data storage section 123.

[0044] For example, if the extraction condition is stoppage of the machine device, the data extraction section 112 reads data on the date and time of the stoppage of the machine device as event data from the event data storage section 122. Depending on the event data, the data extraction section 112 extracts measurement values collected by the sensor in the operation period before the period of the stoppage of the machine device; and stores the measurement values as partial time series data in the extracted data storage section 123. In another case, the data extraction section 112 extracts a value, such as a maximum value, a minimum value, an average value, an integrated value, a value obtained by performing integration in a frequency domain, a differential value, or a second differential value, calculated from the measurement values obtained in a predetermined time of the operation period before the period of the stoppage of the machine device from the time series data storage section 121. The data extraction section 112 then stores the value as partial time series data in the extracted data storage section 123.

[0045] Note that, although the description has been made for the case where the processing is performed on the event data stored in the event data storage section 122 and corresponding to a single type of event, there can be a case where the event data storage section 122 stores event data related to a plurality of types of events. In this case, the operator can select one type of event from the plurality of types of events via the input section 140; and the data extraction section 112 extracts partial time series data pieces related to the selected type of event, and stores the extracted partial time series data pieces in the extracted data storage section 123. In another case, one type of event selected from the plurality of types of events can be registered in advance. In this case, partial time series data pieces related to the registered type of event can be automatically extracted, and stored in the extracted data storage section 123.

[0046] The data combination section 113 uses the plurality of partial time series data pieces stored in the extracted data storage section 123, and creates a graph in which the plurality of partial time series data pieces related to one type of event are aligned with each other. The data combination section 113 can be referred to as a graph forming section. For example, the data combination section 113 creates a graph in which the plurality of partial time series data pieces related to one type of event are combined with each other or disposed close to each other on a horizontal axis representing the number of data pieces or the like; and stores the combined data in the combined data storage section 124. The graph can be displayed on the display section 130 or printed by using a printing device (not shown), if a worker (operator) needs to do so.

[0047] Figure 2 One example of a hardware configuration of a time series data display device of the embodiment is schematically shown. As Figure 2The time-series data display device includes PC hardware including a CPU 1601 serving as a main control portion, and a ROM 1602 and a RAM 1603 serving as storage devices, as shown in FIG. 16. The ROM 1602 stores information (such as a processing program) that implements the information processing method described later. The RAM 1603 serves as a work area of the CPU 1601, for example, when the CPU 1601 executes the information processing method. Further, the PC hardware is connected with an external storage device 1606. The external storage device 1606 can be an HDD, an SSD, or another externally installed system.

[0048] The processing program of the CPU 1601 that implements the information processing device and the information processing method of the embodiment is stored in the external storage device 1606, which can be an HDD or an SSD, or a storage portion (such as an EEPROM area) of the ROM 1602. In this case, the processing program of the CPU 1601 that implements the information processing method (for example, the time-series data display method) can be supplied to the above-mentioned storage device or storage portion via the network interface 1607, and can be updated with a new program. In another case, the processing program of the CPU 1601 that implements the information processing method can be supplied to the above-mentioned storage device or storage portion via one of various storage media (such as a magnetic disk, an optical disk, a flash memory) and a drive device thereof; and can be updated. The storage medium, the storage portion, or the storage device that stores the processing program of the CPU 1601 that implements the information processing method is a computer-readable recording medium for the information processing method or the information processing device of the present application.

[0049] The CPU 1601 is connected with the sensor 11 that acquires the time-series data of the industrial robot, as shown in FIG. 16. The sensor 11 is connected with the CPU 1601 via the network interface 1607 and the network 1608, as shown in FIG. 16. Figure 1 In the embodiment, for simplicity of explanation, the sensor 11 is directly connected to the CPU 1601. However, the sensor 11 can be connected to the CPU 1601 via IEEE 488 (so-called GPIB), for example. In another case, the sensor 11 can be communicably connected to the CPU 1601 via the network interface 1607 and the network 1608. Figure 2 In the embodiment, for simplicity of explanation, the sensor 11 is directly connected to the CPU 1601. However, the sensor 11 can be connected to the CPU 1601 via IEEE 488 (so-called GPIB), for example. In another case, the sensor 11 can be communicably connected to the CPU 1601 via the network interface 1607 and the network 1608.

[0050] The network interface 1607 can conform to a wired communication standard such as IEEE 802.3, or a wireless communication standard such as IEEE 802.11 or IEEE 802.15. The CPU 1601 communicates with the external devices 1104 and 1121 via the network interface 1607. For example, in the case of displaying the time-series data from the industrial robot, the external devices 1104 and 1121 can be a general control device and a management server (such as a PLC and a sequencer) that are deployed for control and management of the industrial robot.

[0051] In Figure 2 the example shown in Figure 1 , an operation section 1604 corresponding to the input section 140 of the machine device 10 and a display device 1605 corresponding to the display section 130 are connected to the CPU 1601 as a user interface device (UI device). The operation section 1604 can be a terminal such as a hand-held terminal, or a device such as a keyboard, a jog dial, a mouse, a pointing device, or a voice input device (the operation section 1604 can be a control terminal including the above-mentioned devices). The display device 1605 can be any device as long as the device can display information related to the processing performed by the data extraction section 112, the data combination section 113, and the like on its display screen. For example, the display device 1605 can be a liquid crystal display device.

[0052] Next, with reference to the flowchart of Figure 3 , the information processing method (time series data display method) performed by the time series data display device 100 will be described. Figure 3 One example of the procedure of the processing performed by the time series data display device 100 is shown.

[0053] In step S101, the time series data display device 100 collects time series data and event data from the machine device 10.

[0054] Figure 4A One example of the time series data collected by the time series data display device 100 is shown. The example is a series of data pieces measured by periodically sampling the driving 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 a plurality of pieces of time series data from the sensor 11 of the machine device 10, and stores the data in the time series data storage section 121.

[0055] Hereinafter, the time series data collected by the data collection section 111 will be described more specifically. Figure 5 A graph showing a current waveform obtained from the time series data in one cycle of normal operation of an industrial robot included in the machine device 10 is shown. Figure 6A A graph showing a current waveform obtained from the time series data collected while the industrial robot continuously performs a cycle operation is shown. In Figure 6A , the graph contains a waveform SPW whose amplitude is different from those of the other waveforms. Figure 6B is a graph showing time series data collected over a long period of time and displayed more compressed in the time axis direction than the time series data shown in Figure 6A . In Figure 6BAs 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.

[0056] Figure 4B An example of event data collected by the time-series data display device 100 is shown. The event is defined as the stopping of an industrial robot within the machine unit 10, and the event data is recorded as the time the event occurs. In this example, the event is the stopping of the robot caused by maintenance work performed periodically or irregularly, or by a robot malfunction occurring irregularly. 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.

[0057] 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.

[0058] For example, data extraction section 112 from Figure 4A Time series data extraction and from Figure 4B The 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.

[0059] 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 7The display screen W is schematically shown. In the drawing, since most of the time series data in the continuous operation is not extracted, the unextracted plurality of time series data segments are not plotted, and only the waveforms of the partial time series data related to one type of event are shown. Therefore, compared with the drawing of Figure 6B However, if the time series data is collected over a long period of time, on the display screen W, the waveforms of the plurality of partial time series data segments will be compressed and distorted in the time axis direction. Therefore, the details of the waveforms cannot be checked. If the waveforms are expanded in the time axis direction in order to easily observe the waveforms and compare the waveforms of the plurality of partial time series data segments, the waveforms can exceed the screen. This is because the waveforms of the plurality of partial time series data segments are separated from each other and positioned at irregular intervals.

[0060] Therefore, in the embodiment, in step S103, the data combining section 113 combines the plurality of partial time series data segments stored in the extracted data storage section 123, and stores the combined data in the combined data storage section 124. That is, compared with the case where the extracted plurality of partial time series data segments are arranged on a linear scale in which time is represented as an index, the data combining section 113 creates an image (combined data) in which the extracted plurality of partial time series data segments (e.g., the drawing) are arranged closer to each other. Specifically, the data combining section 113 arranges the plurality of partial time series data segments (e.g., the drawing) so 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 disposed adjacent to another partial time series data segment with a short interval inserted therebetween. For example, the data combining section 113 performs image processing so 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 value of zero or a predetermined small value. In this way, the data combining section 113 makes the distance between the waveforms short.

[0061] In step S104, the time series data display device 100 displays the graph on the display section 130 by using the combined data stored in the combined data storage section 124. If necessary, the graph can be expanded in the horizontal axis direction to facilitate observation and comparison of the waveforms. Preferably, the index (scale) of the horizontal axis of the graph is not absolute time, but the number of samples of the raw measurement data, the number of operation cycles, or the like. As described above, the plurality of partial time series data segments originally separated from each other and positioned at irregular intervals are disposed adjacent to each other. Therefore, if the index (scale) of the horizontal axis in the graph is absolute time, the value of the index will discontinuously jump at the boundary between one partial time series data segment and another partial time series data segment, making it difficult for the worker to intuitively and easily understand the graph.

[0062] Note that, in step S104, the time series data display device 100 can not display the created image on the display section 130. Instead, the time series data display device 100 can transmit the image to another display device other than the time series data display device 100 and cause the other display device to display the image, or can transmit the image to a printing device and cause the printing device to print the image. That is, the time series data display device 100 can select a method of outputting the created image in accordance with the convenience of the worker (operator).

[0063] Figure 8 The image displayed on the display screen W of the display section 130 in step S104 is shown as an example. In the example, the waveforms of the partial time series data segments are displayed in the same manner as in the example shown in FIG. 6. In the example, the waveforms of the partial time series data segments are displayed in the same manner as in the example shown in FIG. 6. Figure 8 In the example, one partial time series data segment related to one type of event is combined with another partial time series data segment in the horizontal axis direction so as to be adjacent to each other. That is, the event data corresponds to the stop of the industrial robot; the partial time series data segment is extracted for each event from the time series data obtained by monitoring the current value of the industrial robot; and the plurality of partial time series data segments are combined with each other in the graph. Therefore, the graph shows only the plurality of partial time series data segments related to the occurrence of the event and combined with each other. Therefore, the worker (operator) can easily perform inspection and comparison of the waveforms (graph) related to the occurrence of the event.

[0064] For example, if the event (stop) is caused by an inspection performed on the normal state machine device, the waveform of the partial time series data segment becomes similar to the waveform of the normal state machine device, Figure 5 the waveform of the normal state machine device. Therefore, in the example, the waveforms of the partial time series data segments are displayed in the same manner as in the example shown in FIG. 6. Figure 5 Figure 8 ​In the display image of the embodiment shown in FIG. 9, the worker (operator) can easily check the similarity of the waveforms. If the event (stop) is caused by a failure of the machine device, the waveforms of the partial time series data pieces become abnormal waveforms, like Figure 8 ABN1 or ABN2 shown in FIG. 8. Thus, such abnormal waveforms not similar to the normal waveforms can be easily found and compared with other waveforms related to the event. Thus, the worker (operator) can easily extract learning data for creating a failure prediction model.

[0065] Figure 8 The example of FIG. 9 involves the extraction condition (predetermined event) in step S102 including both the stop caused by the check of the normal state machine device and the stop caused by the failure of the machine device. However, the worker can change the extraction condition (predetermined event) of step S102 according to the purpose of the work. For example, if the worker desires to perform comparison only on the waveforms related to the stop caused by the failure and study the correlation between the failure cause and the waveforms, the worker can set the stop caused by the failure as the event used as the extraction condition of step S102.

[0066] As an example, Figure 9A A display image obtained by setting the stop caused by the failure as the event is shown. In the image, one waveform of one partial time series data piece related to the event is combined with another waveform of another partial time series data piece in the horizontal axis direction so as to be adjacent to each other. In this example, the index of the horizontal axis is the number of operation cycles, and the graph is provided with a vertical line at the position where one waveform is combined with another waveform, so that the boundary between the events can be easily recognized. Figure 9B Detailed information related to the event stored in the event data storage section 122 is shown. In Figure 9A In FIG. 10, regarding Figure 9BThe detailed information of the event shown in the middle is shown in association with the corresponding waveforms of the plurality of partial time series data segments. Thus, the worker (operator) can easily understand from the waveforms and the detailed information about the event displayed on the screen that, when the machine device fails and stops due to an excessive motor load, the maximum value of the peak of the waveform abnormally increases as a sign of the failure. In addition, the worker (operator) can easily understand that, when the machine device fails and stops due to a brake failure, the number of peaks observed in one operation cycle increases as a sign of the failure. Thus, the worker (operator) can easily understand the characteristics of each partial time series data segment extracted by using the corresponding event by checking the events for extracting the partial time series data in detail. Therefore, the worker (operator) can easily determine whether the partial time series data segment can be used as learning data for machine learning. Thus, the worker (operator) can efficiently and easily extract learning data for creating a failure prediction model.

[0067] In addition, in order to increase the work efficiency of the worker (operator), an input area in which the worker (operator) can input information can be deployed in the image in addition to the combined waveforms of the plurality of partial time series data segments and the detailed information related to the event. For example, a check box, a drop-down menu, a flag, or the like can be displayed in the image for the work of the worker (operator) to extract the waveforms as learning data. In another case, a box can be deployed in the image for the worker (operator) to write a comment or a memo.

[0068] Figure 10 Another example of a display image of an embodiment is shown. In this example, one partial time series data segment (graph) is deployed adjacent to another partial time series data segment (graph) with a predetermined short interval inserted therebetween for the worker (operator) to visually easily recognize the boundary between one partial time series data segment and another partial time series data segment. In addition, each graph is provided with a mark indicating information about an event as a label. In this example, the mark indicates a subcategory of a stop (event) of the machine device. Specifically, each mark indicates a stop of the machine device in a normal state (for example, a stop caused by an inspection) or a stop of the machine device in an abnormal state (for example, a stop caused by a failure). The mark is displayed in the image as a label in association with the corresponding graph. Above each label, a check box is displayed for determining whether to use the corresponding waveform as learning data for creating a failure prediction model. The label and the check box can be displayed by the worker (operator) instructing the time series data display device 100 via the input section 140, or can be automatically displayed by the control program.

[0069] 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.

[0070] Figure 11 Another example of a display image of an embodiment is shown. In this example, in Figure 3 In 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 current 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.

[0071] Example of a connection between a time-series data display device and a robot

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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).

[0078] 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.

[0079] For example, embodiments of the present application are not limited to a graph of a physical quantity related to a single type of event. For example, in Figure 3 In step S102 of the flowchart of FIG. 10, a plurality of types of events can be set as extraction conditions. Then, in step S103, for each of the plurality of types of events, a plurality of partial time series data pieces of the physical quantity can be extracted, and a graph in which the plurality of partial time series data pieces are combined with each other along a horizontal axis can be formed. In step S104, the graphs can be displayed adjacent to each other in a single screen. The graphs are convenient for an operator to study a correlation between different types of events for the physical quantity.

[0080] Further, although it has been described in the present embodiment for a case in which the machine device 10 is a six-axis articulated robot as one example, the present disclosure is not limited thereto. For example, the machine device 10 can be a machine device that can automatically perform extension and contraction, bending and stretching, up and down movement, left and right movement, pivoting, or a combined movement thereof, in accordance with information stored in a storage device of a control apparatus.

[0081] Other Embodiments

[0082] Embodiments of the present application can also be realized by a computer of a system or device that reads out and executes computer executable instructions (e.g., one or more programs) recorded on storage media (which can also be referred to more fully as a 'non-transitory computer-readable storage medium') to perform the functions of one or more of the above-described embodiments and / or that includes one or more circuits (e.g., application specific integrated circuits (ASICs)) for performing the functions of one or more of the above-described embodiments and by a method performed by the computer of the system or device by, for example, reading out and executing the computer executable instructions from the storage media to perform the functions of one or more of the above-described embodiments and / or controlling the one or more circuits to perform the functions of one or more of the above-described embodiments. The computer can comprise one or more processors (e.g., central processing units (CPUs), micro processing units (MPUs)) and can include a network of the separate computers or separate processors to read out and execute the computer executable instructions. The computer executable instructions can be provided to the computer, for example, from a network or the storage media. The storage media can include, for example, one or more of a hard disk, a random access memory (RAM), a read only memory (ROM), a storage of distributed computing systems, an optical disk (such as a compact disc (CD), digital versatile disc (DVD), or Blu-ray Disc (BD)®), a flash memory device, a memory card, and the like. TM

[0083] ​Embodiments of the present application can also be implemented by a method of providing software (program) for executing the functions of the above-described embodiments to a system or an apparatus through a network or various storage media, and a method of reading and executing the program by a computer or a central processing unit (CPU) of the system or the apparatus.

[0084] While the present application has been described with reference to example embodiments, it is to be understood that the application 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 the modifications and equivalent structures and functions.

Claims

1. An information processing method, comprising: acquiring, by an information processing apparatus, a plurality of time series data of a physical quantity related to a state of a machine apparatus that performs a repetitive operation; extracting, by the information processing apparatus, a plurality of partial time series data segments corresponding to events that have occurred in the machine apparatus during the repetitive operation from the plurality of time series data; and displaying, by the information processing apparatus, an image in which the plurality of partial time series data segments are arranged closer to each other than in a case where the plurality of partial time series data segments are arranged on a linear scale that represents time as an index. The plurality of partial time series data segments are extracted in dependence on event data related to the events that have occurred in the machine apparatus.

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

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

4. The information processing method according to claim 1, wherein The image contains a graph that represents the physical quantity, is combined with each other, and is related to the plurality of partial time series data segments.

5. The information processing method according to claim 1, wherein The image contains a graph that represents the physical quantity, is arranged at a predetermined distance apart from each other, and is related to the plurality of partial time series data segments.

6. The information processing method according to claim 1, wherein The image contains information about the events.

7. The information processing method according to Claim 2, wherein The information processing apparatus 8. The information processing method according to claim 1, wherein 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. The information processing apparatus 9. The information processing method according to claim 2, wherein acquires event data related to a plurality of types of events that have occurred in the machine apparatus, extracts a 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 is arranged for each of the at least two types of events. The image contains an input area in which an operator inputs information.

10. The information processing method according to claim 1, wherein The event is set in dependence on a peak of the physical quantity.

11. The information processing method according to claim 2, wherein The event is set when a value of the peak becomes equal to or greater than a predetermined threshold value and / or when a number of the peak becomes equal to or greater than a predetermined number.

12. The information processing method according to claim 11, wherein The event data is data about a date and time at which the event occurred.

13. The information processing method according to claim 2, wherein The input area allows a label to be set, and the label indicates a category of partial time series data.

14. The information processing method according to claim 10, wherein 15.A computer-readable non-transitory recording medium storing a program that causes a computer to execute the information processing method according to any one of claims 1 to 14. 16.An information processing apparatus comprising a processing section including an acquisition section, an extraction section, and a display section, the acquisition section is configured to acquire a plurality of time series data of a physical quantity related to a state of a machine apparatus that performs a repetitive operation, wherein, ​ wherein the extracting section is configured to extract, from the plurality of time series data, a plurality of partial time series data segments corresponding to events that have occurred in the machine device during the repetitive operation, and wherein the displaying section is configured to display an image in which the plurality of partial time series data segments are combined with each other so as to be arranged closer to each other than in a case where the plurality of partial time series data segments are arranged on a linear scale in which time is represented as an index.

17. A method of manufacturing a product, comprising: acquiring, by the information processing device according to claim 16, the plurality of time series data when the machine device performs an operation for manufacturing a product; and displaying, by the information processing device according to claim 16, the image.

18. A method of acquiring learning data, comprising: creating, by the information processing device according to claim 16, the image; and displaying, by the information processing device according to claim 16, the image for an operator to acquire learning data for creating a learning model that predicts a failure of the machine device.

19. A display method of displaying a physical quantity related to a state of a machine device that continuously performs a repetitive operation, the method comprising: displaying an image obtained by combining a plurality of partial time series data segments with each other so as to be arranged closer to each other than in a case where the plurality of partial time series data segments are arranged on a linear scale in which time is represented as an index, the plurality of partial time series data segments being extracted from a plurality of time series data of the physical quantity and corresponding to events that have occurred in the machine device during the repetitive operation.

20. A display device for displaying a physical quantity related to a state of a machine device that continuously performs a repetitive operation, the display device comprising a processing section configured to display an image obtained by combining a plurality of partial time series data segments with each other so as to be arranged closer to each other than in a case where the plurality of partial time series data segments are arranged on a linear scale in which time is represented as an index, the plurality of partial time series data segments being extracted from a plurality of time series data of the physical quantity and corresponding to events that have occurred in the machine device during the repetitive operation.

Images