Waveform measuring device and method

Abstract

To facilitate shortening of the whole processing time for AI analysis using waveform data while acquiring data indicating a feature quantity.SOLUTION: A waveform measuring device 11 comprises a control section 110 that sets at least one channel of a plurality of channels to a trigger channel, sequentially compares each sample value included in digital signal data written into an area corresponding to the trigger channel with a threshold in a storage, reads at least one sample value included in the digital signal data written during a certain period including a detection time point of a trigger point in the area corresponding to each channel of the plurality of channels in the storage each time one sample value is detected as the trigger point, performs processing for extracting a feature quantity of the read sample value, and outputs data indicating the extracted feature quantity.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present disclosure relates to waveform measurement instruments and methods. [Background technology]

[0002] Non-Patent Document 1 describes a technique for improving the efficiency of setting thresholds used in trend monitoring for detecting equipment failures in advance. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Masahiko Sato, "Application of Machine Learning Technology to Trend Monitoring with Sushi Sensor", Yokogawa Technical Report, Vol. 63, No. 1 (2020), pp. 23-26 Summary of the Invention [Problem to be solved by the invention]

[0004] In trend monitoring, a waveform measuring instrument with a trigger function is used. The trigger function is a function that detects a characteristic signal of digital signal data as a trigger to start a predetermined process executed on the digital signal data. Detecting a characteristic signal of digital signal data is also called trigger detection. Measurement using a waveform measuring instrument with a trigger function is also called trigger measurement. Trigger measurement is effective for monitoring the behavior of a processing machine during processing in a machining production line. For example, when measuring signals from various sensors installed on a processing machine to observe the behavior of the processing machine, if a characteristic signal during processing is used as a trigger, the behavior of the processing machine can be captured into the waveform measuring instrument for each processing. By using the trigger function, it is possible to capture data using the same point as a reference in a series of operations of the trend monitoring target. A waveform measuring instrument with a trigger function transmits the digital signal data captured in response to trigger detection to an external device such as a local PC or a server each time the digital signal data is captured. "PC" is an abbreviation for personal computer. On the external device side, AI analysis is performed using the received digital signal data, for example, for the purpose of predicting failures of the processing machine. "AI" is an abbreviation of artificial intelligence. Here, the digital signal data sent from the waveform measuring instrument is time sampling data. In order to improve the sampling accuracy, it is necessary to make the sampling period faster, and the amount of data increases. Therefore, if the raw digital signal data captured by the waveform measuring instrument, that is, the "raw data", is directly passed to an external device, the amount of data communication will be enormous. Also, if the external device directly analyzes the received raw data, the analysis time will be long due to the large number of sample values. Therefore, it is considered that the feature amount of the sample value of a specific part of the raw data is extracted and AI analysis is performed on the feature amount. A "feature amount" is a representative value that characterizes the sample value contained in the raw data, for example, the average value of the sample value of a specific part of the raw data. In this case, if the feature amount is extracted from the raw data on the external device side, the data processing load and processing time will increase. As a result, the overall processing time for AI analysis using waveform data will be longer.

[0005] An object of the present disclosure is to make it easier to shorten the overall processing time for AI analysis using waveform data while obtaining data indicating feature amounts. [Means for solving the problem]

[0006] A waveform measuring device according to some embodiments is a waveform measuring device that converts the waveform of an analog signal input from a plurality of channels into digital signal data and writes the digital signal data of each channel into a corresponding area in a storage device, and includes a control unit that sets at least one of the plurality of channels as a trigger channel, sequentially compares each sample value included in the digital signal data written into the area in the storage device corresponding to the trigger channel with a threshold value, and each time a sample value is detected as a trigger point, reads at least one sample value included in the digital signal data written during a certain period including the time point at which the trigger point was detected in the area in the storage device corresponding to each of the plurality of channels, executes a process of extracting a feature value of the read sample value, and outputs data indicating the extracted feature value. In such a waveform measuring device, each time a trigger point is detected, a process of extracting a feature value of at least one sample value included in the digital signal data written during the certain period is executed, and the execution result is output as data indicating the feature value. In other words, the waveform measuring device can execute a process of acquiring data indicating the feature value from a specific part of the raw data. By transmitting data indicating the acquired feature quantities from the waveform measuring device to the terminal device, the terminal device can immediately use the machine learning data used for AI analysis. Therefore, compared to the case where raw data is transmitted directly to the external device, the amount of data communication between the waveform measuring device and the external device and the data processing load on the external device are reduced. Therefore, it becomes easier to shorten the overall processing time for AI analysis using waveform data while acquiring data indicating feature quantities.

[0007] In a waveform measuring instrument according to an embodiment, the control unit executes data import and feature extraction in parallel. For example, when data import is performed for a press machine to monitor the trend of the behavior of press processing by the press machine, if data import and feature extraction are not executed in parallel, data import will not be executed while the feature extraction is being executed. In this case, it is not realistic to prioritize data import, set a time for data import during press processing, and interrupt press processing until data import is completed. Therefore, data import will be interrupted instead of press processing. In that case, data import will be discontinuous, and data loss may occur. On the other hand, according to such an embodiment, data import can be performed even during feature extraction, so that no dead time between data imports will occur and the continuity of data import is guaranteed.

[0008] In one embodiment of the waveform measuring instrument, the control unit further executes a process of extracting features of sample values ​​read from areas corresponding to two or more of the multiple channels, converting the two or more features obtained by executing the process into one feature, and includes data indicating the one feature in the output data. According to this embodiment, it is possible to combine the results of the process of extracting features of the multiple channels to obtain data indicating another feature.

[0009] A method according to some embodiments includes the steps of: when performing data capture by converting the waveform of an analog signal input from a plurality of channels into digital signal data and writing the digital signal data of each channel into a corresponding area in a storage, setting at least one of the plurality of channels as a trigger channel; sequentially comparing each sample value included in the digital signal data written into the area in the storage corresponding to the trigger channel with a threshold value; reading at least one sample value included in the digital signal data written during a certain period including the time point of detection of the trigger point in the area in the storage corresponding to each of the plurality of channels; executing a process to extract a feature value of the read sample value; and outputting data indicating the extracted feature value. According to this method, each time a trigger point is detected, a process to extract a feature value of at least one sample value included in the digital signal data written during the certain period is executed, and the execution result is output as data indicating the feature value. In other words, data indicating the feature value can be obtained from a specific portion of raw data to extract data for machine learning used in AI analysis.

[0010] The method according to an embodiment further includes performing data import and a process of extracting a feature in parallel. For example, when data import is performed for a press machine to monitor the trend of the behavior of the press machine during press processing, if the data import and the process of extracting a feature are not performed in parallel, the data import is not performed while the process of extracting a feature is being performed. In this case, it is not realistic to prioritize data import, set a time for data import during press processing, and interrupt press processing until the data import is completed. Therefore, data import is interrupted instead of press processing. In that case, data import becomes discontinuous, and data loss may occur. On the other hand, according to such an embodiment, data import can be performed even during feature extraction, so that no dead time occurs between data imports, and the continuity of data import is guaranteed.

[0011] In one embodiment, the method further includes converting two or more feature quantities obtained by performing a process of extracting feature quantities of sample values ​​read from areas corresponding to two or more of the multiple channels into one feature quantity, and including data indicating the one feature quantity in the output data. According to such an embodiment, it is possible to combine the results of the process of extracting feature quantities of the multiple channels to obtain data indicating another feature quantity. Effect of the Invention

[0012] According to the present disclosure, it becomes easier to shorten the overall processing time for AI analysis using waveform data while acquiring data indicating feature amounts. [Brief description of the drawings]

[0013] [Figure 1] FIG. 11 is a diagram showing a data flow of a system according to a comparative example. [Diagram 2] FIG. 11 is a block diagram showing a detailed configuration of a waveform measuring instrument according to a comparative example. [Diagram 3] FIG. 13 illustrates data writing and reading in a ring buffer when a trigger is detected. [Figure 4] FIG. 2 is a diagram showing a data flow of the system according to the present embodiment. [Diagram 5] 1 is a block diagram showing a configuration of a system according to an embodiment of the present invention. [Figure 6] FIG. 2 is a block diagram showing a detailed configuration of a waveform measuring instrument according to the present embodiment. [Figure 7] 4 is a flowchart showing the operation of the system according to the present embodiment. [Figure 8] FIG. 13 is a diagram showing an example of a waveform generated by plotting sample values ​​acquired by trigger measurement. [Figure 9] FIG. 1 shows regions corresponding to each channel when data is acquired through four channels. [Figure 10] 11A and 11B are diagrams illustrating a specific example of data reading and feature extraction. [Figure 11] FIG. 2 is a diagram showing a time series of data import, data readout, and feature extraction. [Figure 12] 13A and 13B are diagrams illustrating data import, data readout, and feature extraction according to one modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] First, a comparative example will be described.

[0015] 1 shows the configuration of a system 20 according to a comparative example. System 20 includes a waveform measurement instrument 21 having a trigger function, and a local PC 22 connected to waveform measurement instrument 21 via a network such as the Internet.

[0016] The waveform measuring instrument 21 converts the waveform of an analog signal into digital signal data and transmits it to the local PC 22. The local PC 22 accumulates the digital signal data and acquires data for machine learning from the accumulated data. The local PC 22 generates a model used for AI analysis for trend monitoring from the acquired data for machine learning.

[0017] The configuration of waveform measuring device 21 will be described with reference to FIG.

[0018] In the waveform measuring instrument 21, as shown in FIG. 2, the analog signal of the analog input channel CH1 to be observed is normalized by the input amplifier 201 and input to the A / D converter 202. "A / D" is an abbreviation of analog to digital. The analog signal of the analog input channel CH2, which is observed simultaneously with the analog input channel CH1, is normalized by the input amplifier 204 and input to the A / D converter 205. The timing of taking in the data is controlled by the sample timing generating circuit 211. The A / D converters 202 and 205 perform A / D conversion according to the timing signal generated by the sample timing generating circuit 211. The converted data is sent to the memory controller 212 via the interface circuits 203 and 206, and is stored sequentially in the waveform memory 221. The data stored in the waveform memory 221 is converted into waveform display data by the display waveform creating circuit 231, and is displayed as a waveform on the waveform display unit 232. When a certain amount of data is accumulated in the waveform memory 221, it is transmitted to the local PC 22 via the network, read out by the local PC 22 as appropriate, converted into waveform or numerical data, and displayed and observed on the local PC 22.

[0019] FIG. 3 shows data writing and data reading in the waveform memory 221 when trigger detection is performed while the converted data is stored sequentially in the waveform memory 221. In the example shown in FIG. 3, the waveform memory 221 is controlled as a ring buffer by the memory controller 212. Data loading in the ring buffer starts from address A of the waveform memory 221, and when data loading reaches address B, it loops back to address A and data is overwritten. The trigger detection circuit 213 executes trigger detection. Specifically, the trigger detection circuit 213 judges whether the sample value of the digital signal data of the corresponding channel satisfies a preset trigger condition. The trigger detection circuit 213 detects a trigger point according to the judgment result, and notifies the memory controller 212 of the detected trigger point. The memory controller 212 stores the address where the sample value is written at the time when the trigger detection circuit 213 notifies the memory controller 212 of the trigger point as a trigger point address nT. After detecting the trigger point, the memory controller 212 finishes data loading after loading a preset number of sample values, that is, when data writing of the final address nE is completed. The first address for reading data is set to address n0, which is a preset number of addresses back from the trigger point address nT. The display waveform creation circuit 231 reads data from the waveform memory 221 in the order of n0→nT→B→A→nE, creates a display waveform, and displays it on the waveform display 232.

[0020] In such a system 20, the waveform measuring instrument 21 converts the waveform data captured in response to trigger detection into digital signal data and transmits it to the local PC 22 each time the data is captured. As described above, if the raw data is directly passed from the waveform measuring instrument 21 to the local PC 22, the amount of data communication will be enormous. Furthermore, if feature extraction is performed on the raw data on the local PC 22 side, the data processing load and processing time will be excessive. As a result, the overall processing time for AI analysis using the waveform data will be long.

[0021] Therefore, it is necessary to make it easier to shorten the overall processing time for AI analysis using waveform data while obtaining data indicating features.

[0022] Hereinafter, several embodiments of the present disclosure will be described with reference to the drawings. In each drawing, the same or corresponding parts are denoted by the same reference numerals. In the description of each embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0023] A first embodiment, which is an embodiment of the present disclosure, will be described.

[0024] The configuration of a system 10 according to this embodiment will be described with reference to FIG.

[0025] As shown in FIG. 5, the system 10 includes a waveform measurement instrument 11 and a terminal device 12.

[0026] Waveform measuring instrument 11 is a device that converts the waveform of an input analog signal into digital signal data. As shown in Fig. 5, waveform measuring instrument 11 includes an input unit 100, a control unit 110, a storage unit 120, a display unit 130, and a communication unit 140. Waveform measuring instrument 11 can communicate with terminal device 12 via a network 15 such as the Internet.

[0027] The terminal device 12 is a desktop computer or a laptop computer that is installed at the site and displays the waveform. As shown in FIG. 5, the terminal device 12 includes an input unit 150, a control unit 160, a storage unit 170, a display unit 180, and a communication unit 190.

[0028] Some or all of the functions of waveform measurement instrument 11 are realized by a programmable circuit or a dedicated circuit included in control unit 110. In other words, some or all of the functions of waveform measurement instrument 11 are realized by hardware.

[0029] When some of the functions of waveform measuring instrument 11 are realized by hardware, the remaining functions of waveform measuring instrument 11 may be realized by executing a program according to this embodiment in a processor included in control unit 110. That is, the remaining functions of waveform measuring instrument 11 may be realized by software. In this case, the program is a program for making a computer execute processing of a step included in the operation of waveform measuring instrument 11, thereby making the computer realize a function corresponding to the processing of the step. That is, the program is a program for making the computer function as waveform measuring instrument 11.

[0030] The program may be recorded on a computer-readable recording medium. Examples of the computer-readable recording medium include a magnetic recording device, an optical disc, a magneto-optical recording medium, or a semiconductor memory. The program may be distributed, for example, by selling, transferring, or lending a portable recording medium such as a DVD or CD-ROM on which the program is recorded. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read only memory. The program may be distributed by storing the program in the storage of a server and transferring the program from the server to another computer via the network 15. The program may be provided as a program product.

[0031] A computer temporarily stores in memory, for example, a program recorded on a portable recording medium or a program transferred from a server. Then, the computer reads the program stored in the memory with a processor and executes processing according to the read program with the processor. The computer may read the program directly from the portable recording medium and execute processing according to the program. The computer may execute processing according to the received program each time a program is transferred from the server to the computer. Processing may be executed by a so-called ASP-type service that realizes functions only by execution instructions and result acquisition without transferring a program from the server to the computer. Programs include information used for processing by a computer and equivalent to a program. For example, data that is not a direct instruction to a computer but has the property of defining computer processing falls under "substance equivalent to a program."

[0032] The present embodiment will be outlined with reference to FIG. 4 and FIG.

[0033] The waveform measuring instrument 11 is a waveform measuring instrument that converts the waveform of an analog signal input from a plurality of channels into digital signal data, and writes the digital signal data of each channel into a corresponding area in a storage device to capture data. The waveform measuring instrument 11 sets at least one of the plurality of channels as a trigger channel. The "trigger channel" is a channel that detects a sample value that serves as a trigger for starting the execution of a process for extracting a feature amount. The waveform measuring instrument 11 sequentially compares each sample value included in the digital signal data written into an area in the storage device corresponding to the trigger channel with a threshold value, and detects one sample value as a trigger point TP. The "trigger point TP" is a sample value that serves as a trigger for starting the execution of a process for extracting a feature amount. Each time the waveform measuring instrument 11 detects a trigger point TP, the waveform measuring instrument 11 reads out at least one sample value included in the digital signal data written into an area in the storage device corresponding to each channel during a certain period including the time point at which the trigger point was detected, and executes a process for extracting a feature amount of the read sample value. The waveform measuring instrument 11 outputs data indicating the extracted feature amount. In this embodiment, the storage device is managed as a ring buffer. Data capture is performed by overwriting data in a ring shape in the section from the first address to the last address of the area corresponding to the trigger channel in the storage until the trigger point TP is detected. Therefore, when the number of sample values ​​included in the digital signal data is L, L is not a fixed value but an indefinite value until the trigger point TP is detected. For example, depending on the time until the trigger point TP is detected, the ring-shaped data overwriting process in the section may be repeated several hundred times. In other words, the number of sample values ​​L varies depending on the measurement conditions at each time. On the other hand, the number of addresses in the area where the sample values ​​are written is a fixed value. This fixed value is larger than the number of sample values ​​for which the process of extracting the feature is performed, that is, the number of sample values ​​to be observed in the trigger measurement. Trigger detection is started at the same time as data capture and is performed in real time for all sample values ​​included in the captured digital signal data. The waveform measuring instrument 11 outputs data indicating the extracted feature to the terminal device 12.

[0034] According to this embodiment, as shown in FIG. 4, the waveform measuring device 11 can execute a process of acquiring data indicating a feature amount from a specific part of raw data and extracting data for machine learning used in AI analysis. That is, the waveform measuring device 11 can execute a process of extracting a feature amount and transfer the acquired data indicating the feature amount to the terminal device 12. The terminal device 12 only needs to accumulate the transferred data indicating the feature amount and generate a model to be used in AI analysis for trend monitoring from the accumulated data. Therefore, the amount of data communication between the waveform measuring device 11 and the terminal device 12 and the data processing load on the terminal device 12 side are reduced compared to the case where raw data is sent directly to the terminal device 12. Therefore, it is easy to shorten the overall processing time for AI analysis using waveform data while acquiring data indicating a feature amount.

[0035] Next, the configuration of the system 10 according to the first embodiment will be described in detail with reference to FIGS.

[0036] As described above, the system 10 includes the waveform measurement instrument 11 and the terminal device 12.

[0037] As described above, waveform measurement instrument 11 includes input section 100, control section 110, storage section 120, display section 130, and communication section 140.

[0038] Input section 100 is an interface that inputs data of each channel into waveform measuring instrument 11. As shown in FIG 6, input section 100 includes input amplifiers 101-1, 101-2, . . ., A / D converters 102-1, 102-2, . . ., and interface circuits 103-1, 103-2, . . .

[0039] As shown in Fig. 6, the analog signal of channel CH1 to be observed is normalized by input amplifier 101-1 and input to A / D converter 102-1. Here, normalization means adjusting the amplitude of the analog input signal so that it falls within an appropriate range for the input specifications of the A / D converter. In addition, analog signals of channels CH2, CH3, and CH4 that are simultaneously observed are each normalized by input amplifiers 101-2, ..., and input to A / D converters 102-2, .... As shown in Fig. 6, when there are multiple channels, input amplifiers, A / D converters, and interface circuits are provided for the number of channels.

[0040] The control unit 110 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or a GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The programmable circuit is, for example, an FPGA (field-programmable gate array). The dedicated circuit is, for example, an ASIC (application specific integrated circuit). The control unit 110 executes processes related to the operation of the waveform measurement device 11 while controlling each part of the waveform measurement device 11. As shown in FIG. 6, the control unit 110 includes a sample timing generation circuit 111, a memory controller 112, a trigger detection circuit 113, a memory controller 114, a calculator 115, a data number counting circuit 116, and a process indicator 117. The sample timing generation circuit 111 controls the timing of data capture. A / D conversion is performed in the A / D converters 102 and 105 of the input unit 100 according to a timing signal generated by the sample timing generation circuit 111. The memory controller 112 receives the data converted by the A / D converters 102 and 105 through the interface circuits 103 and 106 of the input unit 100. The trigger detection circuit 113 executes trigger detection, which will be described later. The memory controller 114 receives a notification indicating the end of data capture after trigger detection from the memory controller 112, and sequentially reads data from a corresponding address of a waveform memory 121 of the storage unit 120, which will be described later. The data number counting circuit 116 counts the number of sample values ​​sequentially read from the waveform memory 121 with a counter. The sample values ​​sequentially read from the waveform memory 121 are input to the calculator 115. The calculator 115 executes processing to extract features from the input data. The processing indicator 117 controls the type of processing to be executed by the calculator 115 for the sample values ​​input to the calculator 115, as well as the start and stop of the processing, according to the number of sample values ​​indicated by the count value of the counter of the data number counting circuit 116.

[0041] The storage unit 120 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, a random access memory (RAM). The RAM is, for example, a static random access memory (SRAM) or a dynamic random access memory (DRAM). The storage unit 120 may be an electrically erasable programmable read only memory (EEPROM). As shown in FIG. 6, the storage unit 120 includes a waveform memory 121 and a calculation result memory 122.

[0042] Digital signal data acquired in each sampling interval is written into the waveform memory 121 by the memory controller 112 of the control unit 110 in response to a timing signal generated by the sample timing generating circuit 111. The waveform memory 121 is controlled by the memory controller 112 as a ring buffer as described above with reference to FIG.

[0043] The calculation result memory 122 stores the results of the processing executed by the calculator 115 of the control unit 110.

[0044] As shown in FIG. 6, the display unit 130 includes a display waveform generating circuit 131 and a waveform display unit 132.

[0045] The display waveform creation circuit 131 is a general-purpose processor such as a GPU, a dedicated processor specialized for waveform display processing, a programmable circuit such as an FPGA, or a dedicated circuit such as an ASIC. The display waveform creation circuit 131 converts the digital signal data stored in the waveform memory 121 into waveform display data as required by an instruction from the calculator 115. The display waveform creation circuit 131 displays the waveform display data as a waveform on the waveform display unit 132 as required.

[0046] The waveform display 132 includes at least one output interface. The output interface is, for example, an LCD (liquid crystal display) or an organic EL (electro luminescent) display. The waveform display 132 outputs data obtained by the operation of the waveform measurement instrument 11. The waveform display 132 may be provided integrally with a touch panel capable of receiving input from a user. The waveform display 132 displays waveform display data under the control of the display waveform creation circuit 131.

[0047] The communication unit 140 includes a communication circuit. The communication circuit is one or more communication ICs. "IC" is an abbreviation for integrated circuit. The communication IC is, for example, a LAN communication IC. "LAN" is an abbreviation for local area network. The communication unit 140 may be a PCI network adapter, a USB network adapter, or an Ethernet (registered trademark) adapter. "PCI" is an abbreviation for Peripheral Component Interconnect. "USB" is an abbreviation for Universal Serial Bus. The communication unit 140 receives information used in the operation of the waveform measuring instrument 11 via the network 15, and transmits information obtained by the operation of the waveform measuring instrument 11 via the network 15.

[0048] As described above, the terminal device 12 includes the input unit 150, the control unit 160, the storage unit 170, the display unit 180, and the communication unit 190.

[0049] The input unit 150 includes at least one input interface. The input interface is, for example, a physical key, a capacitive key, a pointing device, a touch screen, or a microphone. The input unit 150 accepts an operation for inputting data used in the operation of the terminal device 12. The input unit 150 may be connected to the terminal device 12 as an external input device instead of being provided in the terminal device 12.

[0050] The control unit 160 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or a GPU, or a dedicated processor specialized for a specific process. The programmable circuit is, for example, an FPGA. The dedicated circuit is, for example, an ASIC. The control unit 160 executes processes related to the operation of the terminal device 12 while controlling each part of the terminal device 12.

[0051] The storage unit 170 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, a RAM. The RAM is, for example, an SRAM or a DRAM. The storage unit 170 may be an EEPROM.

[0052] The display unit 180 includes at least one output interface. The output interface is, for example, an LCD or an organic EL display. The display unit 180 outputs data obtained by the operation of the terminal device 12. The display unit 180 may be provided integrally with a touch panel capable of receiving input from a user. The display unit 180 displays waveform display data under the control of the control unit 160.

[0053] The communication unit 190 is one or more communication ICs. The communication IC is, for example, a LAN communication IC. The communication unit 190 may be a PCI network adapter, a USB network adapter, or an Ethernet (registered trademark) adapter. The communication unit 190 receives information used in the operation of the terminal device 12 via the network 15, and transmits information obtained by the operation of the terminal device 12 via the network 15.

[0054] Next, the operation of the system 10 according to this embodiment will be described with reference to Figures 7 to 11. Figure 7 shows the operation of the system 10. The operation of Figure 7 corresponds to the method according to this embodiment.

[0055] In step S101, the control unit 110 of the waveform measuring instrument 11 sets at least one of the multiple channels as a trigger channel. Specifically, the control unit 110 converts the waveforms of analog signals input from the multiple channels into digital signal data. When performing data capture to write the digital signal data of each channel into a corresponding area in the storage, the control unit 110 sets at least one of the multiple channels as a trigger channel. In this embodiment, the storage is the memory unit 120 of the waveform measuring instrument 11, specifically the waveform memory 121 of the memory unit 120, but it may be an external storage device of the waveform measuring instrument 11. In that case, the waveform measuring instrument 11 may upload the digital signal data to the external storage device via the network 15. In the example shown in FIG. 8, in order to monitor the trend of the behavior of a press machine, which is a processing machine, trigger measurement is performed using four channels, channel CH1 to channel CH4. Channel CH1 receives the AC voltage for driving the press machine, channel CH2 receives the displacement of the press machine obtained from the displacement sensor, channel CH3 receives the vibration displacement of the press machine obtained from the vibration sensor, and channel CH4 receives an analog signal indicating the hydraulic pressure change of the press machine obtained from the pressure sensor. The four waveforms shown in Figure 8 are plots of sample values ​​contained in the digital signal data of each channel, with the horizontal axis representing time and the vertical axis representing signal strength. Of these four channels, one channel, CH2, is set as the trigger channel.

[0056] Next, the control unit 110 sequentially compares each sample value included in the digital signal data written in the area in the storage corresponding to the trigger channel with a threshold value, and whenever one sample value is detected as a trigger point, reads at least one sample value included in the digital signal data written in the area in the storage corresponding to each of the multiple channels during a certain period including the detection time of the trigger point. Specifically, the control unit 110 executes the following processes from steps S102 to S105.

[0057] In step S102, the control unit 110 executes trigger point detection for the trigger channel set in step S101. The trigger point detection is executed during data capture in which digital signal data including a plurality of sample values ​​for the trigger channel is written in a ring shape in an area having a predetermined number of addresses corresponding to the trigger channel in the memory unit 120 corresponding to the storage. The predetermined number is an integer of 2 or more, and is set in advance as the number of addresses capable of storing sample values ​​for each channel including the trigger channel in the memory unit 120. The control unit 110 executes trigger point detection by comparing each sample value of the plurality of sample values ​​with a threshold value and detecting one sample value from the plurality of sample values ​​as a trigger point TP. Specifically, the trigger detection circuit 113 of the control unit 110 determines whether the sample value of the digital signal data of the trigger channel satisfies a preset trigger condition. The trigger condition is that a sample value exceeding or falling below a preset threshold value is detected from the sample values ​​included in the digital signal data acquired for the trigger channel. In the example shown in FIG. 8, the trigger detection circuit 113 executes trigger detection during data capture in which digital signal data including a plurality of sample values ​​indicating the displacement amount of the press machine for the channel CH2 is sequentially written into an area in the storage unit 120 corresponding to the channel CH2. The trigger detection circuit 113 compares each sample value with a threshold value of the displacement amount of the press machine. If one sample value exceeding the threshold value is detected as a result of the comparison, the trigger detection circuit 113 detects the detected sample value as a trigger point TP. For example, by setting the threshold value to a value near the maximum value of the displacement amount of the press machine in a press operation, it is possible to record the change in the signal associated with each series of press operations. The trigger detection circuit 113 notifies the memory controller 112 of the detected trigger point TP. In this way, the control unit 110 sequentially compares each sample value included in the digital signal data written into an area in the storage corresponding to the trigger channel with the threshold value to detect one sample value as the trigger point.

[0058] In step S103, the control unit 110 sets the address where the sample value was written at the time when the trigger point TP was detected in step S102 as the trigger point address nT in the area corresponding to each of the multiple channels. Specifically, the trigger detection circuit 113 of the control unit 110 notifies the memory controller 112 of the trigger point TP. When the trigger point TP is notified, the memory controller 112 stores the address where the sample value was written at the time when the trigger point TP was detected as the trigger point address nT for the trigger channel.

[0059] In step S104, the control unit 110 specifies, as a target address, an address in an area corresponding to each channel, including the trigger point address nT set in step S103, to which K sample values ​​have been written, where K is an integer equal to or greater than 1 and less than the predetermined number. In the example shown in FIG. 8, the control unit 110 sets, in an area corresponding to each channel, from channel CH1 to channel CH4, an address one or more addresses before the corresponding trigger point address nT, as a leading address n0 to which the first sample value of the K sample values ​​has been written. The leading address n0 is defined as an address going back from the trigger point address nT by a number that is preset for each channel. Hereinafter, the sample value written to the address before the trigger point address nT is also referred to as pre-trigger data. The final address nE of the readout is defined as the number of sample values ​​from the leading address n0, which is preset for each channel. Hereinafter, the number of sample values ​​is also referred to as the number of data points. When data acquisition after trigger detection is completed, the memory controller 112 of the control unit 110 notifies the memory controller 114 of the start address n0 and the end address nE of the readout together with data indicating the end of the data acquisition. The number of sample values ​​sequentially read out from the waveform memory 121 is counted by the data number counter circuit 116. For example, for channel CH1, it is assumed that the trigger point address nT is set to address "n1T". It is also assumed that the start address n0 is set to address "n1T-500" that is 500 back from address "n1T". It is assumed that the number of sample values ​​represented by K is set to 1000. In this case, the control unit 110 sets the 1000th address "n1T+500" counting from address "n1T-500" as the end address nE of the readout. The addresses from the start address n0 to the end address nE of the readout of each channel correspond to the target addresses in this embodiment.

[0060] In this way, the control unit 110 sets, in the area corresponding to each channel, an address that is at least one address before the corresponding trigger point address as the starting address at which the first sample value of the K sample values ​​is written, and sets the Kth address counting from the set starting address as the final address for reading, thereby identifying the address at which the K sample values ​​are written as the target address.

[0061] In step S105, the control unit 110 sequentially reads out K sample values ​​from the identified target addresses in the areas corresponding to each channel. Specifically, the memory controller 112 of the control unit 110 notifies the memory controller 114 that data acquisition after trigger detection has ended. At the same time, the memory controller 112 notifies the memory controller 114 of the start address n0 and the end address nE of data writing. In response to this, the memory controller 114 specifies a target address from the start address n0 and the end address nE in the areas corresponding to each channel in the waveform memory 121 of the storage unit 120, and sequentially reads out sample values ​​from the target addresses of each channel.

[0062] FIG. 9 shows the areas in the storage unit 120 corresponding to each channel when data is captured on four channels, channel CH1 to channel CH4. The sample values ​​of each channel are stored in the areas in the storage unit 120 corresponding to each channel. In the example shown in FIG. 9, in the first to fourth areas corresponding to channels CH1 to CH4, A1, A2, A3, and A4 correspond to the start addresses of the ring buffer, and B1, B2, B3, and B4 correspond to the end addresses of the ring buffer. n1T, n2T, n3T, and n4T are set as trigger point addresses corresponding to each area. The data capture of each channel is synchronized with the same sampling period. Therefore, the start addresses (n10, n20, n30, and n40) and the end addresses (n1E, n2E, n3E, and n4E) of reading in each channel are relatively at the same position, and the number of sample values ​​stored in the target address is also equal. In addition, FIG. 3 above shows how data is overwritten in a ring shape over more than two round trips on consecutive addresses arranged in one dimension from the start address A to the end address B of the ring buffer. In contrast, FIG. 9 shows the addresses of each channel as consecutive addresses arranged in two dimensions. For example, in CH1, there are m+1 addresses from the start address A1 to the end address B1 of the ring buffer. The m+1 addresses correspond to the above-mentioned predetermined number of addresses. The same applies to CH2 to CH4.

[0063] In step S106, the control unit 110 executes a process of extracting features from J sample values ​​among K sample values ​​sequentially read out in an area corresponding to each channel, where J is an integer between 1 and K. The control unit 110 acquires the execution result as data indicating the features. As a result, a process of acquiring data indicating the features from a specific portion of the raw data and extracting data for machine learning to be used in AI analysis is executed on the waveform measuring instrument 11 side. Specifically, the control unit 110 identifies J sample values ​​read out from addresses in a range indicated by a set value among K sample values ​​sequentially read out in an area corresponding to each channel. The "set value" is a pair of values ​​indicating the first address and the last address of J sample values, and is set in advance for each channel depending on the process to be executed. J may be set to the same number or different numbers between channels. In the example shown in FIG. 8, p11 and p12 are set as set values ​​for the channel CH1. The control unit 110 identifies the sample values ​​read out from the address range from p11 to p12 in the area corresponding to the channel CH1. Similarly, p21, p22, p23, and p24 are set as the set values ​​of channel CH2, p31 and p32 are set as the set values ​​of channel CH3, and p41 and p42 are set as the set values ​​of channel CH4. The control unit 110, like channel CH1, specifies sample values ​​read from addresses in the ranges indicated by the respective set values ​​in the areas corresponding to the channels CH2 to CH4. Then, the control unit 110 executes a process to extract a feature amount for the specified J sample values. The process to extract a feature amount may be one type of process or two or more types of processes for each channel. In the example shown in FIG. 8, in channel CH1, a process to obtain a root mean square (RMS) is executed for sample values ​​read from the address range (dashed line) from p11 to p12. This allows the feature amount of the driving AC voltage of the press machine to be acquired. In channel CH2, a process to obtain a slope is executed for sample values ​​read sequentially from the address range (dashed line) from p21 to p22.In addition, in the channel CH2, a process of obtaining a maximum value and a minimum value is also performed for the sample values ​​sequentially read from the address range of p23 to p24 (dashed line). This allows the feature of the displacement amount of the press machine to be acquired. In the channel CH3, a process of obtaining an average value is performed for the sample values ​​sequentially read from the address range of p31 to p32 (dashed line). This allows the feature of the vibration displacement of the press machine to be acquired. In the channel CH4, a process of obtaining a maximum value is performed for the sample values ​​sequentially read from the address range of p41 to p42 (dashed line). This allows the feature of the hydraulic pressure change amount of the press machine to be acquired. In addition, the control unit 110 may perform a process of converting two or more feature amounts obtained by performing a process of extracting feature amounts of sample values ​​read from areas corresponding to two or more channels among the multiple channels into one feature amount, and may include data indicating one feature amount in the data to be output. For example, the control unit 110 performs a process of obtaining a slope of the displacement amount of the press machine in the channel CH2. The control unit 110 obtains a feature of the work efficiency of the press machine from a combination of the obtained slope of the displacement amount and the maximum value indicating the feature of the hydraulic pressure change amount obtained by the channel CH4 (for example, maximum pressure value / slope of the displacement amount).The control unit 110 can then include the obtained data indicating the feature of the work efficiency of the press machine in the data to be output.

[0064] FIG. 10 shows a specific example of performing different processing for each channel on J sample values ​​out of 1000 sample values ​​sequentially read out in the areas corresponding to each channel from channel CH1 to channel CH4 in the storage unit 120 shown in FIG. 9. The 1000 sample values ​​correspond to K sample values ​​in this embodiment. In the example shown in FIG. 10, data reading is performed by reading addresses of each area one by one while circulating through the areas corresponding to each channel from channel CH1 to channel CH4. That is, data reading is performed in the order of n10→n20→n30→n40→n11→···→n41→n12→···n42→···. 1000 sample values ​​are read out for each channel, and 4000 sample values ​​are read out in total for the four channels from n10 to n4E. The data number counting circuit 116 of the control unit 110 increments the count value of the counter by 1 every time a sample value of channel CH1 is read out. In the example shown in FIG. 10, the count value pE is 1000. As shown in FIG. 10, the timing of executing the process of extracting the feature may overlap between channels. In this embodiment, the timing of executing two different processes in one channel CH2 is set not to overlap, but the timing of executing the process of extracting one or more feature may overlap in the same channel. For example, the timing of executing the process of obtaining the slope in channel CH2 and the timing of executing the process of obtaining the maximum and minimum values ​​may overlap. Also, in channel CH2, the same process of extracting the feature, for example, the process of obtaining the slope, may be executed for sample values ​​sequentially read from each address range of p21 to p22 and p23 to p24, and the execution timing of each process may overlap.

[0065] As described above, the control unit 110 specifies J sample values ​​read from the range of addresses indicated by the preset setting value for each channel. The setting value for channel CH1 is a pair of values ​​p11 and p12. For example, p11 indicates the first address counting from the start address "n10" of CH1, and p12 indicates the 1000th address counting from "n10". In this case, the address corresponding to p11 is "n10", and the address corresponding to p12 is "n1E". Therefore, the control unit 110 specifies 1000 sample values ​​read from the address range from "n10" to "n1E". Next, the setting value for channel CH2 is a pair of values ​​p21 and p22, and a pair of values ​​p23 and p24. For example, p21 indicates the 451st address counting from the start address "n20" of CH2, and p22 indicates the 550th address counting from "n20". In this case, the control unit 110 identifies 100 sample values ​​read from the address range from the address corresponding to "p21" to the address corresponding to "p22". For example, p23 indicates the 601st address counting from the start address "n20" of CH2, and p24 indicates the 800th address counting from "n20". In this case, the control unit 110 identifies 200 sample values ​​read from the address range from the address corresponding to p23 to the address corresponding to p24. Next, the set value for channel CH3 is a pair of values ​​p31 and p32. For example, p31 indicates the first address counting from the start address "n30" of CH3, and p32 indicates the 1000th address counting from "n30". In this case, the control unit 110 identifies 1000 sample values ​​read from the address range from "n30" to "n3E". Finally, the set value for channel CH4 is a pair of values ​​p41 and p42. For example, p41 indicates the 651st address counting from the first address "n40" of CH4, and p42 indicates the 850th address counting from "n40." In this case, the control unit 110 identifies 200 sample values ​​read from the address range from the address corresponding to p41 to the address corresponding to p42.After identifying the J sample values ​​in each channel, the process indicator 117 of the control unit 110 judges whether the count value of the data number counter circuit 116 is equal to the set value for each channel. If the result of the judgment is that a channel whose count value is equal to the set value is identified, the process indicator 117 instructs the calculator 115 on the type of process to extract features to be executed on the J sample values ​​identified for that channel, as well as the start and end timings of the process. The calculator 115 executes the process to extract features according to the instruction from the process indicator 117, and obtains the execution result.

[0066] In this way, each time the control unit 110 detects one sample value as a trigger point, it reads at least one sample value contained in the digital signal data written during a certain period including the time point at which the trigger point was detected in an area in the storage corresponding to each of the multiple channels, and executes a process of extracting features of the read sample value.

[0067] In this embodiment, the control unit 110 executes data acquisition and feature extraction in parallel. FIG. 11 shows an example in which data acquisition by the above-mentioned trigger measurement is repeatedly performed, and feature extraction is performed on sample values ​​of digital signal data acquired in each trigger measurement. FIG. 11 shows data acquisition, data readout, and feature extraction in chronological order from the left to right of the page. As shown in FIG. 11, for the first data acquisition, data readout and feature extraction are started for sample values ​​written to target addresses n0 to nE identified through trigger point detection. The second data acquisition and trigger point detection are started without waiting for the completion of the first data readout and feature extraction. The same applies to the third and subsequent data acquisitions and trigger point detections. Thus, in this embodiment, data acquisition and feature extraction are executed in parallel. In this embodiment, data acquisition into the waveform memory 121 and data readout from the waveform memory 121 can be executed simultaneously in parallel by pipeline processing by the memory controller 112 and the memory controller 114. That is, data capture, data readout, and feature extraction can be performed simultaneously in real time. In this case, there is no need to secure a calculation time for feature extraction between one data capture and the next data capture. Therefore, even when trigger measurements are performed repeatedly, data capture can be easily continued without generating dead time due to feature extraction. The processing speed of the calculator 115 may be the same as the sampling period, and does not need to be faster than the sampling period. This is because pipeline processing is possible if the calculator 115 can process the captured data at the same processing speed as the sampling period.

[0068] In step S107, the control unit 110 outputs data indicating the feature quantities extracted in step S106. Specifically, the communication unit 140 of the waveform measuring instrument 11 transmits data indicating the feature quantities of the K sample values ​​acquired to the terminal device 12 via the network 15. In the example shown in FIG. 8, the communication unit 140 transmits the feature quantities acquired for each channel from the channel CH1 to the channel CH4 to the terminal device 12 as data indicating the feature quantities of the K sample values. The communication unit 190 of the terminal device 12 receives the data indicating the feature quantities of the K sample values ​​transmitted from the waveform measuring instrument 11 via the network 15. The control unit 160 of the terminal device 12 accumulates the data indicating the feature quantities of the K sample values ​​received by the communication unit 190 in the storage unit 170. The control unit 160 of the terminal device 12 reads out the data indicating the feature quantities of the K sample values ​​accumulated in the storage unit 170, and performs AI analysis for the purpose of, for example, predicting failures of a processing machine. In this embodiment, the communication unit 140 transmits data indicating the feature quantities of the K sample values ​​to the terminal device 12, but may transmit the K sample values ​​read for each channel together with the data indicating the feature quantities to the terminal device 12. In this case, the terminal device 12 displays a waveform as shown in Fig. 8, which is obtained by plotting the K sample values ​​for each channel, on the display unit 180. In the example shown in Fig. 8, the left end of each displayed waveform corresponds to the plot point of the sample value stored at the start address n0 for the corresponding channel, and the right end corresponds to the plot point of the sample value stored at the end address nE for the corresponding channel.

[0069] According to this embodiment, the waveform measuring instrument 11 can execute a process of acquiring data indicating feature amounts from a specific portion of raw data and extracting data for machine learning to be used in AI analysis. The extraction of feature amounts is realized by hardware and can be processed at the same high speed as data acquisition, so no dead time occurs between data acquisitions. Therefore, the amount of data communication between the waveform measuring instrument 11 and the terminal device 12 and the data processing load on the terminal device 12 side are reduced compared to the case where raw data is sent directly to the terminal device 12. Therefore, it becomes easier to shorten the overall processing time for AI analysis using waveform data while acquiring data indicating feature amounts.

[0070] However, the present disclosure is not limited to the above-mentioned embodiment. For example, multiple blocks shown in the block diagram may be integrated, or one block may be divided. Instead of executing multiple steps shown in the flowchart in chronological order according to the description, each step may be executed in parallel or in a different order according to the processing capacity of the device executing each step, or as necessary. Other modifications are possible within the scope of the present disclosure.

[0071] For example, the above embodiment is based on the premise that pre-trigger data is also acquired, but if pre-trigger data is not acquired, data reading and feature extraction may be started simultaneously with the start of data acquisition. In that case, since no dead time occurs between data acquisitions, the processing by the memory controller 112 and the memory controller 114 does not necessarily have to be pipeline processing. FIG. 12 shows the operation of the system 10 when pre-trigger data is not acquired as a modification of this embodiment. As shown in FIG. 12, data reading and feature extraction are started simultaneously with the start of data acquisition. That is, the processing by the memory controller 112 and the memory controller 114 is sequential processing instead of pipeline processing. In this case, as in the above method, the number of data points from the start of data acquisition is preset, and feature values ​​can be extracted from a specific portion of raw data.

[0072] In the above embodiment, the sampling period is the same for each channel as shown in Fig. 8, but the sampling period may be different for each channel. In that case, by reading from the waveform memory 121 in accordance with the sampling period of each channel and adjusting the calculation rate of the calculator 115 to the sampling period of each channel, processing can be performed even if the sampling periods are different between channels. [Explanation of symbols]

[0073] 10. System 11 Waveform measuring instrument 12 Terminal Equipment 15 Network 20 Systems 21 Waveform measuring instrument 22 Local PC 100 Input section 101-1, 101-2 Input amplifier 102-1, 102-2 A / D converter 103-1, 103-2 Interface circuit 110 Control section 111 Sample timing generation circuit 112 Memory Controller 113 Trigger detection circuit 114 Memory Controller 115 Arithmetic unit 116 Data Counting Circuit 117 Processing indicator 120 Storage section 121 Waveform Memory 122 Calculation result memory 130 Display section 131 Display waveform creation circuit 132 Waveform display 140 Communications Department 150 Input section 160 Control section 170 Storage section 180 Display section 190 Communications Department 201,204 Input amplifier 202,205 A / D converter 203,206 Interface circuit 211 Sample timing generation circuit 212 Memory Controller 221 Waveform Memory 231 Display Waveform Creation Circuit 232 Waveform display

Claims

1. 1. A waveform measuring device that converts the waveforms of analog signals input from a plurality of channels into digital signal data and writes the digital signal data of each channel into a corresponding area in a storage device, a control unit that sets at least one of the multiple channels as a trigger channel, sequentially compares each sample value included in digital signal data written in an area in the storage corresponding to the trigger channel with a threshold value, and each time a sample value is detected as a trigger point, reads out sample values ​​of one or more specific partial areas that are set in advance for each channel from among the sample values ​​of the digital signal data written in the area in the storage corresponding to each of the multiple channels during a certain period including the time point at which the trigger point was detected, executes a process of extracting feature values ​​of the read sample values ​​of the specific partial areas, and outputs data indicating the extracted feature values.

2. 2. The waveform measuring instrument according to claim 1, wherein the control unit executes the data acquisition and the process of extracting the feature amount in parallel.

3. 3. The waveform measuring instrument according to claim 1 or 2, wherein the control unit further executes a process of extracting features of sample values ​​read from areas corresponding to two or more of the multiple channels, converting the two or more feature quantities obtained by executing a process of extracting features of sample values ​​read from areas corresponding to two or more of the multiple channels into one feature quantity, and includes data indicating the one feature quantity in the data to be output.

4. A method carried out in a waveform measuring instrument, comprising: When performing data capture in which a waveform of an analog signal input from a plurality of channels is converted into digital signal data and the digital signal data of each channel is written to a corresponding area in a storage device, at least one of the plurality of channels is set as a trigger channel; a step of sequentially comparing each sample value included in the digital signal data written in an area in the storage corresponding to the trigger channel with a threshold value, and each time one sample value is detected as a trigger point, reading out sample values ​​of one or more specific partial areas preset for each channel from among the sample values ​​of the digital signal data written in the area in the storage corresponding to each of the multiple channels during a certain period including the time point at which the trigger point was detected; executing a process of extracting a feature amount of the read sample values ​​of the specific partial area; outputting data indicative of the extracted features; The method includes:

5. The method according to claim 4 , further comprising: performing the data acquisition and the feature extraction in parallel.

6. The method according to claim 4 or 5, further comprising: performing a process of extracting features of sample values ​​read from areas corresponding to two or more of the multiple channels, converting the two or more features obtained by performing a process of extracting features of sample values ​​read from areas corresponding to two or more of the multiple channels into a single feature, and including data indicating the single feature in the data to be output.

Images