Program, data selection device, data analysis system, and data selection method

Abstract

A data analysis device (10) comprising: an analysis information acquisition unit (14) that acquires analysis information indicating the method of data analysis and the purpose of data analysis designated by a user; a selection unit (15) that, on the basis of the analysis information, selects device data acquired from an FA device (20); and an output unit (16) that outputs the device data selected by the selection unit (15) from among the device data to a data analysis unit (17) that analyzes data.

Description

Program, data selection device, data analysis system, and data selection method

[0001] The present disclosure relates to a program, a data selection device, a data analysis system, and a data selection method.

[0002] There are known techniques for collecting and analyzing data from equipment installed at production sites. For example, Patent Literature 1 discloses a data processing device that collects and analyzes measurement data of vibrations generated from production equipment and determines whether the production equipment is operating normally.

[0003] International Publication No. 2022 / 044175

[0004] In the data processing device described in Patent Document 1, one type of data, namely vibration measurement data, is analyzed using one analysis method and for one analysis purpose.

[0005] On the other hand, data can be analyzed using various analytical methods and for various analytical purposes, so in order to analyze data in accordance with various analytical methods and analytical purposes, it is necessary to collect a large amount of various data from devices.

[0006] Consider analyzing a large amount of data based on a certain analytical method and purpose. Since much of the data is irrelevant to the analytical method and purpose, targeting all of the data for analysis can lead to problems such as a large processing load during analysis and poor analysis accuracy.

[0007] Therefore, it is necessary to select only necessary data before conducting an analysis. For example, it is conceivable that a user selects appropriate data depending on the analysis method and purpose of the analysis.

[0008] However, if a user is required to select appropriate data from a large amount of data according to the analysis method and purpose, the burden on the user becomes heavy.

[0009] In view of the above circumstances, an object of the present disclosure is to provide a program or the like that can reduce the burden on a user in selecting data according to an analysis method and an analysis purpose.

[0010] In order to achieve the above-mentioned object, the program disclosed herein causes a computer to function as: an analytical information acquisition means for acquiring analytical information indicating a data analysis method and a purpose of the data analysis designated by a user; a selection means for selecting equipment data acquired from an equipment based on the analytical information; and an output means for outputting the equipment data selected by the selection means from the equipment data to a data analysis means for analyzing the data.

[0011] According to the present disclosure, the burden on the user in selecting data according to the analysis method and purpose of analysis can be reduced.

[0012] FIG. 1 is a diagram showing a functional configuration of a data analysis device according to a first embodiment of the present disclosure. FIG. 2 is a diagram showing an example of a hardware configuration of a data analysis device according to a first embodiment of the present disclosure. FIG. 3 is a flowchart showing an example of a data analysis operation by a data analysis device according to a first embodiment of the present disclosure. FIG. 4 is a diagram showing a functional configuration of a data analysis device according to a second embodiment of the present disclosure. FIG. 5 is a diagram showing an example of an analysis target selection screen displayed by a data analysis device according to a second embodiment of the present disclosure. FIG. 6 is a diagram showing an overall configuration of a data analysis system according to a modified example of the present disclosure.

[0013] Hereinafter, an embodiment in which a data selection device according to the present disclosure is applied to a data analysis device will be described with reference to the drawings. In each drawing, the same or equivalent parts are denoted by the same reference numerals.

[0014] (First Embodiment) A data analysis device 10 according to a first embodiment will be described with reference to FIG. 1 . The data analysis device 10 is a data analysis device that collects equipment data from FA (Factory Automation) equipment 20, selects the collected equipment data, and then analyzes it. The data analysis device 10 is an example of a data selection device according to the present disclosure. The data analysis device 10 is also an example of a data analysis system according to the present disclosure.

[0015] The FA device 20 is an FA device installed at a production site. The FA device 20 is, for example, a sensor, a programmable logic controller (PLC), or the like, that can transmit device data to the data analysis device 10. For example, when the FA device is a sensor, the device data is data indicating a sensor value obtained by the sensor. Although one FA device 20 is shown in FIG. 1 , there may be multiple FA devices 20. The FA device 20 is an example of a device according to the present disclosure.

[0016] The data analysis device 10 collects equipment data from the FA devices 20. The data analysis device 10 also selects the collected equipment data based on an analysis method and an analysis purpose specified by the user, and analyzes the selected equipment data. The data analysis device 10 automatically selects equipment data based on the analysis method and analysis purpose specified by the user, thereby reducing the burden on the user in selecting data according to the analysis method and analysis purpose.

[0017] The data analysis device 10 includes a data collection unit 11 , a memory unit 12 , an input unit 13 , an analysis information acquisition unit 14 , a selection unit 15 , an output unit 16 , a data analysis unit 17 , and a display unit 18 .

[0018] The data collection unit 11 collects equipment data from the FA equipment 20 and stores the data in the storage unit 12 .

[0019] The storage unit 12 stores the device data collected by the data collection unit 11 .

[0020] The input unit 13 accepts input operations from the user. The input unit 13 includes input devices such as a keyboard, a mouse, and a touch screen. The input unit 13 is particularly used when the user specifies an analysis method and an analysis purpose for equipment data. When the user performs an operation to specify an analysis method and an analysis purpose, the input unit 13 outputs analysis information indicating the data analysis method and the purpose of the data analysis specified by the user to the analysis information acquisition unit 14 described below.

[0021] Examples of the data analysis method designated by the user include "data classification" and "multiple regression analysis." Examples of the data analysis purpose designated by the user include "three-level evaluation of quality indexes" and "calculation of quality index values." Note that "quality" here refers to, for example, the quality of a product produced by the FA device 20.

[0022] The analytical information acquisition unit 14 acquires the analytical information output by the input unit 13, and outputs it to the selection unit 15 and the data analysis unit 17, which will be described later. The analytical information acquisition unit 14 is an example of analytical information acquisition means according to the present disclosure.

[0023] The selection unit 15 selects equipment data to be analyzed by the data analysis unit 17, which will be described later, from the equipment data collected from the FA equipment 20 by the data collection unit 11 and stored in the storage unit 12, based on the analysis information output by the analysis information acquisition unit 14, that is, based on the analysis method and analysis purpose specified by the user. The selection unit 15 is an example of a selection means according to the present disclosure.

[0024] The device data to be analyzed is selected according to, for example, any one of the following rules (1) to (4).

[0025] (1) The trend of equipment data collected within a certain period is determined, and whether or not to include the data in the analysis is determined based on the trend. The trend of the equipment data refers to, for example, whether the measurement values ​​indicated by the equipment data are monotonically increasing or monotonically decreasing, whether the measurement values ​​are fluctuating, and the extent to which there are gaps in the measurement values. This makes it possible to exclude from the analysis data data that are unsuitable for analysis, such as constant values ​​such as device parameters, monotonically increasing data such as index numbers, and noise.

[0026] (2) When equipment data includes multiple types of data, the correlation between each type of data collected within a certain period of time is calculated. Data types whose correlation exceeds a threshold are determined to be interdependent, and only one of the types of data is analyzed. An example of equipment data including multiple types of data is when multiple sensors measure the current value of the same current path, and all of the current values ​​measured by these sensors are included in the equipment data. In this case, the correlation between these current values ​​is extremely high. In such a case, only one of the types of current value can be analyzed.

[0027] (3) When the equipment data includes data indicating whether the equipment is normal or abnormal and other data, data among the other data that does not fluctuate at the time of switching between normal and abnormal is excluded from the analysis. This is because data that does not change between normal and abnormal states is considered unnecessary data. Note that when the equipment data includes data indicating "good," "passable," or "unacceptable" for the equipment and other data, similarly to the above, data among the other data that does not fluctuate at the time of switching between "good," "passable," and "unacceptable" may be excluded from the analysis. Similarly, when the equipment data includes data indicating a staged state for the equipment and other data, data that does not fluctuate at the time of switching between the staged states may be excluded from the analysis.

[0028] (4) Apply a variable selection algorithm with low computational complexity to the equipment data and exclude data with low contribution from the analysis. An example of a variable selection algorithm with low computational complexity is Lasso regression.

[0029] One or more of these rules are applied based on the analysis information. For example, when the analysis method is "data classification" and the analysis purpose is "three-level evaluation of quality indexes," the rules are applied as follows: First, rule (1) excludes device parameters, index numbers, etc. from the analysis target. Next, rule (2) leaves only one type of highly correlated data as the analysis target. Next, rule (3) excludes data that does not change between normal and abnormal conditions from the analysis target. The remaining data to be analyzed is then analyzed, the data is classified, and the quality index is evaluated on a three-level scale.

[0030] Furthermore, for example, when the analysis method is "multiple regression analysis" and the analysis purpose is "calculation of a quality index value," the rules are applied as follows. First, rules (1) and (2) are applied in the same manner as above. Next, rule (4) excludes data with low contribution from the analysis target. The remaining data to be analyzed is then analyzed by multiple regression analysis, and a quality index value is calculated.

[0031] Rule (3) is based on discrete values, so it is well suited to a "three-level evaluation" that also uses discrete values. On the other hand, rule (4) is based on continuous values, so it is well suited to a "calculation of index values" that also uses continuous values.

[0032] The output unit 16 acquires the equipment data selected by the selection unit 15 and outputs it to the data analysis unit 17. The output unit 16 is an example of an output means according to the present disclosure.

[0033] The data analysis unit 17 analyzes the equipment data selected by the selection unit 15 and output by the output unit 16 based on the analysis information output by the analysis information acquisition unit 14, i.e., based on the analysis method and analysis purpose specified by the user. The data analysis unit 17 is an example of a data analysis means according to the present disclosure.

[0034] The display unit 18 displays a screen showing the results of the data analysis by the data analysis unit 17. The display unit 18 includes a display device such as a liquid crystal display or a touch screen.

[0035] Next, an example of the hardware configuration of the data analysis apparatus 10 will be described with reference to Fig. 2. The data analysis apparatus 10 shown in Fig. 2 is realized by a computer such as a personal computer or a microcontroller.

[0036] The data analysis apparatus 10 includes a processor 1001 , a memory 1002 , an interface 1003 , and a secondary storage device 1004 , which are connected to each other via a bus 1000 .

[0037] The processor 1001 is, for example, a CPU (Central Processing Unit). The processor 1001 loads an operating program stored in the secondary storage device 1004 into the memory 1002 and executes the program, thereby realizing each function of the data analysis device 10.

[0038] The memory 1002 is a main storage device configured, for example, by a RAM (Random Access Memory). The memory 1002 stores the operating program that the processor 1001 reads from the secondary storage device 1004. The memory 1002 also functions as a working memory when the processor 1001 executes the operating program.

[0039] The interface 1003 is an I / O (Input / Output) interface such as a serial port, a USB (Universal Serial Bus) port, a network interface, etc. The interface 1003 realizes the functions of the data collection unit 11.

[0040] The secondary storage device 1004 is, for example, a flash memory, a hard disk drive (HDD), or a solid state drive (SSD). The secondary storage device 1004 stores the operating programs executed by the processor 1001. The secondary storage device 1004 realizes the function of the storage unit 12.

[0041] Next, an example of the operation of data analysis by the data analysis device 10 will be described with reference to Fig. 3. The operation shown in Fig. 3 starts, for example, when a user inputs a data analysis method and a purpose of the data analysis via the input unit 13 and the input unit 13 outputs analysis information.

[0042] The analytical information acquisition unit 14 of the data analysis device 10 acquires analytical information from the input unit 13, and outputs the analytical information to the selection unit 15 and the data analysis unit 17 (step S101).

[0043] The selection unit 15 of the data analysis device 10 selects the equipment data stored in the storage unit 12 based on the analysis information output in step S101 (step S102).

[0044] The output unit 16 of the data analysis device 10 outputs the equipment data selected in step S102 to the data analysis unit 17 (step S103).

[0045] The data analysis unit 17 of the data analysis device 10 analyzes the selected equipment data output in step S103 based on the analysis information output in step S101 (step S104).

[0046] The output unit 16 of the data analysis device 10 displays a screen showing the results of the analysis performed in step S104 (step S105), and the data analysis device 10 then ends the data analysis operation.

[0047] The above has described the data analysis device 10 according to the first embodiment. According to the data analysis device 10, the equipment data collected from the FA device 20 is automatically selected as an analysis target based on the data analysis method and the purpose of the data analysis input by the user. This eliminates the need for the user to manually select the equipment data, thereby reducing the burden on the user in selecting data according to the analysis method and the purpose of the analysis.

[0048] Furthermore, the data analysis device 10 can automatically select equipment data, allowing a large amount of equipment data to be selected as the subject of analysis, which is expected to improve the accuracy of the analysis compared to when a user manually selects equipment data.

[0049] (Embodiment 2) A data analysis apparatus 10 according to embodiment 2 will be described with reference to Fig. 4. The data analysis apparatus 10 according to embodiment 2 differs from embodiment 1 in that it includes an importance calculation unit 19. It also differs from embodiment 1 in the following respects.

[0050] Unlike in the first embodiment, when a user inputs a data analysis method and a purpose of the data analysis, the data analysis apparatus 10 according to the second embodiment first calculates the importance of each piece of equipment data and displays the importance of each piece of data on the analysis target selection screen shown in Fig. 5 . The user then determines which data to use as the analysis target based on the importance and selects the data to use as the analysis target by checking or unchecking a check box in the "Select analysis target" column via the screen shown in Fig. 5 . The data analysis apparatus 10 selects and analyzes the selected equipment data as the analysis target.

[0051] The "importance" is calculated based on the results of applying the above selection rules (1)-(4) described in the first embodiment based on the analysis information, that is, based on the analysis method and the analysis purpose. For example, the above selection rules (1)-(4) are weighted based on the extent to which each rule affects the analysis, and the importance is calculated based on whether each rule was selected or not and the weighting of each rule. The "weighting" is determined based on, for example, empirical rules.

[0052] 4 again, the analysis information acquisition unit 14 in the second embodiment differs from the first embodiment in that it also outputs the analysis information to the importance calculation unit 19.

[0053] The importance calculation unit 19 calculates the importance of each piece of device data stored in the storage unit 12 based on the analysis information output by the analysis information acquisition unit 14. As described above, for example, the importance is calculated by weighting each of the above selection rules, based on whether or not each rule was selected, and the weighting of each rule. The importance calculation unit 19 is an example of an importance calculation means according to the present disclosure.

[0054] The display unit 18 differs from the first embodiment in that, when the importance calculation unit 19 calculates the importance, the display unit 18 displays an analysis target selection screen including a display of equipment data and a display of importance, as shown in FIG. 5 . Note that, when the screen is displayed, equipment data whose importance is equal to or greater than a predetermined threshold may be automatically selected as an analysis target, i.e., a check box in the "Select analysis target" column may be checked. This automatically selects equipment data with high importance, reducing the operational burden on the user. The display unit 18 according to the second embodiment is an example of a display means according to the present disclosure.

[0055] The input unit 13 differs from the first embodiment in that it accepts an operation for selecting an analysis target by the user when the display unit 18 displays the analysis target selection screen shown in FIG.

[0056] The selection unit 15 differs from embodiment 1 in that it does not select equipment data when the user first inputs the data analysis method and the purpose of the data analysis, but selects the equipment data selected by the user as the analysis target when the input unit 13 accepts the operation to select the analysis target.

[0057] According to the data analysis apparatus 10 of the second embodiment, the data analysis apparatus 10 first calculates the importance of the equipment data and displays it on the screen shown in Fig. 5, the user then determines the equipment data that the user wants to analyze based on the importance and selects the equipment data that the user wants to analyze on the screen shown in Fig. 5, and the data analysis apparatus 10 then selects the selected equipment data. As a result, unlike the first embodiment, the equipment data to be analyzed is not selected completely automatically, but the user can select the equipment data to be analyzed based on the importance, thereby improving flexibility in analysis.

[0058] In each of the above embodiments, the data analysis device 10 performs both the selection of device data and the analysis of the selected device data. However, the selection of device data and the analysis of the selected device data may be performed by separate devices.

[0059] For example, consider a data analysis system 3 shown in Fig. 6. The data analysis system 3 includes a data selection device 30 and a data analysis device 31. Note that the FA device 20 is not shown in Fig. 6.

[0060] The functional configuration of the data selection device 30 is generally the same as that of the data analysis device 10 according to the first embodiment shown in FIG. 1 , but differs from the first embodiment mainly in that it does not include a data analysis unit 17, that the analysis information acquisition unit 14 outputs analysis information to the output unit 16, and that the output unit 16 outputs the equipment data selected by the selection unit 15 and the analysis information output by the analysis information acquisition unit 14 to the data analysis device 31.

[0061] The data selecting device 30 does not include the data analysis unit 17, but instead a data analysis device 31, which is a device separate from the data selecting device 30, analyzes the equipment data selected by the selecting unit 15 and output by the output unit 16 of the data selecting device 30. When analyzing the equipment data, the data analysis device 31 analyzes the equipment data based on the analysis information output by the output unit 16 of the data selecting device 30. The data analysis device 31 also displays the analysis results on the display unit 18 of the data selecting device 30.

[0062] The above-described data analysis system 3 allows the selection of equipment data and the analysis of the selected equipment data to be performed by separate devices. In this case, the data analysis system 3 is an example of a data analysis system according to the present disclosure, the data selection device 30 is an example of a data selection device according to the present disclosure, and the data analysis device 31 is an example of a data analysis means according to the present disclosure.

[0063] 2, the data analysis apparatus 10 includes a secondary storage device 1004. However, the present invention is not limited to this, and the secondary storage device 1004 may be provided outside the data analysis apparatus 10, and the data analysis apparatus 10 and the secondary storage device 1004 may be connected via an interface 1003. In this configuration, removable media such as a USB flash drive or a memory card can also be used as the secondary storage device 1004.

[0064] 2, data analysis apparatus 10 may be configured with a dedicated circuit using an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), etc. In the hardware configuration shown in FIG. 2, some of the functions of data analysis apparatus 10 may be realized by a dedicated circuit connected to interface 1003, for example.

[0065] The program used in data analysis device 10 can be stored and distributed on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD (Digital Versatile Disc), a USB flash drive, a memory card, or a HDD. By installing such a program on a specific or general-purpose computer, the computer can function as data analysis device 10.

[0066] Furthermore, the above-mentioned program may be stored in a storage device owned by another server on the Internet, and the program may be downloaded from that server.

[0067] The present disclosure allows various embodiments and modifications without departing from the broad spirit and scope of the present disclosure. Furthermore, the above-described embodiments are intended to explain the present disclosure and do not limit the scope of the present disclosure. In other words, the scope of the present disclosure is defined by the claims, not the embodiments. Various modifications made within the scope of the claims and the meaning of equivalent disclosures are considered to be within the scope of the present disclosure.

[0068] 3 Data analysis system, 10 Data analysis device, 11 Data collection unit, 12 Memory unit, 13 Input unit, 14 Analysis information acquisition unit, 15 Selection unit, 16 Output unit, 17 Data analysis unit, 18 Display unit, 19 Importance calculation unit, 20 FA equipment, 30 Data selection device, 31 Data analysis device, 1000 Bus, 1001 Processor, 1002 Memory, 1003 Interface, 1004 Secondary storage device.

Claims

1. Computer, An analysis information acquisition means for acquiring analysis information indicating a data analysis method and a purpose of the data analysis, which is specified by a user; a selection means for selecting the equipment data acquired from the equipment based on the method of the data analysis indicated by the analysis information and the purpose of the data analysis indicated by the analysis information; an output means for outputting the equipment data selected by the selection means from the equipment data to a data analysis means for analyzing the data; A program that functions as a

2. The selection means determines a trend of data from the equipment data collected within a certain period of time, and selects the equipment data based on the trend. The program according to claim 1.

3. The device data includes a plurality of types of data, The selecting means selects the equipment data based on correlations between various types of equipment data collected within a certain period of time. The program according to claim 1.

4. The device data includes data indicating a staged state of the device, the selection means excludes from the device data a data item that does not change at a time when the stepwise state of the device changes in the data item indicating the stepwise state of the device, from a selection target. The program according to any one of claims 1 to 3.

5. The selection means applies a variable selection algorithm to the equipment data, and excludes equipment data having a low contribution degree when the variable selection algorithm is applied from a selection target. The program according to any one of claims 1 to 3.

6. The computer, an importance calculation means for calculating an importance of the equipment data acquired from the equipment based on the analysis information; a display means for displaying a screen including a display of the equipment data and a display of the importance, the screen allowing the user to select the equipment data; It also functions as the selection means selects the device data selected by the user via the screen displayed by the display means as a selection target. The program according to any one of claims 1 to 3.

7. An analysis information acquisition means for acquiring analysis information indicating a data analysis method and a purpose of the data analysis designated by a user; A selection means for selecting the equipment data acquired from the equipment based on the data analysis method indicated by the analysis information and the purpose of the data analysis indicated by the analysis information; an output means for outputting the equipment data selected by the selection means from the equipment data to a data analysis means for analyzing the data; A data selection device comprising:

8. A data selection device according to claim 7 and the data analysis means, The data analysis means analyzes the selected equipment data based on the analysis information. Data analysis system.

9. Obtain analysis information indicating the method and purpose of the data analysis specified by the user; Selecting the equipment data acquired from the equipment based on the data analysis method indicated by the analysis information and the purpose of the data analysis indicated by the analysis information; outputting the selected equipment data from the equipment data to a data analysis means for analyzing the data; Data selection methods.