Data analyzer, data analysis method, and data analysis program

Abstract

A data analyzer (100) analyzes multiple data sets handled by an equipment (200) being monitored. A design information acquisition unit (110) acquires design information (91) containing information that indicates multiple data sets. A classification unit (120) uses the design information (91) to classify data items of each of the multiple data sets, which are defined in the equipment (200), into input, output, or internal variable. Then, the classification unit (120) generates, as a classification result (92), the correspondence among the input, output, and internal variable obtained through the classification.

Description

Data analysis device, data analysis method, and data analysis program

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

[0002] One example of a technique for analyzing the causes of problems in monitored equipment is invariant analysis. This technique finds invariant relationships that hold under normal circumstances from the correlations of multiple signals, and determines that an abnormality exists when some of the correlations are broken. However, invariant analysis has the problem of high computational costs because it examines correlations across all data.

[0003] In Patent Document 1, data is grouped and the relationship between data within the monitored group or between data within the monitored group and data within a non-monitored group is analyzed. This omits the analysis of data within the non-monitored group and analyzes only the parts related to the monitored group, thereby reducing the processing load without significantly reducing accuracy.

[0004] Japanese Patent Application Laid-Open No. 2021-111214

[0005] The technology of Patent Document 1 limits the analysis target to relationships inside and outside a predetermined group, which poses a problem in that it is not possible to extract or limit unknown data to be analyzed.

[0006] An object of the present disclosure is to provide a data classification and data analysis technique that can extract or limit unknown data as an analysis target.

[0007] The data analysis device according to the present disclosure includes a design information acquisition unit that acquires design information including information indicating a plurality of data handled by equipment to be monitored, and a classification unit that uses the design information to classify data items of each of the plurality of data that are defined by the equipment as input, output, or internal variables, and generates a classification result that is a correspondence between the input, output, and internal variables obtained by the classification.

[0008] The data analysis device according to the present disclosure has the effect of being able to extract or limit unknown data as an analysis target.

[0009] 1 is a diagram showing an example of the configuration of a data analysis apparatus according to a first embodiment. FIG. 2 is a flow diagram showing an overview of the operation of a classification unit according to the first embodiment. FIG. 3 is a diagram showing an example of design information (control program) acquired by a design information acquisition unit according to the first embodiment. FIG. 4 is a flow diagram showing the operation of a classification unit according to the first embodiment. FIG. 5 is a diagram showing an example of a classification result by the classification unit according to the first embodiment. FIG. 6 is a diagram showing an example of information included in design information acquired by the design information acquisition unit according to the first embodiment. FIG. 7 is a diagram showing an example of the configuration of a data analysis apparatus according to a modified example of the first embodiment. FIG. 8 is a diagram showing an example of the configuration of a data analysis apparatus according to a second embodiment. FIG. 9 is a flow diagram showing the operation of a classification unit according to the second embodiment. FIG. 10 is a diagram showing an example of a control program acquired by a design information acquisition unit according to the second embodiment. FIG. 11 is a diagram showing an example of a variable list acquired by a design information acquisition unit according to the second embodiment. FIG. 12 is a diagram showing an example of a classification result according to the second embodiment. FIG. 13 is a flow diagram showing the operation of a mapping unit according to the second embodiment. FIG. 14 is a diagram showing an example of collected data according to the second embodiment. FIG. 15 is a diagram showing an example of a mapping result according to the second embodiment. FIG. 16 is a diagram showing an example of the configuration of a data analysis apparatus according to a third embodiment. FIG. 17 is a flow diagram showing the operation of an analysis unit according to the third embodiment. FIG. 18 is a diagram showing an example of the configuration of a data analysis apparatus according to a fourth embodiment. FIG. 19 is a flow diagram showing the operation of a factor location estimation unit according to the fourth embodiment. A diagram showing an example of a classification result according to embodiment 4. A diagram showing an example of a factor location classification table according to embodiment 4. A diagram showing an example of an analysis result according to embodiment 4. A diagram showing an image of factor locations indicated in the factor location classification table according to embodiment 4. A diagram showing an example of a factor location estimation result according to embodiment 4. A diagram showing another example of a factor location estimation result according to embodiment 4.

[0010] The present embodiment will be described below with reference to the drawings. In each drawing, identical or corresponding parts are designated by the same reference numerals. In the description of the embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate. Arrows in the drawings mainly indicate the flow of data or the flow of processing. Furthermore, the sized relationships between components in the following drawings may differ from the actual relationships. Furthermore, in the description of the embodiment, directions or positions such as up, down, left, right, front, rear, front and back may be indicated. These notations are used for convenience of explanation and do not limit the placement, direction or orientation of devices, instruments, parts, etc.

[0011] Embodiment 1. ***Description of Configuration*** Fig. 1 is a diagram showing an example of the configuration of a data analysis apparatus 100 according to this embodiment. Data analysis apparatus 100 is connected to a controller 201 via a network. Controller 201 is a controller provided in facility 200, which is an object to be monitored or analyzed. Facility 200 may be production facility, production equipment, or other device or facility.

[0012] The data analysis apparatus 100 is a computer. The data analysis apparatus 100 includes a processor 910, as well as other hardware such as a memory 921, an auxiliary storage device 922, an input interface 930, an output interface 940, and a communication device 950. The processor 910 is connected to the other hardware via signal lines and controls the other hardware.

[0013] The data analysis apparatus 100 includes, as functional elements, a design information acquisition unit 110, a classification unit 120, and a storage unit 190. The storage unit 190 stores design information 91 and classification results 92.

[0014] The functions of the design information acquisition unit 110 and the classification unit 120 are realized by software. The storage unit 190 is provided in the memory 921. The storage unit 190 may be provided in the auxiliary storage device 922, or may be provided separately in the memory 921 and the auxiliary storage device 922.

[0015] The processor 910 is a device that executes a data analysis program. The data analysis program is a program that realizes the functional elements of the data analysis apparatus 100. In this embodiment, the data analysis program is a program that realizes the functions of the design information acquisition unit 110 and the classification unit 120. The processor 910 is an IC that performs arithmetic processing. Specific examples of the processor 910 are a CPU, a DSP, and a GPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0016] The memory 921 is a storage device that temporarily stores data. Specific examples of the memory 921 are SRAM and DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory. The auxiliary storage device 922 is a storage device that saves data. A specific example of the auxiliary storage device 922 is an HDD. The auxiliary storage device 922 may also be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, flexible disk, optical disk, compact disk, Blu-ray (registered trademark) disk, or DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD (registered trademark) is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash (registered trademark). DVD is an abbreviation for Digital Versatile Disk.

[0017] The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. Specifically, the input interface 930 is a USB terminal. The input interface 930 may also be a port connected to a LAN. USB is an abbreviation for Universal Serial Bus. LAN is an abbreviation for Local Area Network.

[0018] The output interface 940 is a port to which a cable of an output device such as a display 941 is connected. Specifically, the output interface 940 is a USB terminal or an HDMI (registered trademark) terminal. Specifically, the display 941, i.e., the display, is an LCD. The output interface 940 is also called a display interface. HDMI (registered trademark) is an abbreviation for High Definition Multimedia Interface. LCD is an abbreviation for Liquid Crystal Display.

[0019] The communication device 950 has a receiver and a transmitter. The communication device 950 is connected to a communication network such as a LAN, the Internet, a telephone line, or Wi-Fi (registered trademark). Specifically, the communication device 950 is a communication chip or NIC. In this embodiment, the communication device 950 is connected to a controller 201 provided in the facility 200 to be monitored. NIC is an abbreviation for Network Interface Card.

[0020] The data analysis program is executed in the data analysis apparatus 100. The data analysis program is read into the processor 910 and executed by the processor 910. In addition to the data analysis program, an OS is also stored in the memory 921. The OS is an abbreviation for Operating System. The processor 910 executes the data analysis program while running the OS. The data analysis program and the OS may be stored in an auxiliary storage device 922. The data analysis program and the OS stored in the auxiliary storage device 922 are loaded into the memory 921 and executed by the processor 910. Note that part or all of the data analysis program may be incorporated into the OS.

[0021] Data analysis apparatus 100 may include multiple processors that replace processor 910. These multiple processors share the task of executing the data analysis program. Each processor is a device that executes the data analysis program, just like processor 910.

[0022] Data, information, signal values ​​and variable values ​​used, processed or output by the data analysis program are stored in memory 921 , secondary storage device 922 , or registers or cache memory within processor 910 .

[0023] The "parts" of the design information acquisition unit 110 and the classification unit 120 may be read as "circuits," "processes," "procedures," "processes," or "circuitry." The data analysis program causes a computer to execute a design information acquisition process and a classification process. The "processes" of the design information acquisition process and the classification process may be read as "programs," "program products," "computer-readable storage media storing programs," or "computer-readable recording media recording programs." The data analysis method is a method performed by the data analysis apparatus 100 executing a data analysis program. The data analysis program may be provided by being stored in a computer-readable recording media. The data analysis program may be provided as a program product.

[0024] The design information acquisition unit 110 acquires design information 91, which includes information indicating multiple data items handled by the equipment 200. The design information 91 is, for example, information that can be output from the controller 201 of the equipment 200, such as a control program executed by the controller 201. The design information 91 may also be information such as a design document or specifications related to the data and control program handled by the equipment 200. The design information 91 may be in any form as long as it is information necessary to categorize the data items described below. The controller 201 is a device used to control equipment or equipment. The controller 201 is, for example, a programmable logic controller (PLC). The storage unit 190 stores the design information 91 acquired by the design information acquisition unit 110. The classification unit 120 uses the design information 91 as input data. The classification unit 120 uses the design information 91 to classify each data item of the multiple data items included in the design information into input, output, or internal variables. The data items are items defined in the equipment or equipment to be monitored. The classification unit 120 generates the correspondence relationships between the inputs, outputs, and internal variables obtained by the classification as a classification result 92. Specifically, the classification unit 120 classifies various data items of the control program included in the design information 91 into inputs, outputs, and internal variables. Then, the classification unit 120 classifies the data by linking these correspondence relationships (relationships between input variables, output variables, and internal variables).

[0025] ***Description of Operation*** Next, the operation of data analysis apparatus 100 according to this embodiment will be described. The operation procedure of data analysis apparatus 100 corresponds to a data analysis method. Furthermore, a program that realizes the data analysis processing, which is the operation of data analysis apparatus 100, corresponds to a data analysis program.

[0026] 2 is a flow diagram showing an outline of the operation of data analysis apparatus 100 according to this embodiment. First, the outline of the operation of data analysis apparatus 100 will be described with reference to FIG.

[0027] 1 , the design information acquisition unit 110 acquires design information 91 from the controller 201 of the equipment 200 to be monitored. The design information acquisition unit 110 stores the design information 91 in the storage unit 190. The classification unit 120 acquires the control program from the design information 91 stored in the design information acquisition unit 110 or the storage unit 190.

[0028] FIG. 3 is a diagram showing an example of design information 91 (control program 912) acquired by the design information acquisition unit 110 according to this embodiment. The control program 912, as shown in the example of FIG. 3, is an instruction list acquired from the controller 201. Such an instruction list is, for example, the IL language defined in IEC 61131-3, and can be converted from the LD language commonly used in Japan. IEC is an abbreviation for International Electrotechnical Commission. IL is an abbreviation for Instruction List. LD is an abbreviation for Ladder Diagram. The instruction list describes the instructions to be executed by the controller 201 and their targets. The control program may include model information for the controller 201. Since the control program may be divided into multiple parts and written according to the functions to be realized, multiple control programs may exist.

[0029] <Classification Process: Step S2> After acquiring the information shown in FIG. 3, the classification unit 120 classifies data based on this information. In step 0 of the command list in FIG. 3, an "LD" command is executed for variable "X0." According to the controller model information, variables with an "X" suffix correspond to inputs, and "LD" is an input command, so "X0" can be classified as an input. Furthermore, in step 5, an "OUT" command is executed for variable "Y0." Since variables with a "Y" suffix correspond to outputs, and "OUT" is an output command, "Y0" is classified as an output. In addition, variables with an "M" or "T" suffix correspond to internal variables, so the variable "M0" in step 3 is classified as an internal variable regardless of the command type. Furthermore, a search is performed to determine whether there is an output associated with the input, or whether there is an input associated with the output. In this way, the classification unit 120 classifies the various data items handled by the controller from the control program into input, output, or internal variables, and creates correspondence relationships to classify the data.

[0030] <Classification Result Output Process> In step S3, the classification unit 120 outputs the classification result as the classification result 92.

[0031] Fig. 4 is a flow diagram showing the operation of the classification unit 120 according to this embodiment. The operation of the classification unit 120 will be described in detail with reference to Fig. 4. Specifically, the classification unit 120 classifies inputs, outputs, and internal variables using the command list of Fig. 3 and creates correspondence relationships.

[0032] In step S21, the classification unit 120 acquires the instruction list (control program) of FIG. 3. In step S22, the classification unit 120 focuses on "X0" in step 0, which has the suffix "X" and can be classified as an input from the input instruction "LD." In step S23, the classification unit 120 creates a correspondence relationship in which "X0" in step 0 is an input variable. In step S24, the classification unit 120 searches for an output instruction signal to find an output related to "X0." It is determined that "OUT," an output instruction to "M0," which has the suffix "M" indicating an internal variable, in step 3 in the instruction list, corresponds. In step S25, the classification unit 120 organizes the correspondence relationship between step 0 and step 3 in the instruction list. The classification unit 120 creates a correspondence relationship in which the input "X0" is output to the internal variable "M0." In step S26, the classification unit 120 searches for an input instruction signal to search for an input to "M0." This corresponds to "LD," the output instruction to "M0" in step 4. In step S27, the classification unit 120 searches for an output instruction signal to search for an output related to "M0." This corresponds to "OUT," the output instruction to "Y0" with the subscript "Y" indicating the output variable in step 5 in the instruction list. In step S28, the classification unit 120 can organize the correspondence into a correspondence such that the input "X0" is output to "Y0" via the internal variable "M0," and create the correspondence. In step S29, the classification unit 120 outputs the results of the categorization and correspondence in steps S22 to S28 as the classification result 92.

[0033] 5 is a diagram showing an example of a classification result 92 by the classification unit 120 according to this embodiment. In the classification result 92, the correspondence between inputs, internal variables, and outputs is organized.

[0034] The classification methods and the methods for creating correspondence relationships are not limited to those described above, and the classification of input, output, and internal variables and the creation of correspondence relationships may be performed using techniques such as static analysis. Variable classifications may overlap, such as when an output variable doubles as another input variable.

[0035] 6 is a diagram showing an example of information included in the design information 91 acquired by the design information acquisition unit 110 according to this embodiment. Information that assists in classification may also be added to the design information 91. For example, information on a closed control loop of a ladder program, as shown in FIG. 6, may be included in the design information 91. The information on a closed control loop of a ladder program is called a program block in FIG. 6. When program block information is available, classification becomes easier by searching for input / output instructions and the like within the program block.

[0036] ***Other Configurations*** In this embodiment, the functional elements of data analysis apparatus 100 are realized by software. As a variation, the functional elements of data analysis apparatus 100 may be realized by hardware. Specifically, data analysis apparatus 100 includes an electronic circuit 909 instead of processor 910.

[0037] 7 is a diagram showing an example of the configuration of a data analysis apparatus 100 according to a modified example of this embodiment. The electronic circuit 909 is a dedicated electronic circuit that realizes the functional elements of the data analysis apparatus 100. Specifically, the electronic circuit 909 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.

[0038] The functional elements of data analysis apparatus 100 may be realized by a single electronic circuit, or may be realized by distributing them across multiple electronic circuits.

[0039] As another modification, some of the functions of the functional elements of data analysis apparatus 100 may be realized by electronic circuits, and the remaining functions may be realized by software. Also, some or all of the functions of the functional elements of data analysis apparatus 100 may be realized by firmware.

[0040] Each of the processor and the electronic circuit is also called processing circuitry. That is, the functional elements of the data analysis apparatus 100 are realized by the processing circuitry.

[0041] ***Explanation of Effects of the Present Embodiment*** As described above, data analysis apparatus 100 according to the present embodiment categorizes data from the controller of the equipment to be monitored into input, output, and internal variables. Data analysis apparatus 100 then creates correspondence relationships between these variables, enabling data classification. By classifying data in this way, data analysis apparatus 100 according to the present embodiment can perform analysis in accordance with the correspondence relationships rather than comprehensively analyzing all data, thereby achieving the effect of being able to extract and limit the analysis target (data to be analyzed).

[0042] Embodiment 2 In this embodiment, differences from and additions to embodiment 1 will be mainly described. In this embodiment, components having the same functions as those in embodiment 1 will be assigned the same reference numerals, and descriptions thereof will be omitted.

[0043] In the first embodiment, it is assumed that the variables of the control program exist as data items in the collected data collected directly from the monitored equipment 200. In this embodiment, a data analysis device 100 will be described that can handle a case where the data items of the various data in the control program differ from the data items in the collected data collected from the equipment 200. For example, the various data items in the control program may differ from the data items collected from the equipment due to a process such as a user changing the variable names of the control program.

[0044] ***Description of Configuration*** Fig. 8 is a diagram showing an example of the configuration of data analysis apparatus 100 according to this embodiment. Fig. 8 shows only the functional elements of data analysis apparatus 100. The hardware is the same as in embodiment 1. Data analysis apparatus 100 according to this embodiment is connected to a data collection device 202 in addition to a controller 201 via a network.

[0045] Data analysis apparatus 100 according to this embodiment includes a collected data acquisition unit 130 and a mapping unit 140 in addition to the configuration of embodiment 1. Also, collected data 93 is stored in storage unit 190. Although not shown, data analysis apparatus 100 may also include a classification result output unit and a mapping result output unit. The design information acquisition unit 110, design information 91, classification unit 120, and classification result output unit basically conform to the description of embodiment 1.

[0046] The data collection device 202 is a device that collects data from the monitored facility 200. The controller 201 may also function as the data collection device 202.

[0047] In this embodiment, the design information acquisition unit 110 acquires design information 91 including a control program and a variable list. The variable list is a list that associates data items defined in the equipment 200 with user-defined items that are obtained by replacing the data items with different names in the control program.

[0048] The collected data acquisition unit 130 acquires collected data 93 from the data collection device 202. The collected data 93 is data collected from the equipment 200. The data items of the various data included in the collected data 93 are defined in the equipment 200. The collected data 93 is time-series data collected from the equipment to be monitored. The collected data items are data items of the collected data 93. The mapping unit 140 maps the classification results 92 and the collected data 93 using a variable list, and outputs the mapping results 94 obtained by the mapping. The mapping unit 140 associates the classification results 92 with the collected data 93. The mapping result output unit outputs the mapping results 94 obtained by the mapping unit 140.

[0049] ***Explanation of Operation*** <Classification Process> Fig. 9 is a flow diagram showing the operation of the classification unit 120 according to this embodiment. As explained in the first embodiment, the classification unit 120 basically performs classification of inputs, outputs, and internal variables and creates correspondence relationships for various data items of the control program. However, if the user has changed the variable names of the control program, it becomes difficult to classify data items by inputs, outputs, and internal variables. In this embodiment, the classification process is performed as shown in Fig. 9.

[0050] In step S31, the classification unit 120 acquires the design information 91. In step S32, the classification unit 120 checks whether there are any variables other than those defined in the various data items of the control program. A variable other than the defined variable name means a variable for which a user-defined item is set, which replaces a data item defined in the equipment 200 with a different name. In step S33, if there are any variables other than those defined, the classification unit 120 refers to the variable list 911 in the design information 91 and associates the variable names set by the user with the originally defined variable names. The variable list 911 is a list for associating variable names used in the control program defined by the specifications of the controller 201 when the user replaces them with arbitrary names. The variable list can be output from the controller 201.

[0051] FIG. 10 is a diagram showing an example of a control program acquired by the design information acquisition unit 110 according to this embodiment. FIG. 11 is an example of a variable list 911 acquired by the design information acquisition unit 110 according to this embodiment. As an example, the command list in FIG. 10 will be classified. In step 0 of FIG. 10, the variable name is "sensor F," making it difficult to categorize it by input, output, and internal variable. Therefore, the variable list 911 shown in FIG. 11 is referenced. FIG. 11 shows that the variable name "X0" originally defined in the control program has been replaced with "sensor F" by the user.

[0052] In step S34, the classification unit 120 classifies the various data items of the control program into inputs, outputs, and internal variables to create correspondence relationships.

[0053] FIG. 12 is a diagram showing an example of a classification result 92 according to this embodiment. In step S35, the classification unit 120 outputs the results of the classification and the correspondence relationships created as a classification result 92, for example, as shown in FIG. 12. When creating the correspondence relationships, the variable names may be written using either the variable names set by the user or the originally defined variable names. FIG. 12 shows an example in which the variable names set by the user, i.e., the user-defined items, are used.

[0054] 13 is a flow diagram showing the operation of the mapping unit 140 according to this embodiment. In step S41, the mapping unit 140 acquires the classification result 92 output from the classification unit 120. In step S42, the mapping unit 140 acquires the collected data 93. In step S43, the mapping unit 140 acquires the variable list 911 included in the design information 91. The processing from step S41 to step S43 may be performed in any order.

[0055] 14 is a diagram showing an example of collected data 93 according to this embodiment. An example of the variable list 911 has been described with reference to FIG. 11. In step S44, the mapping unit 140 determines whether the data items of the classification results 92 correspond to the data items of the collected data 93. If there is no correspondence, the process proceeds to step S45. If there is a correspondence, the process proceeds to step S46.

[0056] In step S45, the mapping unit 140 refers to the variable list 911 of the design information 91, and associates the variable names set by the user, i.e., the user-set items, with the originally defined variable names (data items). In step S46, the mapping unit 140 then associates the classification results 92 with the collected data 93. In step S47, the mapping unit 140 outputs information associating the classification results 92 with the collected data 93 as the mapping result 94.

[0057] FIG. 15 is a diagram showing an example of a mapping result 94 according to this embodiment. Here, the mapping process will be described in detail with reference to FIGS. 11 to 15 . Focusing on the classification result for correspondence 1 in FIG. 12 , it can be seen from the variable list in FIG. 11 that the original variable name for "sensor F" is "X0." Therefore, the mapping result for correspondence 1 of the classification result in FIG. 12 and the collected data in FIG. 14 is output as shown in FIG. 15 , for example, by referring to the variable list in FIG. 11 . Ultimately, mapping results are generated and output for all correspondences (correspondences 2 to 6 in FIG. 12 ). While FIG. 15 shows that the data items of the classification result are associated with the collected data, which is time-series data, the association may also be based on the collected data items rather than the time-series data. While FIG. 13 shows that the variable list is referenced when the data items of the classification result do not correspond to the collected data items, the variable list may also be referenced when they correspond. As a result, when the classification unit 120 in this embodiment creates classification results, even if the variable names of the control program are set using the originally defined variable names rather than the user-set items, it is possible to associate the classification results with the user-set variable names and collected data.

[0058] ***Explanation of Effects of the Present Embodiment*** As described above, in data analysis apparatus 100 according to the present embodiment, even if the user changes the variable names of the control program, data can be classified by the classification device made up of a classification unit and a mapping unit. By classifying data, analysis can be performed in accordance with the correspondence relationships of the classification results, rather than comprehensively analyzing all data, making it possible to extract and limit the analysis target.

[0059] Embodiment 3 In this embodiment, differences from and additions to Embodiments 1 and 2 will be mainly described. In this embodiment, components having the same functions as those in Embodiments 1 and 2 will be assigned the same reference numerals, and descriptions thereof will be omitted. In this embodiment, differences from and additions to Embodiment 1 will mainly be described.

[0060] In the first and second embodiments, it is assumed that data analysis apparatus 100 classifies data of facility 200 into input, output, and internal variables and creates correspondence relationships. In the present embodiment, an aspect of analyzing data of facility 200 based on the classification results by data analysis apparatus 100 will be described.

[0061] ***Description of Configuration*** Fig. 16 is a diagram showing an example of the configuration of data analysis apparatus 100 according to this embodiment. Fig. 16 shows only the functional elements of data analysis apparatus 100. The hardware is the same as in the first embodiment.

[0062] In addition to the configuration of the first embodiment, the data analysis apparatus 100 according to this embodiment includes a collected data acquisition unit 130, an analysis unit 150, and an analysis result output unit 160. Also, collected data 93 is stored in a storage unit 190. The design information acquisition unit 110, design information 91, classification unit 120, collected data acquisition unit 130, and collected data 93 basically conform to the descriptions in the first and second embodiments.

[0063] The collected data acquisition unit 130 acquires collected data 93, which is time-series data. The analysis unit 150 performs analysis on only data having a corresponding relationship among the collected data 93, based on the corresponding relationship in the classification result 92. The analysis unit 150 outputs an analysis result 95 obtained by the analysis to a display 941 or the like.

[0064] ***Explanation of Operation Fig. 17 is a flow diagram showing the operation of analysis unit 150 according to this embodiment. Hereinafter, the operation of analysis unit 150 according to this embodiment will be described with reference to Figs. 5, 14, 16, and 17.

[0065] <Analysis Process> In step S51, the analysis unit 150 acquires the classification result 92. In step S52, the analysis unit 150 acquires the collected data 93. The order of steps S51 and S52 does not matter.

[0066] In step S53, the analysis unit 150 analyzes the collected data 93 based on the correspondence relationships in the classification results 92. At this time, analysis between inputs, outputs, and internal variables that do not have a correspondence relationship is omitted. In step S54, the analysis unit 150 outputs the analysis results 95 to the analysis result output unit 160. The analysis results 95 may be output by the analysis result output unit 160 to an output device such as a display 941.

[0067] As an example, assume that the analysis unit 150 acquires the classification result 92 in FIG. 5 and the collected data 93 in FIG. 14. Focusing on the correspondence relationship 1 in FIG. 5, the input "X0," the internal variable "M0," and the output "Y0" are mutually analyzed. On the other hand, analysis of variables that do not have a corresponding relationship, such as the input "X0" and the input "X1," can be omitted. The analysis method used by the analysis unit 150 is not particularly important. For example, correlation analysis, or other methods targeting data between two points, can be easily applied. It can also be similarly applied to regression analysis or machine learning methods that determine a dependent variable and an explanatory variable. For example, it is possible to avoid using data that does not have a corresponding relationship with the dependent variable as an explanatory variable. Furthermore, when data that does not have a corresponding relationship with the dependent variable is used as an explanatory variable, it is possible to lower the priority of that data. Alternatively, the dependent variable may be input separately, and the explanatory variable may be determined based on this correspondence relationship. The collected data 93 in FIG. 14 is bit (0 / 1) data. The analysis unit 150 may convert these into feature quantities (for example, a period of 0, a period of 1, or an interval at which the value changes from 0 to 1) and perform analysis. The collected data 93 may be numerical data other than bit data.

[0068] In this embodiment, the configuration has been described in which the collected data 93 is analyzed using the classification result 92 described in embodiment 1. Alternatively, the data analysis apparatus 100 according to this embodiment may be configured to analyze the collected data 93 using the mapping result 94 described in embodiment 2. The mapping result 94 by the mapping unit 140 may be used during analysis. In this case, the data analysis apparatus 100 may not analyze data other than those having the corresponding relationship represented by the mapping result 94 described in embodiment 2. This limits the analysis target and reduces the processing load required for the analysis. Specifically, a case will be described in which the mapping result 94 described in embodiment 2 is used with the collected data 93 shown in FIG. 14. The mapping result 94 in FIG. 15 is actually a result of mapping all of the correspondences 1 to 6 described in FIG. 12. The data analysis apparatus 100 refers to the classification result 92 described in FIG. 12 based on this mapping result 94, and operates so as not to analyze data other than those having the corresponding relationship. This reduces the processing load required for the analysis.

[0069] ***Explanation of Effects of the Present Embodiment*** As described above, data analysis apparatus 100 according to the present embodiment performs analysis using classification results, thereby enabling analysis by extracting and limiting the analysis target. By limiting the analysis target, the processing load required for the analysis can be reduced.

[0070] Embodiment 4 In this embodiment, differences from and additions to Embodiments 1 to 3 will be mainly described. In this embodiment, components having the same functions as those in Embodiments 1 and 2 will be given the same reference numerals, and descriptions thereof will be omitted. In this embodiment, differences from and additions to Embodiment 3 will mainly be described.

[0071] In the above-described third embodiment, it is assumed that an analysis target of the facility 200 is extracted through classification by the classification unit 120, and the limited analysis target is analyzed by the analysis unit 150. Therefore, in this embodiment, an aspect of estimating a potential occurrence location using the analysis result 95 will be described.

[0072] ***Description of Configuration*** Fig. 18 is a diagram showing an example of the configuration of data analysis apparatus 100 according to this embodiment. Fig. 18 shows only the functional elements of data analysis apparatus 100. The hardware is the same as in embodiment 1. Data analysis apparatus 100 according to this embodiment is connected to controller 201, data collection device 202, and also to classification table database 203 via a network.

[0073] In addition to the configuration of the third embodiment, the data analysis apparatus 100 according to this embodiment includes a classification table acquisition unit 170, a factor location estimation unit 180, and an estimation result output unit 161. A factor location classification table 96 is stored in a storage unit 190. Other functional elements are basically the same as those described in the first to third embodiments.

[0074] The classification table database 203 stores a factor location classification table 96. The factor location classification table 96 is a table in which estimated factors are set according to combinations of analysis results of each data of a plurality of data. The classification table acquisition unit 170 acquires the factor location classification table 96 from the classification table database 203 or the like. The factor location classification table 96 is stored in the storage unit 190. The factor location estimation unit 180 estimates factor locations in the correspondence relationship based on the analysis result 95 based on the classification result 92 and the factor location classification table 96. The factor location estimation unit 180 outputs a factor location estimation result 97 obtained by the estimation. The estimation result output unit 161 outputs the factor location estimation result 97 to a display 941 or the like.

[0075] ***Explanation of Operation Fig. 19 is a flow diagram showing the operation of the factor location estimating unit 180 according to this embodiment. Hereinafter, the operation of the factor location estimating unit 180 according to this embodiment will be described with reference to Figs. 5, 14, 18 to 25.

[0076] 18 , the classification table acquisition unit 170 acquires a factor location classification table 96 from the classification table database 203. The factor location classification table 96 may be provided in the factor location estimation unit 180. Alternatively, if each piece of equipment has a factor location classification table 96, the factor location classification table 96 may be acquired from each piece of equipment. The acquired factor location classification table 96 is stored in the storage unit 190.

[0077] In step S61, the factor location estimating unit 180 acquires the classification result 92 output from the classifying unit 120. The factor location estimating unit 180 may acquire the classification result 92 via the analyzing unit 150. In step S62, the factor location estimating unit 180 acquires the analysis result 95 output from the analyzing unit 150. In step S63, the factor location estimating unit 180 acquires the factor location classification table 96 acquired by the classification table acquiring unit 170. The order of steps S61, S62, and S63 does not matter.

[0078] In step S64, the factor location estimation unit 180 estimates a factor location from the acquired analysis result 95 and factor location classification table 96. In step S65, the factor location estimation unit 180 outputs the estimation result of the factor location to the estimation result output unit 161 as a factor location estimation result 97. The estimation result output unit 161 displays the factor location estimation result 97 on the display 941, for example.

[0079] Fig. 20 is a diagram showing an example of a classification result 92 according to this embodiment. Fig. 21 is a diagram showing an example of a factor location classification table 96 according to this embodiment. Fig. 22 is a diagram showing an example of an analysis result 95 according to this embodiment. Fig. 23 is a diagram showing an image of factor locations indicated by the factor location classification table 96 according to this embodiment. Fig. 24 is a diagram showing an example of a factor location estimation result 97 according to this embodiment. Fig. 25 is a diagram showing another example of a factor location estimation result 97 according to this embodiment.

[0080] As an example, the cause location is estimated using an analysis result 95 obtained by analysis based on the classification result 92 in Fig. 20 and a cause location classification table 96 shown in Fig. 21. Fig. 22 shows a part of the analysis result 95. The analysis result 95 in Fig. 22 is the result of analyzing whether each piece of data was constant (normal) or indefinite (abnormal) for the correspondence relationship 3 in Fig. 20.

[0081] The cause location classification table 96 in FIG. 21 shows that, when focusing on the analysis results of input and output items in a certain correspondence relationship, each estimated cause can be classified into classification numbers A to D. Classification number A indicates a case where the input is constant (normal) and the output is constant (normal). In this case, it is estimated that the cause of the trouble was not observable from the collected data or exists outside the collected range. Classification number B indicates a case where the input is constant (normal) and the output is undefined (abnormal). In this case, it is estimated that the cause of the trouble exists in the control program logic inside the controller that processed the input. Classification number C indicates a case where the input is undefined (abnormal) and the output is constant (normal). In this case, it is estimated that the cause of the trouble exists in the environment outside the controller leading up to the input and / or that the control program logic inside the controller is incorrectly correcting it. Classification number D indicates a case where the input is undefined (abnormal) and the output is undefined (normal). In this case, it is estimated that the cause of the trouble exists in the environment outside the controller leading up to the input, and that the input directly leads to the undefined output.

[0082] FIG. 23 illustrates the cause locations indicated by the above classification numbers. According to the analysis results for correspondence relationship 3 in FIG. 22, the analysis results for the input items are indefinite, while the analysis results for the output items are constant. Therefore, referring to the cause location classification table 96 in FIG. 21, correspondence relationship 3 corresponds to classification number C. Therefore, it is estimated that the cause of the trouble lies in the environment external to the controller and / or within the controller leading up to the input.

[0083] FIG. 24 shows an example of the results of estimating the cause locations for correspondence relationships 1 to 4 based on the classification result 92 in FIG. 20. According to FIG. 24, the cause lies before the input of correspondence relationship 2, before the input of correspondence relationship 3, and / or in the control program logic of the device. When a process in a certain piece of equipment corresponds to a correspondence relationship, it can also be estimated that the uncertainty in correspondence relationship 2 occurred before the uncertainty in correspondence relationship 3, as shown by the order in FIG. 25. The cause location estimating unit 180 may also identify the order in which such uncertainty occurred.

[0084] In this embodiment, the configuration has been described in which the collected data 93 is analyzed using the classification result 92 described in embodiment 3. Alternatively, the data analysis apparatus 100 according to this embodiment may be configured to analyze the collected data 93 using the mapping result 94 described in embodiment 2. The mapping result 94 by the mapping unit 140 may be used during analysis.

[0085] ***Explanation of the Effects of the Present Embodiment*** As described above, in addition to the effects of the first to third embodiments, the data analysis apparatus 100 according to the present embodiment can estimate the causal location by utilizing the analysis results based on the correspondence of the classification results.

[0086] In the above first to fourth embodiments, each unit of the data analysis apparatus has been described as an independent functional block. However, the configuration of the data analysis apparatus does not have to be the same as that of the above-described embodiments. The functional blocks of the data analysis apparatus may have any configuration as long as they can realize the functions described in the above-described embodiments. Furthermore, the data analysis apparatus may not be a single device, but may be a system composed of multiple devices. Furthermore, multiple parts of the first to fourth embodiments may be combined and implemented. Alternatively, only one part of these embodiments may be implemented. In addition, these embodiments may be combined in any way, either as a whole or in part. That is, in the first to fourth embodiments, each embodiment may be freely combined, or any component of each embodiment may be modified, or any component of each embodiment may be omitted.

[0087] The above-described embodiments are essentially preferred examples and are not intended to limit the scope of the present disclosure, the scope of application of the present disclosure, or the scope of use of the present disclosure. The above-described embodiments can be modified in various ways as needed. For example, the procedures described using flow charts or sequence diagrams may be modified as appropriate.

[0088] 81 Data item, 82 User setting item, 91 Design information, 911 Variable list, 912 Control program, 92 Classification result, 93 Collected data, 94 Mapping result, 95 Analysis result, 96 Factor location classification table, 97 Factor location estimation result, 100 Data analysis device, 110 Design information acquisition unit, 120 Classification unit, 130 Collected data acquisition unit, 140 Mapping unit, 150 Analysis unit, 160 Analysis result output unit, 161 Estimation result output unit, 170 Classification table acquisition unit, 180 Factor location estimation unit, 190 Storage unit, 200 Equipment, 201 Controller, 202 Data collection device, 203 Classification table database, 909 Electronic circuit, 910 Processor, 921 Memory, 922 Auxiliary storage device, 930 Input interface, 940 Output interface, 941 Display, 950 Communication device.

Claims

1. A data analysis device comprising: a design information acquisition unit that acquires design information including information indicating multiple data handled by equipment to be monitored; and a classification unit that uses the design information to classify data items of each of the multiple data that are defined by the equipment as either input, output, or internal variables, and generates a classification result that shows the correspondence between the input, output, and internal variables obtained by the classification.

2. The data analysis device according to claim 1, wherein the design information acquisition unit acquires the design information including a control program executed in the equipment and a variable list that associates the data items with user-defined items in the control program that have been replaced with different names for the data items, and the data analysis device further comprises: a collected data acquisition unit that acquires collected data collected from the equipment; and a mapping unit that uses the variable list to map the classification results to the collected data and output the mapping results obtained by the mapping.

3. The data analysis device according to claim 2, wherein the collected data acquisition unit acquires the collected data which is time series data, and the data analysis device further comprises an analysis unit that analyzes data having a correspondence among the collected data based on the correspondence of the classification results, and outputs the analysis results obtained by the analysis.

4. The data analysis device according to claim 3, further comprising a factor location estimation unit that estimates factor locations in a correspondence relationship based on a factor location classification table in which estimated factors are set according to the combination of analysis results of each of the plurality of data, and the analysis results and the classification results.

5. A data analysis method in which a computer acquires design information containing information indicating multiple data handled by equipment to be monitored, and the computer uses the design information to classify each data item of the multiple data that is defined by the equipment as either an input, output, or internal variable, and generates a classification result that shows the correspondence between the input, output, and internal variable obtained by the classification.

6. A data analysis program that causes a computer to execute the following steps: a design information acquisition process that acquires design information containing information indicating multiple data handled by equipment to be monitored; and a classification process that uses the design information to classify each data item of the multiple data that is defined in the equipment as either an input, output, or internal variable, and generates a classification result that shows the correspondence between the input, output, and internal variable obtained by the classification.

Images