Data visualization device, data visualization method, and program

Abstract

To efficiently grasp the features and tendencies of massive and complicated data.SOLUTION: A data visualization device of an embodiment of the present invention comprises: a storage unit configured to store a prescribed analysis result for an analysis object; an index value calculation unit configured to calculate a prescribed index value from each analysis result for one or more analysis objects selected by a user; and a display unit configured to display a list of analysis tables, which represents the analysis results for each of the one or more analysis objects. The display unit is configured to differentiate the display mode of the analysis table, which shows the analysis result corresponding to the index value, according to the index value.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a data visualization device, a data visualization method, and a program. [Background technology]

[0002] Techniques for displaying multiple images or screens as thumbnails to supervise or monitor processes in a plant or the like have been known for some time (see, for example, Patent Documents 1 to 4). On the other hand, when an abnormality or the like (e.g., a malfunction of equipment or facilities, an abnormality in product quality, etc.) occurs in a process in a plant or the like, it may be desirable to check the results of an analysis of the process (e.g., data characteristics and trends) in order to identify the cause. Furthermore, there may be cases where it is desirable to check the results of an analysis of the process for some other purpose other than identifying the cause of the abnormality or the like. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-26627 [Patent Document 2] Japanese Patent Application Laid-Open No. 2013-527346 [Patent Document 3] Japanese Patent Application Laid-Open No. 2015-187860 [Patent Document 4] International Publication No. 2020 / 075299 Summary of the Invention [Problem to be solved by the invention]

[0004] However, data representing processes such as those in plants is generally multivariate and complex, and the amount of data is often large, making it difficult to efficiently grasp the characteristics and trends of such large amounts of complex data.

[0005] One embodiment of the present invention has been made in consideration of the above points, and aims to improve the efficiency of grasping the characteristics and trends of large amounts of complex data. [Means for solving the problem]

[0006] In order to achieve the above-mentioned object, a data visualization device according to one embodiment comprises a memory unit configured to store predetermined analysis results for analysis targets; an index value calculation unit configured to calculate predetermined index values ​​from the analysis results for each of one or more analysis targets selected by a user; and a display unit configured to display a list of analysis tables representing the analysis results for each of the one or more analysis targets, wherein the display unit is configured to change the display mode of the analysis table representing the analysis results corresponding to the index value depending on the value of the index value. [Effects of the Invention]

[0007] It is possible to efficiently grasp the characteristics and trends of large amounts of complex data. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of a data visualization system according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram showing an example of an analysis table. [Figure 3] FIG. 10 is a diagram illustrating an example of an analysis table list screen. [Figure 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of a terminal according to the present embodiment. [Figure 5] FIG. 2 is a diagram illustrating an example of a functional configuration of a terminal according to the present embodiment. [Figure 6] 10 is a flowchart illustrating an example of a display process of an analysis table list screen according to the present embodiment. [Figure 7] FIG. 10 is a diagram showing a modified example (part 1) of the analysis table list screen. [Figure 8] FIG. 10 is a diagram showing a modified example (part 2) of the analysis table list screen. [Figure 9] FIG. 10 is a diagram showing a modified example (part 3) of the analysis table list screen. [Figure 10] FIG. 10 is a diagram (part 1) showing an example of the display order of the analysis table. [Figure 11] FIG. 10 is a diagram (part 2) showing an example of the display order of the analysis table. DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of the present invention will be described below. In this embodiment, a data visualization system 1 will be described that targets a plant process and visualizes a list of analysis tables that show the analysis results of data representing the process (hereinafter also referred to as process data), thereby enabling efficient understanding of the characteristics and trends of large amounts of complex process data. Furthermore, the following description will be made assuming that the plant process is primarily a batch process. However, the batch process is merely an example, and the present invention is not limited to this, and can be similarly applied to processes other than batch processes, such as continuous system processes, for example.

[0010] Note that using plant process data as the analysis target is just one example, and any large amount of complex data (i.e., particularly large amounts of multivariate data) can be used as the analysis target. For example, large amounts of complex data obtained from various devices, equipment, facilities, systems, robots, etc. other than plants can also be used as the analysis target.

[0011] <Overall configuration example of data visualization system 1> An example of the overall configuration of a data visualization system 1 according to this embodiment is shown in Fig. 1. As shown in Fig. 1, the data visualization system 1 according to this embodiment includes a terminal 10, a data analysis system 20, a control device 30, and a plant 40. The terminal 10 and the data analysis system 20 are communicatively connected via an arbitrary communication network. Similarly, the data analysis system 20 and the control device 30 are connected via an arbitrary communication network, and the control device 30 and the plant 40 are connected via an arbitrary communication network.

[0012] The terminal 10 is, for example, a terminal such as a PC (personal computer) used by a person in charge of grasping the characteristics and trends of the process data of the plant 40 based on the analysis results of the process data.

[0013] The data analysis system 20 performs various analyses on the process data (for example, correlation analysis between process variables, etc.). Here, a list of analysis tables showing the analysis results by the data analysis system 20 may be visualized on a display provided in the data analysis system 20, or may be visualized on a display provided in the terminal 10. Below, as an example, a case where a list of analysis tables is visualized on a display provided in the terminal 10 will be mainly described.

[0014] In addition to the various analyses described above, the data analysis system 20 also diagnoses the presence or absence of an abnormality in the process (batch process) of the plant 40 using, for example, multivariate statistical process control (MSPC). More specifically, the data analysis system 20 acquires measurement values ​​of various process variables from the control device 30 at each measurement cycle and calculates a statistical quantity called a Q value from these measurement values ​​and a pre-created model (this model is also called a normal model because it is created from normal data of the batch process). The data analysis system 20 then diagnoses that an abnormality (or a sign of an abnormality) has occurred in the batch process when the maximum Q value in the batch process exceeds a predetermined threshold, also called a control limit. Here, the process variables of the batch process may be referred to as "diagnostic parameters" or simply "parameters." The process variables present may vary depending on the process, but examples include temperature, pressure, flow rate, gas concentration, current, voltage, frequency, rotation speed, output, and various control information. Note that abnormality diagnosis using MSPC is a known technique, and for details thereof, see, for example, reference material such as "Kano Manabu, 'Statistical Process Management Using Process Chemometrics,' Systems / Control / Information, Vol. 48, No. 5, pp. 165-170, 2004." However, diagnosing the presence or absence of an abnormality using MSPC is just one example, and the data analysis system 20 may diagnose the presence or absence of an abnormality using any other arbitrary technique (for example, a machine learning technique such as a neural network).

[0015] The data analysis system 20 may have a plurality of abnormality diagnosis units (or may be called abnormality diagnosis engines) having different models etc. depending on the type or category of batch processes, for example.

[0016] The control device 30 acquires measured values ​​of various process variables from the plant 40, and controls the plant 40 based on these measured values. An example of the control device 30 is a programmable logic controller (PLC).

[0017] The plant 40 is various types of equipment or facilities that execute a batch process (hereinafter simply referred to as "batch"). Specific examples of the plant 40 include a petrochemical plant, a steel plant, a food plant, etc.

[0018] 1 is merely an example, and other configurations may be used. For example, the data analysis system 20 and the control device 30 may be integrated into one unit.

[0019] <Analysis table> Here, an analysis table will be explained. An analysis table is a table that shows the results of a predetermined analysis performed by the data analysis system 20 for each predetermined analysis unit (e.g., batch) using the measured values ​​of various process variables of the process data for that analysis unit. Note that, in the following, the analysis unit is mainly assumed to be a batch unit, but is not limited to this.

[0020] Examples of analysis tables include correlation tables that show the correlation between process variables, histograms that show the frequency of values ​​that process variables take, scatter plots that plot values ​​between process variables, trend graphs that show the time-series changes in the values ​​of process variables, and any form that lists the values ​​of specific process variables and related character strings. In the following, the analysis table will be mainly described assuming a correlation table. Note that analysis tables are obtained for each batch. However, this is not limited to this, and as described above, a predetermined analysis may be performed for each predetermined analysis unit, and an analysis table that shows the analysis results may be obtained for each analysis unit.

[0021] An example of an analysis table is shown in Figure 2. Analysis table 1000 shown in Figure 2 shows the results of a correlation analysis performed using the measurement values ​​of various process variables for a certain batch, and includes measurement start date and time 1001 indicating the date and time when measurement of the process variables for that batch started, diagnosis start date and time 1002 indicating the date and time when diagnosis of the batch for the presence or absence of an abnormality started, abnormality presence / absence 1003 indicating the abnormality diagnosis result for that batch, and correlation display field 1004 in which the correlation coefficient between the process variables is displayed.

[0022] The correlation display field 1004 included in the analysis table 1000 shown in FIG. 2 displays the correlation coefficient between two different process variables from the process variables "001" to "010." Correlation coefficients equal to or greater than a predetermined threshold (hereinafter, this threshold will also be referred to as the "first threshold") are highlighted. For example, in FIG. 2, the first threshold is "0.8," and the correlation coefficient between the process variables "001" and "002" is "0.9," so this correlation coefficient "0.9" is highlighted. Similarly, the correlation coefficient between the process variables "002" and "003" is "0.96," and this correlation coefficient "0.96" is highlighted.

[0023] When identifying the cause of an abnormality in a certain batch, the user can find out whether there is a correlation between the process variables of the batch by checking the analysis table 1000 as shown in FIG.

[0024] 2, analysis tables with correlation coefficients equal to or greater than a first threshold are highlighted, but multiple thresholds may be set to vary the highlighting mode. Specifically, th1, th2, and th3 may be set as first thresholds, and the display mode may be different for cases where the correlation coefficient is equal to or greater than th1 but less than th2, between th2 and less than th3, and equal to or greater than th3.

[0025] <Analysis table list screen> Here, when grasping the characteristics and trends of process data for some purpose, such as identifying the cause of an abnormality in a certain batch, a user may want to check the analysis tables of multiple batches (especially many batches within a certain period of time). However, checking the analysis tables of many batches one by one requires a great deal of effort and time, and is inefficient. Furthermore, even if checking the analysis tables of many batches one by one, it is difficult to grasp the characteristics and trends of the process data.

[0026] One way to address this issue is to display the analysis tables for many batches as thumbnails (i.e., displaying a list of reduced images of many analysis tables arranged vertically and horizontally), but even if many analysis tables (e.g., 100 analysis tables) are displayed as thumbnails, it is still difficult to grasp the characteristics and trends of the process data.

[0027] Therefore, in this embodiment, when displaying a large number of analytical tables as thumbnails, a predetermined index value is calculated for each analytical table, and the display mode of each analytical table is changed according to this index value. Fig. 3 shows an example of an analytical table list screen on which analytical tables are displayed in this manner. The analytical table list screen 2000 shown in Fig. 3 includes an analytical table display field 2001 in which multiple analytical tables are displayed in a list (thumbnail display) arranged vertically and horizontally. For example, in Fig. 3, 100 analytical tables, analytical table 1 to analytical table 100, are displayed in the analytical table display field 2001.

[0028] At this time, each analysis table is displayed in a different display mode depending on the predetermined index value in the analysis table display field 2001. For example, Fig. 3 shows an example in which analysis tables whose predetermined index value is equal to or greater than a certain threshold value (hereinafter, this threshold value will also be referred to as the "second threshold value") are highlighted, and analysis tables 12 to 25 are highlighted in the analysis table display field 2001.

[0029] Here, the index value refers to various statistical quantities for the analysis results represented by the analysis table, and various values ​​can be used. For example, if the analysis table is a correlation table, the index value can be the proportion of pairs of process variables in the correlation table whose correlation coefficient is equal to or greater than a first threshold. If the analysis table is a histogram, the index value can be the mean or median of the histogram's frequency, the skewness or kurtosis of the histogram, or a combination thereof (e.g., a weighted sum of one or more of the mean, median, skewness, and kurtosis). If the analysis table is a scatter plot, the index value can be the correlation coefficient, variance, standard deviation, or a combination thereof (e.g., a weighted sum of one or more of the correlation coefficient, variance, and standard deviation). If the analysis table is a trend graph, the index value can be a score representing the degree of deviation between the trend graph and the normal waveform represented by the normal model. Furthermore, for example, if the analysis table is a form, it is conceivable that the index value would be a specific value contained in the form, the presence or absence of a keyword, or the like.

[0030] This allows users to get an overview of a large number of analysis tables, understand the characteristics and trends of the process data (i.e., biases and trends in the analysis results for each batch), and compare analysis tables with each other. For example, they can identify analysis tables for batches where significant abnormalities or signs of abnormality are evident, and then identify the cause of the abnormality from those analysis tables.

[0031] <Example of hardware configuration for terminal 10> An example of the hardware configuration of the terminal 10 according to this embodiment is shown in Fig. 4. As shown in Fig. 4, the terminal 10 according to this embodiment includes an input device 101, a display device 102, an external I / F 103, a communication I / F 104, a RAM (Random Access Memory) 105, a ROM (Read Only Memory) 106, an auxiliary storage device 107, and a processor 108. Each of these pieces of hardware is connected to each other via a bus 109 so as to be able to communicate with each other.

[0032] The input device 101 is, for example, a keyboard, a mouse, a touch panel, a physical button, etc. The display device 102 is, for example, a display, a display panel, etc.

[0033] The external I / F 103 is an interface with an external device such as a recording medium 103a. Examples of the recording medium 103a include a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), and a USB (Universal Serial Bus) memory card.

[0034] The communication I / F 104 is an interface for connecting the terminal 10 to a communication network. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily stores programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can store programs and data even when the power is turned off. The auxiliary storage device 107 is a non-volatile storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that stores programs and data. The processor 108 is a variety of arithmetic devices such as a CPU (Central Processing Unit).

[0035] 4 is an example, and the terminal 10 may have other hardware configurations. For example, the terminal 10 may have multiple auxiliary storage devices 107 and multiple processors 108, or may have various types of hardware other than the hardware shown in the figure.

[0036] <Example of functional configuration of terminal 10> An example of the functional configuration of the terminal 10 according to this embodiment is shown in Fig. 5. As shown in Fig. 5, the terminal 10 according to this embodiment has a user interface unit 201 and an index value calculation unit 202. These units are realized, for example, by processing in which one or more programs installed in the terminal 10 are executed by the processor 108. The terminal 10 according to this embodiment also has an analysis result DB 203. The analysis result DB 203 is realized, for example, by the auxiliary storage device 107. Note that the analysis result DB 203 may also be realized, for example, by a storage device (such as a database server) connected to the terminal 10 via a communication network.

[0037] The user interface unit 201 displays various screens (such as the analysis table list screen described above) on the display device 102, and accepts various operations by the user on these various screens (various input operations via the input device 101).

[0038] The index value calculation unit 202 calculates index values ​​for the analysis tables displayed on the analysis table list screen using analysis result data corresponding to the analysis tables.

[0039] The analysis result DB 203 stores analysis result data representing the analysis results of each batch. Each analysis result data represents the analysis results of the respective batch and includes, for example, items such as "batch ID," "measurement start date and time," "diagnosis start date and time," "equipment," "diagnosis system," "diagnosis unit," "quality," "comments," "metadata," and "analysis result." The "batch ID" is set to an ID (e.g., a batch index) that identifies the analysis result data or the batch corresponding to the analysis result data. The "measurement start date and time" is set to the date and time when measurement of the process variables (diagnosis parameters) of the batch started. The "diagnosis start date and time" is set to the date and time when the diagnosis of the presence or absence of an abnormality of the batch started. The "equipment" is set to an ID or name that identifies the equipment corresponding to the batch (i.e., the plant 40). The "diagnosis system" is set to an ID or name that identifies the data analysis system 20 that diagnosed the presence or absence of an abnormality of the batch. The "diagnosis unit" is set to an ID or name that identifies the diagnosis unit of the data analysis system 20 that diagnosed the presence or absence of an abnormality of the batch. "Quality" contains information indicating the abnormality diagnosis result for that batch (for example, information indicating either "normal" or "abnormal"). "Comment" contains any comment (character string) set by the person in charge of monitoring that batch. "Metadata" contains the diagnostic parameters (process variables) for that batch. "Analysis results" contains information indicating the analysis results for that batch. Examples of analysis results include the correlation coefficient between any two process variables for that batch, the frequency for each class of each process variable for that batch, and a point cloud represented by any two process variables for that batch.

[0040] The above analysis result data is acquired from the data analysis system 20 by, for example, FTP (File Transfer Protocol) or the like, and stored in the analysis result DB 203. However, using FTP is just one example, and the method of acquiring the analysis result data is not limited to this. For example, the analysis result data may be stored in the recording medium 103a or the like, and then acquired from this recording medium 103a.

[0041] <Display process of analysis table list screen> The display process of the analysis table list screen according to this embodiment will be described with reference to FIG.

[0042] First, the user interface unit 201 accepts a selection operation of one or more analysis result data to be displayed in the analysis table (especially a large number of analysis result data whose measurement start dates and times and diagnosis start dates and times fall within a certain period) from the analysis result data stored in the analysis result DB 203 (step S101). This results in the selection of one or more analysis result data to be displayed in the analysis table. The selection operation of the analysis result data is performed by the user, for example, on a data selection screen on which the analysis result data is displayed in a list.

[0043] Next, the index value calculation unit 202 calculates an index value for each analysis table represented by one or more pieces of analysis result data selected in step S101 (step S102). For example, if the analysis table is a correlation table, the index value calculation unit 202 calculates, for each analysis table, the proportion of pairs of process variables whose correlation coefficients are equal to or greater than the first threshold in that analysis table (correlation table) as an index value. To give a specific example, in the analysis table (correlation table) shown in FIG. 2, 15 correlation coefficients are equal to or greater than the first threshold of 0.8, so the proportion of pairs of process variables whose correlation coefficients are equal to or greater than the first threshold of 0.8 is 15 / 45=1 / 3. Therefore, the index value of the analysis table shown in FIG. 2 is 1 / 3.

[0044] The user interface unit 201 then displays an analysis table list screen on which each analysis table represented by one or more pieces of analysis result data selected in step S101 is displayed (step S103). At this time, the user interface unit 201 changes the display mode of the analysis table corresponding to the index value calculated in step S102. For example, the user interface unit 201 highlights, among the analysis tables on the analysis table list screen, those whose index value calculated in step S102 is equal to or greater than the second index value. Highlighting an analysis table means displaying it in a more noticeable manner than non-highlighted analysis tables, and examples of such display modes include displaying the highlighted analysis table in a noticeable color such as red, flashing the highlighted analysis table, surrounding the highlighted analysis table with a thick line, or vibrating the highlighted analysis table.

[0045] This allows users to view a large number of analysis tables at a glance, grasp the characteristics and trends of the process data, and compare analysis tables with each other. For example, they can identify analysis tables for batches where significant abnormalities or signs of abnormality are evident, and then identify the cause of the abnormality from those analysis tables.

[0046] <Supplementary information> In the above embodiment, a case where the analysis table list screen is displayed on the display of terminal 10 has been described, but this is not limiting, and as described above, the analysis table list screen may be displayed on a display provided in data analysis system 20. That is, either one or both of terminal 10 and data analysis system 20 can function as a data visualization device that visualizes a list of analysis tables. Note that when data analysis system 20 functions as a data visualization device, like terminal 10, data analysis system 20 also has a user interface unit, an index value calculation unit, and an analysis result DB.

[0047] The purpose of understanding the characteristics and trends of large amounts of complex data is not limited to identifying the cause of an abnormality in a batch process. Other purposes may include, for example, understanding the operating status of the plant 40 or understanding the degree of variability in the work performed by workers at the plant 40. However, these purposes are merely examples, and the present embodiment is not limited to any particular purpose.

[0048] <Modification> Modifications of this embodiment will be described below. The modifications described below may be used alone or in combination.

[0049] <<Variation 1>> In the above embodiment, we have described a case where analytical tables in the analytical table list screen whose index values ​​are equal to or greater than the second threshold value are highlighted, but for example, the display mode of the analytical table corresponding to the index value may be continuously changed depending on the value of the index value.

[0050] For example, when an index value can take a value between 0 and 100, inclusive, an example of an analysis table list screen in which the color of the analysis table corresponding to the index value changes continuously according to the index value is shown in FIG. 7. In the analysis table display field 2101 of the analysis table list screen 2100 shown in FIG. 7, each analysis table is displayed in a color corresponding to the index value of that analysis table. In addition, the analysis table list screen 2100 shown in FIG. 7 displays a legend 2102 that shows the continuous correspondence between the index value and the color corresponding to that value. This allows the color of the analysis table corresponding to that index value to change in a gradation according to the index value. This allows the user to grasp the characteristics and trends of the process data with higher accuracy.

[0051] <<Variation 2>> As described above, the analysis table may be a histogram, but since a histogram is a graph with the horizontal axis representing the class of a certain process variable and the vertical axis representing the frequency, a histogram may exist for each process variable for each batch. Therefore, when the analysis table is a histogram, the process variables corresponding to each histogram may be displayed selectably on the analysis table list screen.

[0052] 8, analysis table list screen 2200 displays process variable selection field 2202 for selecting a process variable corresponding to each analysis table displayed in analysis table display field 2201. In the example shown in FIG. 8, "pressure" is selected in process variable selection field 2202, and in this case, analysis table 1 to analysis table 100, which are histograms related to "pressure," are displayed in analysis table display field 2201. Note that, for example, if another process variable (e.g., "temperature") is selected in process variable selection field 2202, analysis table 1 to analysis table 100, which are histograms related to that process variable (e.g., "temperature"), are displayed in analysis table display field 2201.

[0053] <<Variation 3>> As described above, the analysis table may be a scatter diagram, but since a scatter diagram is a graph with one process variable on the vertical axis and another process variable on the horizontal axis, a scatter diagram may exist for each set of two process variables for each batch. Therefore, when the analysis table is a scatter diagram, the two process variables corresponding to each scatter diagram may be displayed selectably on the analysis table list screen.

[0054] 9, analysis table list screen 2300 displays process variable selection fields 2302 and 2303 for selecting two process variables corresponding to each analysis table displayed in analysis table display field 2301. In the example shown in Fig. 9, "pressure" is selected in process variable selection field 2302 and "temperature" is selected in process variable selection field 2303. In this case, analysis table display field 2301 displays analysis tables 1 to 100, which are scatter plots with "pressure" as the horizontal axis and "temperature" as the vertical axis. Note that, for example, if a different process variable is selected in at least one of process variable selection fields 2302 and 2303, analysis table display field 2301 displays analysis tables 1 to 100, which are scatter plots with the process variables selected in process variable selection fields 2302 and 2303, respectively, as the horizontal axis and vertical axis.

[0055] <<Variation 4>> In the above embodiment, no particular mention is made of the display order of each analysis table displayed in the analysis table display field on the analysis table list screen, but these analysis tables can be displayed in various display orders.

[0056] For example, for the same equipment and the same product (i.e., batch processes that manufacture the same product in the same plant 40), the analysis table may be displayed in chronological order (newest or oldest) as shown in Fig. 10(a). Alternatively, for the same equipment and the same product, the analysis table may be displayed in index value order (ascending or descending order of index value) as shown in Fig. 10(b).

[0057] Furthermore, for example, for batch processes of different products in the same facility (that is, for batch processes of different products in the same plant when multiple products are manufactured in the same plant 40), it is possible to display the analysis table in chronological order (newest or oldest) for each product in the order shown in Figure 10(c). Alternatively, for example, for batch processes of different products in the same facility, the analysis table may be displayed in index value order (ascending or descending order of index value) in the order shown in Figure 10(d).

[0058] The display orders shown in Figures 10(a) and (c) are suitable for displaying the analysis table list screen on the terminal 10 or the data analysis system 20. On the other hand, the display orders shown in Figures 10(b) and (d) are suitable for displaying the analysis table list screen on the data analysis system 20. However, even when the analysis table list screen is displayed on the terminal 10, the analysis tables may be displayed in the display order shown in Figure 10(b) or (d).

[0059] In addition to the display order shown in FIGS. 10(a) to (d), for example, the display order shown in FIGS. 11(a) to (c) is also possible.

[0060] For example, for batch processes of the same equipment and product, the analysis table may be displayed in chronological order (newest or oldest) for normal and abnormal conditions in the order shown in Figure 11(a). Also, for batch processes of the same equipment but different products, the analysis table may be displayed in chronological order (newest or oldest) for normal and abnormal conditions for each product in the order shown in Figure 11(b). Furthermore, for batch processes of different equipment, the analysis table may be displayed in chronological order (newest or oldest) for each piece of equipment in the order shown in Figure 11(c).

[0061] The display orders shown in Figures 11(a) and (b) are suitable for displaying the analysis table list screen in the data analysis system 20. On the other hand, the display order shown in Figure 11(c) is suitable for displaying the analysis table list screen in the terminal 10. However, even when the analysis table list screen is displayed in the terminal 10, the analysis tables may be displayed in the display order shown in Figure 11(a) or (b). Similarly, even when the analysis table list screen is displayed in the data analysis system 20, the analysis tables may be displayed in the display order shown in Figure 11(c).

[0062] <<Variation 5>> It is also possible to perform some kind of aggregation on the index values ​​of each analysis table displayed in the analysis table display field on the analysis table list screen, and display the aggregation results on the analysis table list screen.

[0063] For example, if the color of each analysis table displayed in the analysis table display area changes depending on the value of its index value, the percentage of each color may be displayed. As a specific example, if the color of the analysis table corresponding to the index value is displayed as "red," "pink," "purple," or "blue" depending on the value of the index, the percentage of each color in each analysis table may be tallied and the tallied result (e.g., "red: 50%, pink: 10%, purple: 25%, blue: 15%) may be displayed.

[0064] Furthermore, for example, when an analysis table is displayed for each normal and abnormal state as in FIG. 11(a) or (b), the above aggregation may be performed for each normal state and each abnormal state.

[0065] <Summary> As described above, in the data visualization system 1 according to this embodiment, when grasping the characteristics and trends of a large amount of complex data, the analysis results of the data are displayed in a simple display format according to the importance of the data (i.e., the value of the index value). This makes it possible to easily grasp the characteristics and trends of a large amount of complex data on a single screen.

[0066] Furthermore, the above-mentioned modified examples may be capable of switching between screens (for example, the display orders shown in Fig. 10 and Fig. 11 may be capable of being switched between), so that the screens can be switched and displayed interactively in response to user operations. This makes it possible to analyze large amounts of complex data from multiple angles.

[0067] In particular, when displaying an analysis table showing the analysis results of a batch process, multiple analysis tables (especially multiple analysis tables showing the results of analyzing multiple batch processes over a certain period of time) are displayed as thumbnails, and the display mode of the analysis table is changed depending on the value of the index value, which is a statistical quantity for the analysis results. This allows the user to check a large number of analysis tables, for example, tens to hundreds, at a glance, to understand their biases and trends, and to compare analysis tables with each other, and for example, to identify analysis tables for batches where significant abnormalities or abnormal symptoms are apparent, and to identify the cause of the abnormality from those analysis tables.

[0068] The present invention is not limited to the above-described specifically disclosed embodiments, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of symbols]

[0069] 1. Data visualization system 10 devices 20 Data Analysis System 30 Control device 40 Plants 101 Input Device 102 Display device 103 External I / F 103a Recording media 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary storage 108 processors 109 Bus 201 User Interface Section 202 Index value calculation unit 203 Analysis result DB

Claims

1. a storage unit configured to store a predetermined analysis result for the analysis target; an index value calculation unit configured to calculate a predetermined index value from the analysis result for each of one or more analysis targets selected by a user; a display unit configured to display a list of an analysis table showing the analysis results for each of the one or more analysis targets; and the analysis result is a correlation coefficient between process variables of the process to be analyzed; The index value calculation unit The method is configured to calculate, as the index value, a ratio of pairs of process variables whose correlation coefficient is equal to or greater than a predetermined second threshold value, The display unit The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; The data visualization device is configured to display a list of a correlation table as the analysis table.

2. A memory unit configured to store predetermined analysis results for an analysis target; an index value calculation unit configured to calculate a predetermined index value from the analysis result for each of one or more analysis targets selected by a user; a display unit configured to display a list of an analysis table showing the analysis results for each of the one or more analysis targets; and the analysis result is a set of values ​​between process variables of the process to be analyzed; The index value calculation unit the index value is calculated as one of a correlation coefficient, a variance, and a standard deviation of a scatter diagram represented by the analysis results, or a value obtained by combining one or more of the correlation coefficient, the variance, and the standard deviation; The display unit The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; The data visualization device is configured to display, as the analysis table, a list of the scatter plots for a pair of two process variables selected by a user.

3. The display unit 3. The data visualization device according to claim 1, wherein the data visualization device is configured to display an analysis table showing an analysis result corresponding to the index value in an emphasized display mode, depending on a comparison result between the value of the index value and one or more predetermined first threshold values.

4. The display unit 3. The data visualization device according to claim 1, wherein the analysis table showing the analysis results corresponding to the index values ​​is displayed in a display mode in which the color of the analysis table changes continuously depending on the value of the index value.

5. a storage procedure for storing predetermined analysis results for the analysis target in a storage unit; an index value calculation step of calculating a predetermined index value from the analysis results for each of one or more analysis targets selected by a user; a display step of displaying a list of an analysis table showing the analysis results for each of the one or more analysis targets; The computer executes the analysis result is a correlation coefficient between process variables of the process to be analyzed; The index value calculation procedure includes: calculating a ratio of pairs of process variables whose correlation coefficient is equal to or greater than a second predetermined threshold as the index value; The display procedure includes: The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; A data visualization method that displays a correlation table as the analysis table.

6. A storage procedure for storing predetermined analysis results for an analysis target in a storage unit; an index value calculation step of calculating a predetermined index value from the analysis results for each of one or more analysis targets selected by a user; a display step of displaying a list of an analysis table showing the analysis results for each of the one or more analysis targets; The computer executes the analysis result is a set of values ​​between process variables of the process to be analyzed; The index value calculation procedure includes: Calculating, as the index value, any one of a correlation coefficient, a variance, and a standard deviation of a scatter diagram represented by the analysis results, or a value obtained by combining one or more of the correlation coefficient, the variance, and the standard deviation; The display procedure includes: The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; A data visualization method in which the analysis table is a list of the scatter plots for a pair of two process variables selected by a user.

7. a storage procedure for storing predetermined analysis results for the analysis target in a storage unit; an index value calculation step of calculating a predetermined index value from the analysis results for each of one or more analysis targets selected by a user; a display step of displaying a list of an analysis table showing the analysis results for each of the one or more analysis targets; on the computer, the analysis result is a correlation coefficient between process variables of the process to be analyzed; The index value calculation procedure includes: calculating a ratio of pairs of process variables whose correlation coefficient is equal to or greater than a second predetermined threshold as the index value; The display procedure includes: The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; A program that displays a list of correlation tables as the analysis table.

8. A storage procedure for storing predetermined analysis results for the analysis target in a storage unit; an index value calculation step of calculating a predetermined index value from the analysis results for each of one or more analysis targets selected by a user; a display step of displaying a list of an analysis table showing the analysis results for each of the one or more analysis targets; on the computer, the analysis result is a set of values ​​between process variables of the process to be analyzed; The index value calculation procedure includes: Calculating, as the index value, any one of a correlation coefficient, a variance, and a standard deviation of a scatter diagram represented by the analysis results, or a value obtained by combining one or more of the correlation coefficient, the variance, and the standard deviation; The display procedure includes: The display mode of the analysis table showing the analysis results corresponding to the index values ​​is changed according to the index values; A program that displays, as the analysis table, a list of the scatter plots for a pair of two process variables selected by a user.

Images