Data visualization device, data visualization method, and program

Abstract

To make it possible to grasp a degree of a variant of a value of each of variables in a parallel coordinates plot.SOLUTION: A data visualization system in accordance with an embodiment includes a first calculation unit that calculates a variation coefficient of a value of each of variables of multivariate data that is an object of visualization, a normalization unit that normalizes the value of a variable to a predetermined scale for each variable, a second calculation unit that calculates a correction value, which represents a value obtained by multiplying a normalized value of the variable by the variation coefficient of the variable, for each variable, and a visualization unit that visualizes the multivariate data as a parallel coordinates plot by using the correction value for each of the variables.SELECTED DRAWING: Figure 7

Description

[Technical Field]

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

[0002] A graph called a parallel coordinate plot is known as one of the statistical graphs useful for visualizing multivariate data. Furthermore, technologies related to parallel coordinate plots are known, for example, as described in Patent Documents 1 to 6.

[0003] To examine relationships between variables in a parallel coordinates plot, it is common to use an interactive technique called brushed highlighting. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6621124 [Patent Document 2] Patent No. 6549174 [Patent Document 3] Patent No. 6661500 [Patent Document 4] Patent No. 5392635 [Patent Document 5] Patent No. 4155363 [Patent Document 6] Patent No. 4819273 Summary of the Invention [Problem to be solved by the invention]

[0005] However, it is difficult to simultaneously grasp the degree of variation in the values ​​of each variable using only the interactive operation called brushed highlighting.

[0006] An embodiment of the present invention has been made in view of the above points, and aims to make it possible to grasp the degree of variation in the values ​​of each variable in a parallel coordinate plot. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, a data visualization device according to one embodiment includes a first calculation unit configured to calculate, for each variable of multivariate data to be visualized, a coefficient of variation of the value of the variable; a normalization unit configured to normalize, for each variable, the value of the variable to a predetermined scale; a second calculation unit configured to calculate, for each variable, a correction value representing a value obtained by multiplying the normalized value of the variable by the coefficient of variation of the variable; and a visualization unit configured to visualize the multivariate data as a parallel coordinate plot using the correction value for each variable. [Effects of the Invention]

[0008] The degree of variation in the values ​​of each variable can be understood in a parallel coordinate plot. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of a parallel coordinate plot. [Figure 2] FIG. 10 is a diagram showing an example in which one piece of data is selected in a parallel coordinate plot. [Figure 3] 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 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of the data visualization device according to the present embodiment. [Figure 5] FIG. 2 is a diagram illustrating an example of a functional configuration of the data visualization device according to the present embodiment. [Figure 6] 10 is a flowchart illustrating an example of a parallel coordinate plot display process according to the present embodiment. [Figure 7] FIG. 10 is a diagram showing an example of a parallel coordinate plot after data correction. [Figure 8]FIG. 10 is a diagram showing an example in which one piece of data is selected in a parallel coordinate plot after data correction. DETAILED DESCRIPTION OF THE INVENTION

[0010] An embodiment of the present invention will now be described. In this embodiment, as an example, a case will be described in which performance data such as operation data and process data acquired from a plant are visualized as a parallel coordinate plot.

[0011] Here, the actual data such as operation data and process data are expressed as variables x n (1≦n≦N, N is the total number of variables), variable x at time t n Actual value of X n (t), then X(t) = (X1(t), ,X N In the following, the performance data X(t) is assigned an index i in ascending order of time t, and the i-th performance data is represented as X (i) =(i,t (i) ,X1 (i) ,···,X N (i) ) Specific examples of variables include speed, temperature, pressure, torque, flow rate, concentration, and command values ​​for manipulable variables. Such variables are called, for example, process variables.

[0012] However, targeting performance data such as operation data and process data acquired from a plant is just one example, and this embodiment can target any multivariate data.

[0013] <Parallel coordinate plot> Here, we will explain the conventional parallel coordinate plot. In a parallel coordinate plot, the coordinate axes of each variable are arranged vertically in parallel, and the actual values ​​of each variable are plotted so that the minimum value of that variable is at the bottom and the maximum value is at the top, and the actual values ​​on adjacent coordinate axes are connected by lines for the same actual data.

[0014] An example of a parallel coordinate plot is shown in Fig. 1. In the parallel coordinate plot 1000 shown in Fig. 1, "d_index" represents the index i of the performance data, and "t" represents the time t of the performance data. (i) The coordinate axis of "day", which indicates the day included in the above, is arranged from the left, followed by the coordinate axes of each variable, "Speed ​​command value 1 (rpm)", "Actual speed value 1 (rpm)", "Actual torque value 1 (%)", "Pressure 1 [MPa]", "Pressure 2 [MPa]", "Actual speed value 2 (%)", "Actual torque value 2 (%)", "Pressure 3 [MPa]", "Pressure 4 [MPa]", "Speed ​​command value 3 (rpm)", "Actual speed value 3 (rpm)", "Actual torque value (%)", "Pressure 5 [MPa]", "Pressure 6 [MPa]", and "Actual speed value 4 (rpm)", which are arranged from the left.

[0015] In a parallel coordinate plot, one broken line connecting the performance values ​​on adjacent coordinate axes with a line segment represents one piece of performance data. For example, in the parallel coordinate plot 1000 shown in Fig. 1, the broken line 1100 shown in Fig. 2 represents one piece of performance data (specifically, the performance data with d_index of "750").

[0016] A parallel coordinate plot is useful because it can display the coordinate axes of all variables on a single screen, allowing all performance data to be visualized simultaneously. It is also useful because it allows direct understanding of the relationship between variables on two adjacent coordinate axes and indirect understanding of the relationship between variables on two non-adjacent coordinate axes. However, it is difficult to grasp the degree of variation in the performance values ​​of each variable (e.g., the degree of an index representing the degree of variation, such as variance). For example, when comparing the degree of variation between the performance values ​​of two variables in the parallel coordinate plot 1000 shown in FIG. 1, it is difficult to determine which has a greater degree of variation. To give a specific example, it is difficult to determine which has a greater degree of variation: the performance value of "actual torque value 1 (%)" or the performance value of "actual torque value 2 (%)."

[0017] Therefore, below we will explain a data visualization system 1 that corrects the actual values ​​of each variable contained in performance data, so that when visualized as a parallel coordinate plot, the degree of variation in the actual values ​​of each variable can be simultaneously grasped between variables in the parallel coordinate plot.

[0018] <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. 3. As shown in Fig. 3, the data visualization system 1 according to this embodiment includes a data visualization device 10, a data collection device 20, a control device 30, and a plant 40. The data visualization device 10 and the data collection device 20 are connected to each other so as to be able to communicate with each other via an arbitrary communication network. Similarly, the data collection device 20 and the control device 30 are connected to each other via an arbitrary communication network, and the control device 30 and the plant 40 are connected to each other via an arbitrary communication network.

[0019] The data visualization device 10 acquires performance data from the data collection device 20, and visualizes all or part of the performance data as a parallel coordinate plot.

[0020] The data collection device 20 collects performance data from the control device 30. The data collection device 20 may not only collect performance data from the control device 30, but may also, for example, use the performance data to perform abnormality diagnosis (or abnormality detection) of the plant 40. Such abnormality diagnosis (or abnormality detection) can be realized by a known method such as multi-variate statistical process control (MSPC).

[0021] The control device 30 acquires actual values ​​of various variables from the plant 40 and creates actual data including these actual values. The control device 30 also uses each actual value to control the plant 40. An example of the control device 30 is a programmable logic controller (PLC).

[0022] The plant 40 is equipment or facilities that execute various processes. Specific examples of the plant 40 include a petrochemical plant, a steel plant, a food plant, and the like.

[0023] 3 is just an example, and other configurations may be used. For example, the data visualization device 10 and the data collection device 20 may be integrated into one unit.

[0024] <Example of hardware configuration of data visualization device 10> An example of the hardware configuration of a data visualization device 10 according to this embodiment is shown in Fig. 4. As shown in Fig. 4, the data visualization device 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.

[0025] 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.

[0026] 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.

[0027] The communication I / F 104 is an interface for connecting the data visualization device 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).

[0028] 4 is an example, and the data visualization device 10 may have other hardware configurations. For example, the data visualization device 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.

[0029] <Example of functional configuration of data visualization device 10> FIG. 5 shows an example of the functional configuration of the data visualization device 10 according to this embodiment. As shown in FIG. 5, the data visualization device 10 according to this embodiment includes an acquisition unit 201, a correction unit 202, and a visualization unit 203. These units are realized, for example, by a processor 108 or the like executing one or more programs installed in the data visualization device 10. The data visualization device 10 according to this embodiment also includes a performance data DB 204. This DB (database) is realized, for example, by the auxiliary storage device 107 or the like. Note that the performance data DB 204 may be realized, for example, by a storage device (such as a database server) connected to the data visualization device 10 via a communication network.

[0030] The acquisition unit 201 acquires one or more pieces of performance data to be visualized from the performance data DB 204 .

[0031] The correction unit 202 performs correction on one or more pieces of performance data acquired by the acquisition unit 201 so that when the performance data is visualized as a parallel coordinate plot, the degree of variation in the performance values ​​of each variable can be simultaneously grasped. More specifically, the correction unit 202 calculates a statistic called a coefficient of variation for each variable of the one or more pieces of performance data acquired by the acquisition unit 201, normalizes the performance value of the variable, and then multiplies the performance value of the variable by the coefficient of variation of the variable. This makes it possible to simultaneously grasp the degree of variation in the performance values ​​of each variable when the corrected pieces of performance data are visualized as a parallel coordinate plot.

[0032] The visualization unit 203 visualizes each piece of performance data corrected by the correction unit 202 as a parallel coordinate plot.

[0033] The performance data DB 204 stores performance data acquired from the data collection device 20. Hereinafter, the set of performance data stored in the performance data DB 204 is referred to as E={X (i) =(i,t (i) ,X1 (i) ,···,X N (i) )|i=1, ,|E|}. I is the number of pieces of performance data stored in the performance data DB 204. Note that the performance data may be acquired from the data collecting device 20 via a communication network, or may be acquired by first saving the data from the data collecting device 20 in a recording medium 103a or the like and then reading it from the recording medium 103a.

[0034] <Parallel coordinate plot display processing> The following describes, with reference to FIG. 6, the process of displaying a parallel coordinate plot that allows the degree of variation in the performance values ​​of each variable to be simultaneously grasped between variables when performance data is visualized.

[0035] First, the acquisition unit 201 acquires one or more pieces of performance data to be visualized from the performance data DB 204 (step S101). In the following, {X (i) =(i,t(i) ,X1 (i) ,···,X N (i) )|i=1, ,I}⊂E is acquired. Note that the performance data to be visualized may be, for example, performance data within a period specified by a user or the like, performance data selected by a user or the like, or all performance data stored in the performance data DB 204.

[0036] Next, the correction unit 202 calculates the performance data X obtained in step S101. (i) variable x n For each variable, a statistic called the coefficient of variation is calculated (step S102). n The coefficient of variation corresponding to a n Then, the correction unit 202 calculates a n =σ n / μ n The coefficient of variation a n where σ n is X n (1) ,···,X n (I) standard deviation of μ n is X n (1) ,···,X n (I) This gives the average of the coefficient of variation a n is calculated.

[0037] Next, the correction unit 202 calculates the performance data X obtained in step S101. (i) Actual value X included in n (i) (n=1, . . . , N) (step S103). For example, the correction unit 202 normalizes each performance value X n (i) (n=1, ,N) is normalized to be between -1.0 and 1.0. However, this is just an example, and it may be normalized to be between 0 and 1.0. As a result, for n=1, ,N, each performance value X n (i)is normalized to [-1,1] (or [0,1]). n (i) is normalized to [-1,1], and the normalized actual value is Y n (i) It is expressed as:

[0038] Note that X with respect to i n (i) The maximum value of X n,max , X with respect to i n (i) The minimum value of X n,min , the upper limit of the normalized actual value is Y max , bottom Y min Then, Y n (i) =(X n (i) -X n,min ) / (X n,max -X n,min )×(Y max -Y min )+Y min Actual value X n (i) For example, the actual value X n (i) If you normalize to [-1,1], then Y max =1, Y min =-1 and normalize it using the above formula.

[0039] Next, the correction unit 202 calculates the normalized performance value Y obtained in step S103. n (i) Coefficient of variation a n Specifically, the correction unit 202 multiplies the result by a for n=1, . . . , N and i=1, . . . , I (step S104). n ×Y n (i) Calculate Z n (i) =a n ×Y n (i) This calculates the corrected actual data Z for i=1,...,I. (i) =(i,t (i) ,Z1 (i),···,Z N (i) ) is obtained.

[0040] Then, the visualization unit 203 visualizes the corrected performance data Z obtained in step S104. (i) are visualized as parallel coordinate plots (step S105). n (i) to the variable x n The actual value Z is plotted on the adjacent axis. n (i) and Z n' (i) By connecting these with a line segment, the actual data Z (i) The line corresponding to the actual data Z is visualized. (i) i and t included in (i) The corrected performance data Z (i) A parallel coordinate plot is obtained in which a polygonal line corresponding to the above is plotted. This parallel coordinate plot is displayed on the display device 102, such as a display.

[0041] Here, the corrected actual data Z (i) An example of a parallel coordinate plot visualizing (i=1, , I) is shown in FIG. 7. In the parallel coordinate plot 2000 shown in FIG. 7, “d_index” represents the index i of the performance data, and “time t” represents the time of the performance data. (i) The coordinate axis of "day", which indicates the day included in the above, is arranged from the left, followed by the coordinate axes of each variable, "Speed ​​command value 1 (rpm)", "Actual speed value 1 (rpm)", "Actual torque value 1 (%)", "Pressure 1 [MPa]", "Pressure 2 [MPa]", "Actual speed value 2 (%)", "Actual torque value 2 (%)", "Pressure 3 [MPa]", "Pressure 4 [MPa]", "Speed ​​command value 3 (rpm)", "Actual speed value 3 (rpm)", "Actual torque value (%)", "Pressure 5 [MPa]", "Pressure 6 [MPa]", and "Actual speed value 4 (rpm)", which are arranged from the left.

[0042] 7, it is possible to easily and instantly grasp the degree of variation in the actual values ​​of the variables simultaneously. For example, it is possible to easily and instantly grasp that the degree of variation in the actual value of "actual torque value 2 (%)" is greater than the actual value of "actual torque value 1 (%)."

[0043] In the parallel coordinate plot 2000 shown in Fig. 7, one polygonal line connecting the performance values ​​on adjacent coordinate axes with a line segment represents one piece of performance data. For example, the polygonal line 2100 shown in Fig. 8 represents one piece of performance data (specifically, the performance data with d_index of "800").

[0044] <Summary> As described above, when visualizing performance data as a parallel coordinate plot, the data visualization device 10 according to this embodiment focuses on the statistics of performance values ​​for each variable and uses the statistics to perform a correction to adjust the scale of the performance values ​​for each variable. As a result, when visualizing the corrected performance data as a parallel coordinate plot, it becomes possible to simultaneously, easily, and instantly grasp the degree of variation in the performance values ​​of each variable. Therefore, for example, in an anomaly cause analysis of a plant 40, it becomes easy to perform an analysis such as determining that a variable with a larger degree of variation than other variables is more likely to be an anomaly cause.

[0045] In the above embodiment, the case where the corrected performance data is visualized as a parallel coordinate plot has been described. However, for example, some processing may be performed using the corrected performance data (for example, processing to identify a variable whose degree of variation exceeds a threshold as an abnormality factor variable and control equipment in the plant 40 based on the identification result, etc.).

[0046] 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]

[0047] 1. Data visualization system 10 Data visualization device 20 Data Collection Equipment 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 Acquisition Department 202 Correction Unit 203 Visualization section 204 Performance Data DB

Claims

1. a first calculation unit configured to calculate, for each variable of multivariate data to be visualized, a coefficient of variation of the values ​​of the variable; a normalization unit configured for each of the variables to normalize the value of the variable to a predetermined scale; a second calculation unit configured to calculate, for each of the variables, a correction value representing a value obtained by multiplying the normalized value of the variable by a coefficient of variation of the variable; a visualization unit configured to visualize the multivariate data as a parallel coordinate plot using the corrected values ​​for each of the variables; A data visualization device having:

2. The first calculation unit The data visualization device according to claim 1 , wherein the data visualization device is configured to calculate a quotient obtained by dividing the standard deviation of the values ​​of the variable by the mean of the values ​​of the variable as the coefficient of variation of the variable.

3. The first calculation unit The variables of the multivariate data to be visualized are expressed as x ｎ (n=1,...,N, N is the total number of variables), the i-th (i=1,...,I, I is the number of multivariate data to be visualized) multivariate data variable x ｎ The value of X ｎ （ｉ） In this case, the variable x ｎ For each i, ｎ （ｉ） Standard deviation σ ｎ X with respect to i ｎ （ｉ） The average μ ｎ The quotient obtained by dividing by the variable x ｎ Coefficient of variation a ｎ The data visualization device according to claim 2 , wherein the data visualization device is configured to calculate the following:

4. The normalization unit The variable x ｎ For each variable x ｎ The value of X ｎ （ｉ） is normalized to a predetermined scale, Y ｎ （ｉ） is configured to calculate The second calculation unit The variable x ｎ For each variable x ｎ The normalized value Y ｎ （ｉ） The coefficient of variation a ｎ The correction value Z multiplied by ｎ （ｉ） The data visualization device according to claim 3 , configured to calculate:

5. The visualization unit The correction value Z ｎ （ｉ） the variable x ｎ 5. The data visualization device according to claim 4, wherein the data visualization device is configured to visualize the multivariate data as a parallel coordinate plot by plotting the data on the coordinate axes of i and connecting points plotted on adjacent coordinate axes for the same i with line segments.

6. The normalization unit The data visualization device according to claim 1 , wherein the data visualization device is configured to normalize the values ​​of the variables to a scale of −1 to 1 or a scale of 0 to 1.

7. a first calculation step of calculating a coefficient of variation of values ​​of each variable of multivariate data to be visualized; for each said variable, a normalization procedure for normalizing the values ​​of said variable to a predetermined scale; a second calculation step of calculating, for each of the variables, a correction value representing a value obtained by multiplying the normalized value of the variable by a coefficient of variation of the variable; a visualization step of visualizing the multivariate data as a parallel coordinate plot using the corrected values ​​for each of the variables; A computer-implemented data visualization method.

8. a first calculation step of calculating a coefficient of variation of values ​​of each variable of multivariate data to be visualized; for each said variable, a normalization procedure for normalizing the values ​​of said variable to a predetermined scale; a second calculation step of calculating, for each of the variables, a correction value representing a value obtained by multiplying the normalized value of the variable by a coefficient of variation of the variable; a visualization step of visualizing the multivariate data as a parallel coordinate plot using the corrected values ​​for each of the variables; A program that causes a computer to execute the following.

Images