JP5722371B2 - Know-how visualization device and know-how visualization method - Google Patents

Description

  Embodiments of the present invention include monitoring and control of water and sewage facilities (including water treatment facilities for treating industrial water used in industrial facilities such as steel, paper, semiconductor factories, and food processing factories). The present invention relates to a know-how visualization device used in the system and a know-how visualization method used in this device.

  As skilled operators gradually decrease, passing on know-how such as knowledge and experience of skilled operators to inexperienced operators is crucial for safe and stable operation of water and sewage facilities. It is a serious problem. In order to solve this problem, trial and error measures have been taken, such as instructing inexperienced operators from inexperienced operators in daily work, but know-how has been handed down efficiently and systematically. There is no actual situation.

  In addition, there are many cases where a sufficient number of operators cannot be secured due to financial problems. Therefore, it is required to operate the water and sewage facilities safely and stably with a small number of people.

JP 2011-186517 A

  In view of the above background, there is a demand for an apparatus capable of efficiently transmitting operation know-how to an operator who has little experience in a short period of time. In addition, in order to cope with labor saving of water and sewage facilities, there is a demand for a device that assists operators using the history of operation data obtained by the skilled operators operating the plant using the monitoring and control system of the water and sewage facilities. .

  Therefore, the purpose is to support operators by extracting operation know-how from the history of operation data of skilled operators and visualizing and displaying the extracted operation know-how to operators in the monitoring and control system of water and sewage facilities. It is an object of the present invention to provide a know-how visualization device that can be used and a know-how visualization method used in this device.

  According to the embodiment, in the know-how visualization device used in the monitoring control system that monitors and controls the water and sewage facilities, the know-how visualization device includes a narrowing unit, an extraction unit, and a display unit. The narrowing-down unit determines whether the data collected at the water and sewage facility is data for which of the processing processes at the water and sewage facility. The extraction unit obtains the history of the operation data of the operator for the determined process and the process data corresponding thereto, and determines the operation amount included in the history of the operation data from the process data. The referred state quantity is extracted, and the extracted state quantity is divided into a plurality of cells based on the manipulated variable to generate know-how visualization data. The display unit displays the know-how visualization data generated by the extraction unit as operation know-how.

It is a block diagram which shows the function structure of the monitoring control system with which the know-how visualization apparatus which concerns on this embodiment is provided. It is a block diagram which shows the function structure of the extraction part shown in FIG. It is a figure for demonstrating the clustering process by the division part shown in FIG. It is a figure for demonstrating the clustering process by the division part shown in FIG. The figure at the time of the division | segmentation number divided | segmented by the division part shown in FIG. 2 evaluated using the value of the parameter | index H by an evaluation part is shown. It is a figure which shows the example of a display of the operation know-how displayed on the display part shown in FIG. It is a figure which shows the example of a display of the operation know-how displayed on the display part shown in FIG. It is a flowchart which shows the process at the time of the know-how visualization apparatus shown in FIG. 1 displaying operation know-how. It is a figure which shows the guidance added to the matrix display displayed on the display part shown in FIG. It is a figure which shows the flowchart produced by the flowchart production part. It is a figure which shows the cell order at the time of changing the order of the state quantity of the vertical axis | shaft of a matrix display, and a horizontal axis. It is a figure which shows the cell order at the time of changing the order of the state quantity of the vertical axis | shaft of a matrix display, and a horizontal axis. It is a figure which shows the cell order at the time of changing the order of the state quantity of the vertical axis | shaft of a matrix display, and a horizontal axis. It is a figure which shows the cell order at the time of changing the order of the state quantity of the vertical axis | shaft of a matrix display, and a horizontal axis. It is a figure which shows the evaluation result about the cell order shown by FIGS. It is a figure which shows the example of a display of the operation know-how displayed on the display part shown in FIG.

  Hereinafter, embodiments will be described with reference to the drawings.

  FIG. 1 is a block diagram illustrating a functional configuration of a monitoring control system in which a know-how visualization device 10 according to the present embodiment is provided. The monitoring control system shown in FIG. 1 monitors the state of a water and sewage facility and performs control for operating the water and sewage facility safely and stably. Here, the water and sewage facilities include, for example, industrial water used in industrial facilities such as steelworks, paper mills, semiconductor manufacturing plants, and food processing plants, and water treatment facilities that treat water discharged from these industrial facilities. Is included. In addition, in FIG. 1, a water purification plant facility is described as an example of a water and sewage facility. In the water purification plant facility, for example, the pump of the raw water tank, the driving motor of the flocculant charging device, the driving unit of the discharge valve for discharging the sediment in the coagulating tank, the driving unit of the filtration device, the driving motor of the disinfectant charging device, The power source for the UV disinfection lamp and the water pump for the water purification pond are included.

  The monitoring control system includes a know-how visualization device 10, a data input / output unit 20, a control controller 30 and a database 40.

  The data input / output unit 20 collects and collects process data and other data (not shown) acquired by various devices of the water treatment plant facility monitored and controlled by the monitoring control system. Here, the process data includes raw data actually measured for each device and pseudo data obtained by simulation using computer simulation. Further, the process data is converted into a signal and transmitted to the data input / output unit 20.

  Specific process data necessary for the operation and management of water purification plant facilities include the following. When pumping raw water, the flow rate of raw water flowing through the pipe, when adding flocculant, pH before and after charging, turbidity, when distributing water, discharge pump discharge pressure, flow rate, pressure at the end of water supply, etc. It is. As described above, the process data indicates a state quantity such as a sensor measurement value for monitoring the process state.

  The data input / output unit 20 outputs the collected process data to the database 40.

  In addition, the data input / output unit 20 receives a control signal transmitted from the controller 30 to each device in the water purification plant facility based on the driving operation input by the operator, and transmits the control signal to each device in the water purification plant facility. Thereby, the process object required for operation and management of a water purification plant facility is controlled. The control signal indicates a valve opening degree for directly operating the behavior of the device to be processed, a chemical injection rate (or injection amount), and the like.

  The control controller 30 receives a driving operation from an operator. At this time, the operator refers to the display unit 13 provided in the know-how visualization device 10 and grasps the processing necessary for the water purification plant facility. The control controller 30 performs control based on the input driving operation, and outputs a control signal and driving operation data to the data input / output unit 20 and the database 40. The driving operation data indicates an operation amount related to the driving of the operator such as a flow rate and a pH target value. Note that when the operator directly operates the behavior of the device, control signals such as the valve opening degree and the chemical injection rate are also included in the operation operation data.

  The database 40 records process data output from the data input / output unit 20 and driving operation data output from the control controller 30. The database 40 records a history of past driving operation data and process data corresponding to the driving operation data. The database 40 outputs the process data and the operation data to be recorded to the know-how visualization device 10 in response to a read request from the know-how visualization device 10.

  The know-how visualization device 10 includes, for example, a CPU (Central Processing Unit), and a storage area for programs and data for the CPU to execute processing such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The know-how visualization device 10 constructs the narrowing-down unit 11 and the extraction unit 12 by causing the CPU to execute an application program. In addition, the know-how visualization device 10 includes a display unit 13.

  The narrowing-down unit 11 reads process data and driving operation data from the database 40. The narrowing-down part 11 discriminate | determines which process of the process process which comprises the water treatment plant facility about the read process data based on the object process selection input from an operator. The narrowing-down unit 11 outputs the determination result to the extraction unit 12.

  The narrowing-down unit 11 may directly capture process data from the data input / output unit 20. However, the process data and operation data stored in the database 40 are in a state of being classified and arranged. Therefore, it is possible to quickly reach the search target by fetching the process data and the driving operation data via the database 40, and the search result is also highly accurate.

  As illustrated in FIG. 2, the extraction unit 12 includes a division unit 121 and an evaluation unit 122.

  The dividing unit 121 reads past driving operation data indicated by the determination result given from the narrowing unit 11 and process data corresponding thereto from the database 40. The dividing unit 121 extracts the state quantity referred to when the operation amount included in the past driving operation data is determined by the skilled operator from the read process data. The state quantity is, for example, raw water turbidity, water temperature, pH, alkalinity, and the like. The dividing unit 121 associates the extracted state quantity with the operation amount included in the driving operation data, and performs clustering on the operation amount associated with the state quantity. By performing clustering, the dividing unit 121 groups the driving operation data having the same operation amount with those having the corresponding state amounts close to each other.

  As for the clustering method, K-means method that divides the data so that the distance of all data in the group from the group centroid is minimized, group average method that performs grouping hierarchically, single connection method, complete connection method, Ward method Centroid method, median method, M-Cut method applying graph theory, EM (Expectation Maximization) algorithm using maximum likelihood estimation, SVM (Support Vector Machine) using kernel trick, and the like may be used. By using the clustering technique, the dividing unit 121 automatically sets the upper and lower limit values of the section to be divided based on the maximum value, the minimum value, and the distance between the groups of the state quantities for each grouped driving operation data. It can be obtained quantitatively.

  3 and 4 are diagrams illustrating the clustering process. FIG. 3 shows a case where the operation amount “high injection amount” operation and the “low injection amount” operation are grouped into two based on the state amount x1. At this time, the state quantity x1 = a indicated by the broken line is calculated as the upper and lower limit values. FIG. 4 shows a case where the operation amount “high injection amount” operation and the “low injection amount” operation are grouped into four based on the state amounts x1 and x2. At this time, the state quantity x1 = a indicated by the vertical broken line is calculated as the first upper / lower limit value, and the state quantity x2 = b indicated by the horizontal broken line is calculated as the second upper / lower limit value.

  The evaluation unit 122 evaluates whether the number of divisions divided by the division unit 121 is appropriate. From the viewpoint of visualization, it is better to have a smaller number of divisions, but if the number of divisions is too small, operational know-how cannot be expressed well. Therefore, the evaluation unit 122 calculates an evaluation index for a cell indicating a division into which each state quantity is divided, and adopts the division number with the best evaluation index.

  As an evaluation index, for example, the following examples can be considered.

  First, before describing the evaluation index, signals used in this description are defined.

A set <x ₁ , x ₂ ,..., x _s , y> of s types of state quantities x _i (i = 1,..., s) and one type of operation quantity y is used as evaluation data. A clustering division number N _i (i = 1,..., S) is designated for each type of state quantity. At this time, a mapping x _i → k _i (1 ≦ k _i ≦ N _i ) from each state quantity to the cluster is obtained by clustering. A vector {K} = [k ₁ , k ₂ ,..., K _s ] that summarizes the clustering results is called a cell (where {K} is a bold letter K). In other words, the total number of cell types is

It becomes. Clustering is performed for the state quantity of each evaluation data, and the data group corresponding to the cell {K} is defined as all events. Of all the events, the frequency of data including the manipulated _variable y _[j] is Y _{[j] {K}} . The manipulated variable y takes discrete values y _[1] ,..., Y _[m] .

As an evaluation index, a probability value for each manipulated variable and H _{K} that is an index that can consider both the distribution and the bias of the probability value are used. H _{K} is obtained from the following equation.

Considering the information amount of data belonging to each cell considers the validity that each data becomes the operation amount. This is because the small amount of information given by each data is high because each data has a high validity indicating the amount of operation and does not have other information. Therefore, the evaluation unit 122 evaluates that the operation is more appropriate in the cell as the value of H _{K} is smaller.

When evaluating the number of divisions, first, the evaluation unit 122 calculates H _{K} for all cells. Then, the evaluation unit 122 adds the calculated H _{K} as shown in the following expression.

  The evaluation unit 122 calculates H for each set number of divisions while changing the setting of the number of divisions of the state quantity. The evaluation unit 122 uses the calculated H, and evaluates that the smaller the value of H, the more appropriate the number of divisions.

FIG. 5 shows an example diagram when the number of divisions divided by the dividing unit 121 is evaluated by the evaluation unit 122 using the index H. In FIG. 5, the state quantities x _{1 to} x ₄ included in the process data corresponding to the past driving operation data are clustered with the division number 2. Thereby, the raw water turbidity k1, the water temperature k2, the pH k3, and the alkalinity k4 are divided into “1: high” and “2: low”, respectively. The division result is displayed in a matrix on the display unit 13 as shown in FIG. Although such a matrix display is not performed in the extraction unit 12, FIG. 5 will be described while designating cells in the matrix display. Cell (raw water turbidity: high, water temperature: low, alkalinity: high, injection rate: high) in the matrix table shown in FIG. 5 = first manipulated variable y _[1] for cell (1, 2, 1, 1) _] Is 100, and the frequency of the second manipulated variable y _[2] is zero. The evaluation unit 122 calculates the value of H _{K} at this time as zero from the equation (2). Further, the frequency of the first manipulated variable y _[1] for the cell (2, 1, 2, 1) in the matrix table is 75, and the frequency of the second manipulated variable y _[2] is 25. The evaluation unit 122 calculates the value of H _{K} at this time as 0.244 from Equation (2). The frequencies of the first and second manipulated variables y _[1] and y _[2] for the cell (2, 2, 2, 1) in the matrix table are zero. The evaluation unit 122 calculates the value of H _{K} at this time as zero from the equation (2). The evaluation unit 122 calculates the value of H _{K} for all the cells, and then calculates H based on Expression (3). This H is an index when the number of divisions of the state quantities x _{1 to} x ₄ is two. The evaluation unit 122 also performs the above calculation for the other division numbers, and compares H calculated for each division number.

By the way, as the number of divisions increases, the number of data belonging to each cell decreases, and the average information amount per cell tends to become zero. That is, the value of the evaluation index H _{K} tends to be zero. For this reason, the evaluation index H _{K} may not be able to evaluate the number of divisions appropriate for visualization. Therefore, the evaluation unit 122 evaluates the number of divisions based on how many blank cells with no attributed operation amount data exist in the divided cells. For example, the evaluation unit 122 uses the blank degree E defined as follows as an evaluation index.

  The evaluation unit 122 evaluates that the smaller the value of the evaluation index H and the value of the blankness E, the more appropriate the number of divisions.

  The evaluation unit 122 includes state quantities such as turbidity, water temperature, pH, and alkalinity, the number of divisions determined to be optimal by evaluation, the upper and lower limit values of the divided cells, and the operation amount set for the divided cells. The know-how visualization data for visualizing the know-how is output to the display unit 13.

  The display unit 13 displays the operation know-how by, for example, matrix display based on the know-how visualization data output from the extraction unit 12.

FIG. 6 is a diagram illustrating a display example of operation know-how displayed on the display unit 13. In FIG. 6, with respect to the coagulant injection rate which is the operation amount y included in the past operation data of the plant, two state quantities x ₁ and x ₂ that affect the coagulant injection rate are pH values in the process data. And the water temperature is shown. In FIG. 6, the operation know-how regarding the state quantity pH and the water temperature that are divided into two parts is shown in a matrix display. FIG. 6 shows that when the pH is low (6.7 to 7.0), the flocculant injection rate has been operated at 21 ppm regardless of the water temperature. On the other hand, when the pH is high (7.0 to 7.7), it is indicated that the flocculant injection rate has been changed according to the water temperature.

  In addition, when the matrix display is used, operation know-how when there are two or more state quantities can be presented to the operator. FIG. 7 is a diagram illustrating a display example of operation know-how displayed on the display unit 13. In FIG. 7, operational know-how regarding four-dimensional state quantities (raw water turbidity, water temperature, pH, and alkalinity), each of which is divided into two, is shown in a matrix display. In the cell shown in FIG. 7, the operation amount is actually described.

  In this way, there is no limit on the number of dimensions of the state quantity in the matrix display. Also, the number of divisions in the section is not limited to two.

  Next, processing when the know-how visualization device 10 configured as described above displays operation know-how will be described. FIG. 8 is a flowchart showing processing when the know-how visualization device 10 according to the present embodiment displays operation know-how.

  First, the narrowing-down unit 11 determines which process in the water purification plant facility the process data read from the database 40 is (Step S81).

  The dividing unit 121 in the extracting unit 12 reads the past driving operation data and the process data corresponding thereto for the processing process determined by the narrowing unit 11 from the database 40 (step S82). The dividing unit 121 determines the number of divisions for the state quantity (step S83), and executes clustering for each state quantity so that the grouping is performed with the determined number of divisions (step S84). Thereby, the state quantity is divided according to the operation amount included in the driving operation data, and the upper and lower limit values of the divided section are obtained.

  The evaluation unit 122 of the extraction unit 12 evaluates the number of divisions using the value of the evaluation index H and the value of the blankness E (Step S85). The dividing unit 121 determines whether or not Steps S83 to S85 have been executed a predetermined number of times set in advance (Step S86). If not executed (No in Step S86), the process proceeds to Step S83. The processes in steps S83 to S85 are repeated.

  On the other hand, when the process is executed a predetermined number of times set in advance (Yes in step S86), the dividing unit 121 determines the number of divisions having the smallest value of the evaluation index H and the value of the blankness E from the evaluated number of divisions. Is determined (step S87). The dividing unit 121 outputs know-how visualization data such as the state quantity, the number of divisions determined to be optimal by evaluation, the upper and lower limit values of the divided cells, and the operation amount set to the divided cells to the display unit 13. (Step S88).

  The display unit 13 displays operational know-how based on the know-how visualization data (step S89).

  As described above, in the present embodiment, the narrowing-down unit 11 determines which process the read process data is for. When the extraction unit 12 determines the operation amount by classifying and organizing the operation amount and the state amount included in the history of the driving operation data stored in the database 40 and the process data corresponding thereto in the determined process. The state quantity referred to in Fig. 1, the number of divisions of the optimum state quantity for specifying the operation quantity, the upper and lower limit values of the divided cells, the operation quantity set for each cell, etc. Create know-how visualization data by extracting from process data corresponding to The display unit 13 displays the know-how visualization data as operation know-how. As a result, the know-how visualization device 10 can acquire operation know-how from the history of driving operation data, and can support the operator with the acquired operation know-how. Further, the know-how visualization device 10 can systematically collect and visualize the operation know-how, so that the operation know-how can be efficiently transmitted to an operator who has little experience in a short period of time.

  Note that the know-how visualization device 10 has a printing unit for printing data output from the extraction unit 12 instead of the display unit 13 or an output unit for outputting data output from the extraction unit 12 to the outside. May be provided.

The extraction unit 12 may include a guidance adding unit. The guidance adding unit issues an instruction to add guidance to a position corresponding to the current state quantity in the matrix display displayed on the display unit 13. FIG. 9 is a diagram illustrating an example of a black triangle that is guidance added to the matrix display. In the matrix display shown in FIG. 6 and FIG. 7, when the number of divisions of each state quantity is N _i (i = 1,..., S) for s types of state quantities, the number of cells in the matrix is 1)
It becomes. Therefore, in the case of complicated operation know-how, it is difficult to grasp a cell corresponding to the current state quantity during operation from a huge number of cells.

  As shown in FIG. 9, by adding guidance to the matrix display, the operator can grasp at a glance the cell corresponding to the current state quantity during driving.

  In addition, although the guidance addition part showed as an example the case where guidance as shown in FIG. 9 is added to the display part 13, it is not limited to this. Any other means may be used as long as the information regarding the current state quantity is added to the matrix display to facilitate the understanding of the operator.

  The extraction unit 12 may further include a flowchart creation unit. The flowchart creation unit creates a flowchart based on the know-how visualization data created by the dividing unit 121 and the evaluation unit 122. At this time, the flowchart creation unit creates the flowchart so that the number of judgments is as small as possible with reference to the created know-how visualization data. FIG. 10 shows a flowchart created based on FIG. The display unit 13 displays the created flowchart.

  In order to systematically convey the operation know-how of skilled operators to inexperienced operators, it is necessary to maintain a manual. On the other hand, in the matrix display shown in FIG. 6 and FIG. 7, it is difficult for an inexperienced operator to grasp the process of thinking of the skilled operator.

  By creating the flowchart shown in FIG. 10 and displaying it on the display unit 13, the know-how visualization device 10 allows the skilled operator to obtain the know-how of plant operation based on past operation data related to fluctuations between data. It is possible to display in accordance with the process of thinking when judging. Since the thought process when determining the operation amount from the state quantity related to the driving operation is displayed in order, an inexperienced operator can grasp the thought process when the skilled operator judges the operation amount. It becomes possible.

  The extraction unit 12 may include an abnormality determination unit. The abnormality determination unit determines whether or not the operation amount for the cell corresponding to the current state amount exists in the past driving operation data. If it exists, the abnormality determination unit waits for an operation from the operator. On the other hand, if it does not exist, the abnormality determination unit determines that the situation is abnormal and notifies the operator that the situation is abnormal. This notification includes a warning indicating abnormality and a display for prompting attention.

  For example, for each cell in the matrix display shown in FIGS. 6 and 7, the corresponding operation amount does not always exist in the past driving operation data. Therefore, when the operation amount for the cell corresponding to the current state amount does not exist in the past operation operation data, the abnormality determination unit determines that the operation state of the plant has transitioned to a state where the plant has not been operated so far. judge. That is, the abnormality determination unit determines that an abnormality has occurred in the plant. The abnormality determination unit notifies the operator that there is an abnormal situation because it is necessary to operate the plant as an abnormal situation.

  In this way, by notifying that there is an abnormal situation, the operator can determine whether or not it is necessary to operate away from the assistance of the know-how visualization device.

  Note that the abnormality determination unit is in an abnormal situation when the operation amount currently given to the controller as a driving operation and the cell operation amount corresponding to the current state amount of the matrix display are more than a certain threshold. You may make it judge that there exists.

  The extraction unit 12 may further include a matrix rearrangement unit. The matrix rearrangement unit is arranged in the order of the vertical axis and horizontal axis of the matrix that provides the most easily viewable matrix display for the number of divisions determined to be optimal by the evaluation unit 122 and the upper and lower limit values acquired by the division unit 121. Is calculated.

  In order to automatically calculate the order of the vertical and horizontal axes of the matrix, the matrix rearrangement unit introduces an evaluation index for evaluating the order of the horizontal and vertical axes of the matrix. Examples of the evaluation index used here include the number of divided regions and the maximum area value. The area division number indicates the number of areas into which the matrix display is divided, with a set of cells in which adjacent cells have the same operation amount as one area. It is assumed that a smaller value is appropriate for the number of area divisions. The area maximum value indicates the number of adjacent cells having the same operation amount. It is assumed that a larger area maximum value is appropriate. The matrix rearrangement unit calculates an evaluation index every time the order of the vertical axis and the horizontal axis of the matrix is rearranged, and adopts the order of the vertical axis and the horizontal axis of the matrix with the best evaluation index.

  For example, in FIGS. 11 to 14, the two-dimensional state quantities are divided by the number of divisions 2, and the order of the state quantities on the vertical and horizontal axes of the matrix display in which the upper and lower limit values of the divided sections are the same is changed. It is a figure which shows the cell order (1)-(4) at the time. FIG. 15 is a diagram showing the evaluation indices of the cell orders (1) to (4) shown in FIGS. The matrix rearrangement unit determines that the cell order (1) shown in FIG. 11 having the smallest number of area divisions and the largest area value is the best order of the vertical and horizontal axes of the matrix. . The matrix rearrangement unit includes information on the best cell order in the know-how visualization data and outputs the information to the display unit 13.

  Even if the number of divisions and the upper and lower limit values of the divided sections are the same, the visibility of the matrix display changes depending on the order of the state quantities arranged on the horizontal and vertical axes of the matrix. Therefore, the know-how visualization device uses the matrix rearrangement unit to rearrange the order of the vertical and horizontal axes of the matrix in the optimal order with reference to the evaluation index, thereby making it easier for the operator to determine the driving operation. I try to make it.

  Moreover, the display part 13 may display know-how visualization data by the graph display by the contour line shown in FIG. 16, for example. In FIG. 16, the horizontal axis represents the pH state quantity, the vertical axis represents the water temperature state quantity, and the level of the manipulated variable at that time is expressed by shading. According to FIG. 16, it can be seen that when the water temperature is low and the pH is high, the coagulant injection rate may be lowered.

  Therefore, according to the know-how visualization device according to the present embodiment, in the monitoring and control system of the water and sewage facility, the operation know-how is extracted from the history of the operation data of the skilled operator, and the extracted operation know-how is visualized to the operator. Can be displayed. As a result, the operator can confirm the know-how of plant operation and operate and manage the water purification plant facility safely, securely and efficiently.

  Although the embodiment of the present invention has been described, this embodiment is presented as an example and is not intended to limit the scope of the invention. This embodiment can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. This embodiment and its modifications are included in the scope of the present invention and the gist thereof, and are also included in the invention described in the claims and the equivalent scope thereof.

  DESCRIPTION OF SYMBOLS 10 ... Know-how visualization apparatus, 11 ... Narrowing part, 12 ... Extraction part, 121 ... Dividing part, 122 ... Evaluation part, 13 ... Display part, 20 ... Data input / output part, 30 ... Controller for control, 40 ... Database

Claims (12)

In the know-how visualization device used in the monitoring and control system that monitors and controls water and sewage facilities,
A narrowing-down unit for determining which data is collected from the water and sewage facilities and which is a process among the treatment processes in the water and sewage facilities,
A state referred to when the history of the operation data of the operator for the determined process and the process data corresponding thereto are acquired and the operation amount included in the history of the operation data is determined from the process data. An extraction unit that extracts know-how visualization data by extracting an amount and dividing the extracted state amount into a plurality of cells based on the operation amount;
A display unit for displaying the know-how visualization data generated by the extraction unit as operation know-how ,
The extraction unit includes:
A dividing unit that extracts the state quantity from the acquired process data, divides the extracted state quantity into a plurality of cells based on the operation quantity, and obtains upper and lower limit values of the cells to be divided;
It is determined whether or not the number of divisions of the plurality of cells is appropriate using a preset index, the number of divisions determined to be most appropriate, the upper and lower limit values acquired for the number of divisions, the state quantity And an evaluation unit that outputs the operation amount set in the cell to the display unit as the know-how visualization data;
Know-how visualization device equipped with . The display unit displays the know-how visualization data in a matrix display,
The extraction unit includes:
Wherein the matrix display, the current so as to add the guidance to the position corresponding to the state quantity, expertise visualization apparatus according to claim 1, further comprising a guidance adding unit instructs to the display portion of the process. The extraction unit includes:
Based on the know-how visualization data, a flowchart creation unit that creates a flowchart so that the number of judgments is as small as possible,
Wherein the display unit, knowledge visualization device according to claim 1, wherein displaying the flowchart. The extraction unit includes:
When the operation amount corresponding to the current state amount of the process does not exist in the acquired operation operation data history, an abnormality is determined that an abnormality has occurred, and an abnormality has been displayed on the display unit. expertise visualization device according to claim 1, further comprising a determination unit. The display unit displays the know-how visualization data in a matrix display,
The extraction unit includes:
A matrix rearrangement unit that evaluates the display order of the cells in the matrix display using a second index for evaluating visibility, and changes the arrangement of the cells so that the evaluation becomes the highest display order. The know-how visualization device according to claim 1 provided.   The know-how visualization apparatus according to claim 1, wherein the display unit displays the know-how visualization data in a graph with contour lines. In the know-how visualization method used in monitoring and control systems that monitor and control water and sewage facilities,
The upper and lower water facilities acquired by the data is to determine the data for any process of the processing process in the water and wastewater facilities,
Obtaining a history of the operation data of the operator for the determined process and process data corresponding thereto,
From the acquired process data, extract the state quantity referred to when determining the operation amount included in the history of the driving operation data,
Dividing the extracted state quantity into a plurality of cells based on the manipulated variable ;
Obtain the upper and lower limit values of the cell to be divided,
Judging whether the number of divisions of the plurality of cells is appropriate using a preset index,
The number of divisions determined to be the most appropriate, the upper and lower limit values acquired for the number of divisions, the state quantity, and the operation quantity set in the cell are generated as know-how visualization data,
A know-how visualization method for displaying the generated know-how visualization data as operation know-how. The previous Symbol operational know-how, displayed in the matrix display,
The know-how visualization method according to claim 7 , wherein guidance is added to a position corresponding to a current state quantity of the process in the matrix display. Based on the know-how visualization data, create a flowchart so that the number of judgments is as small as possible,
The know-how visualization method according to claim 7 , wherein the created flowchart is displayed. When the operation amount corresponding to the current state amount of the process does not exist in the history of the acquired driving operation data, it is determined that an abnormality has occurred,
The know-how visualization method according to claim 7 , wherein an indication that an abnormality has occurred is displayed. When displaying the know-how visualization data in a matrix display, the display order of the cells in the matrix display is evaluated using the second index for evaluating the visibility so that the evaluation order becomes the highest display order. The know-how visualization method according to claim 7 , wherein the arrangement of the cells is changed. The know-how visualization method according to claim 7 , wherein the acquired know-how visualization data is displayed in a graph with contour lines.

Images