Monitoring and Control Equipment

Abstract

The present invention relates to a monitoring control device capable of improving the accuracy of maintenance of a monitoring target. The monitoring control device comprises: a relationship definition unit that defines, for a plurality of monitoring items, the relationships between the monitoring items; a related model management database for using a plurality of related monitoring items as related models and manages a plurality of related models; a monitoring data management database for managing the monitoring data of the plurality of monitoring items; a causal relationship calculation unit that, when the occurrence of an abnormality is detected in at least one of the plurality of monitoring items, calculates with which of the plurality of related models the abnormality occurrence has a causal relationship, such calculation being on the basis of the plurality of related models managed by the related model management database and the monitoring data managed by the monitoring data management database; and a cause identification unit that identifies the cause of the abnormality occurrence on the basis of the monitoring item that has a causal relationship.

Description

[Technical Field]

[0001] The present disclosure relates to a monitoring control device, and more particularly to a monitoring control device that monitors a plant such as a water treatment plant. [Background technology]

[0002] In recent years, mechanisms are being developed for monitoring systems in various plants, including water treatment plants, that, when an abnormality occurs, estimate the causal relationship of the abnormality and provide information to plant workers.

[0003] For example, Patent Document 1 discloses a technology that defines correlations between tags of field devices and other field devices, such as the upstream and downstream positional relationships of piping arranged within a plant, to define potential causal relationships, and then constructs a causal relationship model from process data using a Bayesian network.

[0004] The constructed causal model is converted into a format equivalent to a quality management matrix (QMM) in the analysis section and presented. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2022-115643 Summary of the Invention [Problem to be solved by the invention]

[0006] In Patent Document 1, the causal relationships are identified by simply defining the association between tags of a field device and another field device, such as the upstream and downstream positional relationship of a pipe, and there is a problem in that the causal relationships that can be identified are limited.

[0007] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a monitoring control device that does not limit the causal relationships between identifiable monitoring items and can improve the accuracy of maintenance of monitored objects. [Means for solving the problem]

[0008] A monitoring control device according to the present disclosure is a monitoring control device that monitors a plurality of monitoring items that are monitoring targets, and includes: an association definition unit that defines associations between the plurality of monitoring items; an association model management database that manages the plurality of association models, with the plurality of associated monitoring items defined in the association definition unit as association models; a monitoring data management database that manages monitoring data of the plurality of monitoring items; a causal relationship calculation unit that, when an abnormality is detected in at least one of the plurality of monitoring items, calculates which monitoring item of the plurality of associated models has a causal relationship with the abnormality, based on the plurality of associated models managed in the association model management database and the monitoring data managed in the monitoring data management database; and a cause identification unit that identifies a cause of the abnormality, based on the monitoring item with the causal relationship calculated by the causal relationship calculation unit, wherein the causal relationship calculation unit calculates the monitoring item with the causal relationship with the abnormality based on a time-series change in the monitoring data before and after the abnormality occurrence, and the association definition unit determines, as the associations between the monitoring items, The monitoring and control device has a plurality of sensors. Monitoring and control systems Manage plant equipment Define system relationships between the facility management system. [Effects of the Invention]

[0009] According to the monitoring control device of the present disclosure, it is possible to calculate, based on multiple related models and monitoring data, which monitoring item of multiple related models the occurrence of an abnormality is causally related to, and to identify the cause of the abnormality based on the monitoring item with the causal relationship, so that the causal relationships between the monitoring items that can be identified are not limited, thereby improving the accuracy of maintenance of the monitored object. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a monitoring control device according to the present disclosure; [Figure 2] 1 is a diagram illustrating an example of a monitoring item information management DB of a monitoring control device according to the present disclosure. [Figure 3] 1 is a diagram illustrating an example of a monitoring data management DB of a monitoring control device according to the present disclosure. FIG. [Figure 4] 1 is a diagram illustrating an example of an association model between monitoring items defined in an inter-monitoring item association definition unit of a monitoring control device according to the present disclosure; [Figure 5] 10 is a diagram illustrating a case where an abnormality is detected in the monitoring control device according to the present disclosure. FIG. [Figure 6] 10 is a diagram showing the current and previous values ​​of the output value of a sensor in a monitoring data management DB of the monitoring control device according to the present disclosure. FIG. [Figure 7] 4 is a diagram illustrating an example of calculation of a causal relationship with an abnormality occurrence in the monitoring control device according to the first embodiment of the present disclosure. FIG. [Figure 8] 4 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of the monitoring control device according to the first embodiment of the present disclosure. FIG. [Figure 9] 3A and 3B are diagrams illustrating identification of a cause of an abnormality in a cause identifying unit of the monitoring control device according to the first embodiment of the present disclosure. [Figure 10] 4 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of the monitoring control device according to the first embodiment of the present disclosure. FIG. [Figure 11] 3 is a diagram showing an example of a display on a display unit of the monitoring control device according to the first embodiment of the present disclosure. FIG. [Figure 12] FIG. 10 is a diagram illustrating an example of calculation of a causal relationship in a causal relationship calculation unit of a monitoring control device according to a second embodiment of the present disclosure. [Figure 13] 10 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of a monitoring control device according to a second embodiment of the present disclosure. FIG. [Figure 14]FIG. 11 is a diagram illustrating an example of calculation of a causal relationship in a causal relationship calculation unit of a monitoring control device according to a third embodiment of the present disclosure. [Figure 15] 11A and 11B are diagrams illustrating time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of a monitoring control device according to a third embodiment of the present disclosure. [Figure 16] FIG. 11 is a diagram illustrating an example of calculation of a causal relationship in a causal relationship calculation unit of a monitoring control device according to a fourth embodiment of the present disclosure. [Figure 17] FIG. 11 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of a monitoring control device according to a fourth embodiment of the present disclosure. [Figure 18] FIG. 13 is a diagram illustrating an example of calculation of a causal relationship in a causal relationship calculation unit of a monitoring control device according to a fifth embodiment of the present disclosure. [Figure 19] FIG. 13 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of a monitoring control device according to a fifth embodiment of the present disclosure. [Figure 20] FIG. 20 is a diagram illustrating an example of calculation of a causal relationship in a causal relationship calculation unit of a monitoring control device according to a sixth embodiment of the present disclosure. [Figure 21] FIG. 20 is a diagram showing time-series changes in monitoring data before and after the occurrence of an abnormality in a monitoring data management DB of a monitoring control device according to a sixth embodiment of the present disclosure. [Figure 22] FIG. 10 is a block diagram showing a configuration of a modified example of a monitoring control device according to the present disclosure. [Figure 23] 1 is a diagram illustrating a hardware configuration for implementing a monitoring control device according to first to sixth embodiments of the present disclosure. [Figure 24] 1 is a diagram illustrating a hardware configuration for implementing a monitoring control device according to first to sixth embodiments of the present disclosure. [Figure 25] FIG. 1 is a block diagram showing a configuration in which a monitoring control device according to any one of first to sixth embodiments of the present disclosure is provided in a server computer that constitutes a cloud environment. [Figure 26] FIG. 13 is a block diagram showing a configuration of a monitoring and control system according to a seventh embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] <First Embodiment> 1 is a block diagram showing the configuration of a monitoring control device 100 according to a first embodiment of the present disclosure. As shown in FIG. 1, the monitoring control device 100 includes a monitoring item information management database (DB) 10, a monitoring item relationship definition unit 20, a relationship model management database (DB) 30, a monitoring data management database (DB) 40, a causal relationship calculation unit 50, a cause identification unit 60, and a display unit 70.

[0012] The monitoring item information management DB 10 manages monitoring item information such as facility, equipment, and sensor information managed by monitoring data. Fig. 2 is a diagram showing in tabular form an example of the monitoring item information management DB 10. In Fig. 2, the monitoring items are shown as plants, facilities, equipment, equipment, and sensor names, and the plant is shown as a purification center, the facility is shown as a water treatment facility, the equipment is shown as primary sedimentation equipment and reaction tank equipment, the equipment is shown as equipment A, B, and C, and the sensor names are shown as sensors A to E.

[0013] The monitoring item relationship definition unit 20 defines relationships between monitoring items. Relationships between monitoring items can be physical relationships, such as facility relationships representing the equipment configuration (e.g., facilities, equipment, and sensors), wiring relationships (e.g., power wiring in an electric power system), or process flow relationships (e.g., in water purification plants and sewage treatment plants), or correlation relationships, such as correlations based on the experience of monitoring experts and correlations derived through statistical analysis. System relationships between systems, such as between monitoring control systems and facility management systems, are also included. Furthermore, relationships between information from different sensors and data sources, such as inspection information, point cloud information, water level sensor information, vibration sensor information, camera image information, and weather information, for the same object (e.g., facility, equipment, road, bridge, tunnel, etc.) are also included. This allows for a wider range of relationships between monitoring items. Defining relationships between monitoring items means linking the monitoring items together.

[0014] The related model management DB 30 manages the related monitoring items defined in the inter-monitoring item relationship definition unit 20 as related models. A graph database (DB) is used for this management, and the related models are managed as a tree structure. More specifically, a labeled property graph is used for management. Management can also be performed using an RDB (Relational Database). A specific example of the related model management DB 30 will be described later.

[0015] The monitoring data management DB 40 manages the monitoring data output by monitoring devices such as sensors in chronological order, and the monitoring data is input to the causal relationship calculation unit 50 together with the associated models managed in the associated model management DB 30. Fig. 3 is a diagram showing an example of the monitoring data management DB 40 in a table format. Fig. 3 shows the current and previous values ​​of the output values ​​of sensors A to E, respectively.

[0016] When multiple sensors SC installed at various locations in the plant detect an abnormality, the causal relationship calculation unit 50 calculates which monitoring item of which related model is causally related to the abnormality, based on the related model and the time-series changes in the monitoring data before and after the abnormality occurred.

[0017] The cause identification unit 60 identifies the monitoring item that is the cause of the abnormality occurrence based on the monitoring items with causal relationships calculated by the causal relationship calculation unit 50.

[0018] The display unit 70 is a display that displays the monitoring items that are causally related to the occurrence of an abnormality identified by the cause identification unit 60 and the cause of the abnormality.

[0019] Next, the operation of each unit of the monitoring and control device 100 will be described using the associated model management DB 30 when a labeled property graph is used.

[0020] FIG. 4 shows an example of an association model between monitor items defined in the monitor item association definition unit 20, and shows an example of an association model defined based on the monitor item information management DB 10 shown in FIG.

[0021] In Figure 4, multiple monitoring items are displayed in a tree diagram, with the water treatment facility at the purification center plant having primary settling equipment and reaction tank equipment, with the primary settling equipment having equipment A and equipment B, and the reaction tank equipment having equipment C. Equipment A has sensor A, equipment B has sensors B and C, and equipment C has sensors D and E.

[0022] Each monitoring item is surrounded by a frame, and the relationship model showing equipment relationships is defined by connecting the monitoring items with solid lines. The relationship model showing the water treatment flow is defined by closely spaced dashed arrows pointing from equipment B to equipment C. The relationship model showing the correlation relationship is defined by a dot-dash bidirectional arrow between equipment A and equipment C. The relationship model showing the power wiring of the same wiring is defined by widely spaced dashed arrows pointing from equipment A to equipment B.

[0023] In the relationship model between monitoring items defined in this way, an example in which the sensor SC (FIG. 1) of the plant detects the occurrence of an abnormality will be described using FIG. 5. FIG. 5 schematically shows a case in which the sensor D detects the occurrence of an abnormality. FIG. 6 shows the current and previous output values ​​of the sensor D in the monitoring data management DB 40. As shown in FIG. 6, the current output value of the sensor D is 20.0, and the previous value is 18.5.

[0024] If there is a large difference between the current and previous sensor output values, or if the current value exceeds a predetermined threshold, or if the value is determined to be abnormal based on past statistical results, an abnormality is reported. In the example of Figure 6, the difference between the current and previous values ​​is 1.5, and because the difference is large, an abnormality is reported.

[0025] Next, an example of the calculation of the causal relationship by the causal relationship calculation unit 50 will be described with reference to Fig. 7. Fig. 5 schematically shows a case where sensor D detects the occurrence of an abnormality, but Fig. 7 schematically shows the possibility that an abnormality may also occur in sensor E.

[0026] Sensors related to the sensor that detected the abnormality, i.e., sensors that are causally related to the abnormality, are likely to show time-series changes before and after the abnormality, just like the sensor that detected the abnormality. Figure 8 shows the results of calculating the time-series changes in the monitoring data before and after the abnormality, as changes, from the current and previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40. In Figure 8, the change in the output value of sensor D from the previous value is 1.5. The previous output value of sensor E was 8.2, and the current value is 10.0, so the change from the previous value is 1.8, which is larger than the change in sensor D. Therefore, it can be seen that sensor E, like sensor D, is causally related to the abnormality. Note that the change from the previous value of sensors A to C is all less than 0.5.

[0027] In this way, by calculating the amount of change from the previous value of each sensor, sensors with time series changes similar to the time series changes of the sensor that detected the abnormality can be determined as sensors that have a causal relationship with the abnormality. Note that the causal relationship can also be calculated by calculating the time series changes of the monitoring data using a statistical method using Euclidean distance. When Euclidean distance is used, the sensor that is closest in point-to-point distance to the sensor that detected the abnormality is determined as the sensor that has a causal relationship with the abnormality.

[0028] Next, the identification of the cause of the abnormality occurrence by the cause identification unit 60 will be described with reference to Fig. 9. Fig. 9 shows an example in which, when there is a possibility that an abnormality will also occur in sensor E, sensor E is identified as a sensor that has a causal relationship with the abnormality occurrence, similar to sensor D that detected the abnormality occurrence.

[0029] Fig. 10 shows the amount of change calculated as the time series change in the monitoring data before and after the occurrence of an abnormality from the current and previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40. In Fig. 10, the amount of change from the previous value of the output value of sensor D is 1.5, and the amount of change from the previous value of the output value of sensor E is 1.8, both of which are greater than 0.5.

[0030] When identifying a sensor that has a causal relationship with the sensor that detected the abnormality based on the magnitude of the change, it can be identified by whether or not it exceeds a threshold. For example, if the threshold for the change is 0.5, the change for sensor E exceeds the threshold of 0.5. Here, from the association model that shows the equipment association, it is determined that sensors D and E are sensors related to device C, and therefore sensor E, like sensor D, is identified as having a causal relationship with the abnormality.

[0031] Furthermore, sensors D and E are connected to device C by a common solid line, and any abnormality detected by sensor D is identified as being caused by device C. Here, the solid line connecting sensors D and E to device C is what is called an edge in a labeled property graph, and names can be defined for edges. In Figure 9, the edge in question is labeled as edge 1, and its property (attribute) is labeled as cause flag 1. Here, edge 1 is the name that defines "equipment related."

[0032] In this way, the cause identification unit 60 determines that sensors D and E are causally related to the occurrence of the abnormality through the detection of the abnormality by sensor D, and is thereby able to identify device C as the cause of the abnormality. This result is displayed on the display unit 70 and presented to the user of the monitoring control device 100.

[0033] An example of the display on the display unit 70 is shown in Fig. 11. In Fig. 11, the detection of the occurrence of an abnormality by sensor D is indicated by a light emission, sensors D and E are connected to device C by solid lines to indicate that they are causally related to the occurrence of the abnormality, and arrows pointing from sensors D and E to device C indicate that device C is the cause of the occurrence of the abnormality.

[0034] As described above, in the monitoring control device 100 of the first embodiment, by defining the correlation between monitoring items such as devices and sensors linked to equipment, which is a unit smaller than the components of the equipment, the causal relationship between the monitoring item and the occurrence of an abnormality can be identified, and thereby the equipment causing the abnormality can be identified. This makes it possible to reduce the cost of plant maintenance compared to a method in which the cause of the abnormality is unknown and all related equipment is replaced.

[0035] Furthermore, by defining the system relationships between systems such as a supervisory control system and an equipment management system, supervisory control between systems becomes possible, enabling supervisory control of the entire plant.

[0036] In addition, by calculating the amount of change from the previous value of each sensor, sensors that have time series changes similar to the time series changes of the sensor that detected the abnormality can be identified as sensors that are causally related to the abnormality, thereby improving the accuracy of identifying the equipment that is causing the abnormality.

[0037] <Embodiment 2> Next, a monitoring control device 100A according to a second embodiment of the present disclosure will be described. The block diagram showing the configuration of the monitoring control device 100A is the same as that of the monitoring control device 100 according to the first embodiment shown in Fig. 1. In the monitoring control device 100A according to the second embodiment, the processing performed by the causal relationship calculation unit 50 and the cause identification unit 60 differs from that performed in the monitoring control device 100.

[0038] An example of the calculation of the causal relationship in the causal relationship calculation unit 50 of the monitoring control device 100A will be described with reference to Fig. 12. Fig. 12 schematically shows a case where sensor D detects the occurrence of an abnormality. Fig. 13 shows the results of calculating the time-series change in the monitoring data before and after the occurrence of an abnormality from the current and previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40, as the amount of change, and also shows the weights assigned to sensors A to E.

[0039] That is, if a relational model that has a high causal relationship with the occurrence of an abnormality is known in advance from among the relational models defined in the inter-monitoring-item relation definition unit 20, the causal relationship calculation unit 50 assigns a weight to that relational model. Here, a monitoring item such as device A is a node in a labeled property graph, and the name of a sensor with a high causal relationship can be defined for the node. In FIG. 12 , for device A, sensor A is defined as a sensor with a causal relationship with device A, and a weight of 1.0 for sensor A is labeled as a property. Similarly, the names of sensors with a high causal relationship are defined for devices B and C, and the weights of each sensor are labeled. Here, the weight is set as a numerical value by which the current value is multiplied, for example, a weight of 2.0 means that the current value is multiplied by 2.0.

[0040] 13 shows the weights assigned to sensors A to E, with the weights of sensors B and C both being 2.0. In Fig. 13, the change in the output value of sensor D from the previous value is 1.5, and the change in the output value of sensor E from the previous value is 1.8, both of which are greater than 0.5.

[0041] If the threshold for the amount of change is 0.5, the amount of change for sensors D and E exceeds the threshold of 0.5. Here, from the association model showing the equipment association, it is clear that sensors D and E are sensors related to device C, and it is therefore identified that sensors D and E have a causal relationship with the occurrence of the abnormality.

[0042] Furthermore, it is known in advance that there is a strong causal relationship between device B and sensors B and C, and the weights are both set to 2.0, so the current values ​​are multiplied by 2.0, and the change in output value from the previous value exceeds the threshold value of 0.5, identifying sensors B and C as having a causal relationship with the occurrence of an abnormality.

[0043] Furthermore, from the related model showing the water treatment flow, it can be seen that equipment B and equipment C are related models of the water treatment flow and that the cause of the abnormality is also in equipment B, so it can be identified that the cause of the abnormality is equipment B and equipment C.

[0044] As described above, the monitoring control device 100A of the second embodiment uses not only an association model of facilities and devices defined by physical connections between the facilities and devices, but also an association model defined by a process flow such as a water treatment flow to identify devices that are the cause of an abnormality, so that the cause of an abnormality can also be identified for devices that are indirectly related. This allows a wider range of causes of abnormalities to be identified, thereby improving the accuracy of plant maintenance.

[0045] Furthermore, if a related model that has a high causal relationship with the occurrence of an abnormality is known in advance, the related model is weighted, so that the related model that has a high causal relationship with the occurrence of an abnormality can be reliably identified.

[0046] <Third Embodiment> Next, a monitoring control device 100B according to a third embodiment of the present disclosure will be described. The block diagram showing the configuration of the monitoring control device 100B is the same as that of the monitoring control device 100 according to the first embodiment shown in Fig. 1. In the monitoring control device 100B according to the third embodiment, the processing performed by the causal relationship calculation unit 50 and the cause identification unit 60 differs from that performed in the monitoring control device 100.

[0047] An example of the calculation of causal relationships in the causal relationship calculation unit 50 of the monitoring control device 100B will be described with reference to Fig. 14. Fig. 14 schematically shows a case where sensor D detects the occurrence of an abnormality. Fig. 15 shows the results of calculating the time-series changes in the monitoring data before and after the occurrence of an abnormality from the current and previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40, as the amount of change. In Fig. 15, the amount of change from the previous value of the output value of sensor D is 1.5. The previous value of the output value of sensor A was 11.0, and the current value is 11.5, so the amount of change from the previous value is 0.5. The amounts of change from the previous values ​​of sensors B, C, and E are 0.

[0048] If the threshold for the amount of change is 0.5, then the amounts of change for sensor A and sensor D exceed the threshold of 0.5. Here, from the association model showing the equipment association, it is clear that sensor A is a sensor related to device A, and sensor D is a sensor related to device C. Because the amount of change for sensor A exceeds the threshold of 0.5, it is clear that sensor A has a causal relationship with the occurrence of the abnormality. Furthermore, because the amount of change for sensor D exceeds the threshold of 0.5, it is clear that sensor D has a causal relationship with the occurrence of the abnormality.

[0049] Furthermore, since it can be seen from the correlation model showing the correlation that device C is correlated with device A, it is possible to identify that device A is the cause of the abnormality detected by sensor D.

[0050] As described above, the monitoring control device 100B of the third embodiment uses not only an association model of equipment relationships defined by the physical connections between facilities and devices, but also an association model showing correlation relationships to identify the device that is the cause of an abnormality, so it is possible to identify the cause of an abnormality by taking into account correlations based on the empirical values ​​of monitoring experts and correlations derived by statistical analysis. This makes it possible to identify causes of an abnormality that cannot be identified by using other association models.

[0051] <Fourth Embodiment> Next, a monitoring control device 100C according to a fourth embodiment of the present disclosure will be described. The block diagram showing the configuration of the monitoring control device 100C is the same as that of the monitoring control device 100 according to the first embodiment shown in Fig. 1. In the monitoring control device 100C according to the fourth embodiment, the processing performed by the causal relationship calculation unit 50 and the cause identification unit 60 differs from that performed in the monitoring control device 100.

[0052] An example of the calculation of causal relationships in the causal relationship calculation unit 50 of the monitoring control device 100C will be described with reference to FIG. 16. FIG. 16 schematically illustrates a case where sensor D detects the occurrence of an abnormality. FIG. 17 shows the results of calculating the time-series changes in the monitoring data before and after the occurrence of an abnormality from the current and previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40, expressed as a change amount. In FIG. 17, the change amount from the previous value of sensor D's output value is 1.5. The previous value of sensor A's output value is 11.0, and the current value is 11.5, so the change amount from the previous value is 0.5. The previous value of sensor B's output value is 3.0, and the current value is 3.6, so the change amount from the previous value is 0.6. The previous value of sensor C's output value is 5.0, and the current value is 5.9, so the change amount from the previous value is 0.9. Note that the change amount from the previous value of sensor E is 0.

[0053] If the threshold for the amount of change is set to 0.5, the amounts of change for sensors A, B, C, and D exceed the threshold of 0.5, and therefore it can be seen that sensors A to D are causally related to the occurrence of the abnormality. Here, from the association model showing the equipment association, it can be seen that sensor D is a sensor related to device C, and furthermore, from the association model showing the correlation, it can be seen that device C is correlated with device A. Furthermore, from the association model showing the power wiring, it can be seen that device A is a device related to device B, and therefore it can be identified that the cause of the abnormality detected by sensor D is device A.

[0054] As described above, the monitoring and control device 100C of the fourth embodiment can identify the device that is causing an abnormality by combining an equipment-related association model defined by the physical connections between facilities and devices, an association model indicating correlations, and an association model indicating power wiring. This can improve the accuracy of identifying the cause of an abnormality, and can also improve the accuracy of plant maintenance.

[0055] <Fifth Embodiment> Next, a monitoring control device 100D according to a fifth embodiment of the present disclosure will be described. The block diagram showing the configuration of the monitoring control device 100D is the same as that of the monitoring control device 100 according to the first embodiment shown in Fig. 1. In the monitoring control device 100D according to the fifth embodiment, the processing performed by the causal relationship calculation unit 50 and the cause identification unit 60 differs from that performed in the monitoring control device 100.

[0056] An example of the calculation of the causal relationship in the causal relationship calculation unit 50 of the monitoring control device 100D will be described with reference to FIG. 18. FIG. 18 schematically illustrates a case where sensor D detects the occurrence of an abnormality. FIG. 19 shows the results of calculating the time-series change in the monitoring data as a change amount based on the current, previous, and previous-previous values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40. In FIG. 19, the change amount is a value calculated at the timing when the time-series change occurs. The previous output value of sensor C is 5.9, the previous-previous value is 5.0, and the current value is 5.9, indicating that the time-series change occurred between the previous and previous-previous values. On the other hand, the previous output value of sensor D is 18.5, the previous-previous value is 18.5, and the current value is 20.0, indicating that the time-series change occurred between the current and previous values.

[0057] From these results, it can be seen that sensors C and D are causally related to the occurrence of the abnormality. It can also be determined that a time series change occurred in device B before the time when the abnormality occurred in device C. Here, from the association model showing the equipment association, it can be seen that sensor D is a sensor related to device C. Furthermore, from the association model showing the water treatment flow, devices B and C are associated models of the water treatment flow, and the time series change in the monitoring data of sensor C occurred before the time series change in the monitoring data of sensor D. Therefore, it can be identified that device B is the cause of the abnormality detected by sensor D.

[0058] As described above, the monitoring control device 100D of the fifth embodiment uses an equipment-related association model defined by the physical connections between facilities and devices and an association model of the water treatment flow, and can identify the device causing the abnormality by taking into consideration the timing of the time-series change in the monitoring data. This improves the accuracy of identifying the cause of the abnormality, and can improve the accuracy of plant maintenance.

[0059] <Sixth Embodiment> Next, a monitoring control device 100E according to a sixth embodiment of the present disclosure will be described. The block diagram showing the configuration of the monitoring control device 100E is the same as that of the monitoring control device 100 according to the first embodiment shown in Fig. 1. In the monitoring control device 100E according to the sixth embodiment, the processing performed by the causal relationship calculation unit 50 and the cause identification unit 60 differs from that performed in the monitoring control device 100.

[0060] An example of the calculation of causal relationships in the causal relationship calculation unit 50 of the monitoring control device 100E will be described with reference to FIG. 20. FIG. 20 schematically illustrates a case where sensor D detects an abnormality. FIG. 21 shows the results of calculating the time-series changes in the monitoring data as the amount of change, based on the current, previous, second-to-last, and second-to-last values ​​of the output values ​​of sensors A to E in the monitoring data management DB 40. In FIG. 21, the amount of change is the value calculated at the timing when the time-series change occurred. The current, previous, and second-to-last values ​​of the output value of sensor A are all 11.5, and the second-to-last value is 11.0, indicating that the time-series change occurred between the second-to-last and second-to-last times. Furthermore, the current and previous values ​​of sensor C are 5.9, and the second-to-last and second-to-last values ​​are 5.0, indicating that the time-series change occurred between the last and second-to-last times. On the other hand, the previous, previous-previous and previous-previous values ​​of the output value of sensor D are 18.5, and the current value is 20.0, which indicates that a time series change has occurred between the present and the previous time.

[0061] From these results, it can be seen that sensors C and D are causally related to the occurrence of the abnormality. It can also be determined that there was a time series change in device B before the time the abnormality occurred in device C, and that there was an even earlier time series change in device A. Here, from the association model showing the equipment relationships, it can be seen that sensor D is a sensor related to device C. Furthermore, from the association model showing the water treatment flow, it can be seen that devices B and C are associated models of the water treatment flow, and from the association model showing the power wiring, it can be seen that device A is a device related to device B. Furthermore, since the time series change in the monitoring data of sensor C occurred before the time series change in the monitoring data of sensor D, and the time series change in the monitoring data of sensor A occurred before the time series change in the monitoring data of sensor C, it can be identified that devices B and A are the cause of the abnormality detected by sensor D.

[0062] As described above, the monitoring control device 100E of the sixth embodiment combines a facility-related association model defined by the physical connections between facilities and devices, a water treatment flow association model, and an association model showing power wiring, and can identify the device causing an abnormality by taking into consideration the timing of time-series changes in the monitoring data. This makes it possible to improve the accuracy of identifying the cause of an abnormality and to improve the accuracy of plant maintenance.

[0063] <Modification> In the monitoring control devices 100 to 100E of the first to sixth embodiments described above, correlations between monitoring items defined by the inter-monitoring item relationship definition unit 20 include correlations based on the empirical values ​​of monitoring experts and correlations derived by statistical analysis. When defining these, the empirical values ​​of monitoring experts and statistical values ​​can be used as input information, and the correlations can be calculated using machine learning using artificial intelligence (AI), and the calculation results can be input to the inter-monitoring item relationship definition unit 20.

[0064] FIG. 22 shows monitoring control devices 100 to 100E in which information on the correlation between monitoring items calculated by the AI ​​200 is input to the monitoring item correlation definition unit 20.

[0065] By adopting such a configuration, correlations between monitoring items can be defined from vague information such as the experience of an expert monitor, and the processing in the monitoring item correlation definition unit 20 can be simplified.

[0066] <Hardware configuration> Each of the components of the monitoring and controlling devices 100 to 100E according to the first to sixth embodiments described above can be configured using a computer, and is realized by the computer executing a program. That is, the monitoring and controlling devices 100 to 100E are realized, for example, by a processing circuit 1000 shown in Fig. 23. A processor such as a CPU (Central Processing Unit) or a DSP (Digital Signal Processor) is applied to the processing circuit 1000, and the function of each part is realized by executing a program stored in a storage device.

[0067] Dedicated hardware may be applied to the processing circuit 1000. When the processing circuit 1000 is dedicated hardware, the processing circuit 1000 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these.

[0068] In the monitoring control devices 100 to 100E, the functions of the components can be realized by individual processing circuits, or these functions can be realized collectively by one processing circuit.

[0069] 24 shows a hardware configuration in the case where the processing circuit 1000 is configured using a processor. In this case, the functions of each unit of the monitoring and controlling devices 100-100E are realized by a combination of software, etc. (software, firmware, or software and firmware). The software, etc. is written as a program and stored in memory 1002. The processor 1001 functioning as the processing circuit 1000 realizes the functions of each unit by reading and executing the program stored in memory 1002 (storage device). In other words, it can be said that this program causes a computer to execute the procedure and method of operation of the components of the monitoring and controlling devices 100-100E.

[0070] Here, the memory 1002 may be, for example, a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), HDD (Hard Disk Drive), magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disc) and its drive device, or any storage medium that will be used in the future.

[0071] The above describes a configuration in which the functions of each component of the monitoring control devices 100-100E are realized either by hardware or software, etc. However, this is not a limitation, and some of the components of the monitoring control devices 100-100E can be realized by dedicated hardware, and other components can be realized by software, etc. For example, some of the components can be realized by the processing circuit 1000 as dedicated hardware, and other components can be realized by the processing circuit 1000 as the processor 1001 reading and executing a program stored in the memory 1002.

[0072] As described above, the monitoring and control devices 100 to 100E can realize the above-mentioned functions by hardware, software, or a combination of these.

[0073] <Other application examples> The monitoring control devices 100 to 100E of the above-described embodiments 1 to 6 can be installed in a server computer that constitutes a cloud environment, and monitoring data can be input to a server computer on the cloud via a communication network, causal relationships can be identified in the server computer, and the data can be displayed on a display device connected to the communication network.

[0074] FIG. 25 is a block diagram showing a configuration in which monitoring and control devices 100 to 100E are provided in a server computer 300 that constitutes a cloud environment.

[0075] 25, the server computer 300 has a monitoring item information management DB 10, a monitoring item relation definition unit 20, a relation model management DB 30, a monitoring data management DB 40, a causal relationship calculation unit 50, and a cause identification unit 60. These functions are the same as those of the respective components of the monitoring control devices 100 to 100E.

[0076] Monitoring data detected by multiple sensors SC installed at various locations in the plant is input to a server computer 300 via a communication network, and the server computer 300 identifies causal relationships and displays them on a display device DP connected to the communication network.

[0077] The plant manager maintains and manages the plant using the causal relationships displayed on the display device DP. By providing the monitoring and control devices 100 to 100E in a server computer 300 that constitutes a cloud environment, they can be accessed from anywhere, making them more convenient.

[0078] <Seventh Embodiment> 26 is a block diagram showing the configuration of a monitoring control system 400 according to the seventh embodiment of the present disclosure. As shown in FIG. 26, the monitoring control system 400 includes a monitoring item information management DB 10, a monitoring item relationship definition unit 20, a relationship model management DB 30, a monitoring data management DB 40, a causal relationship calculation unit 50, a cause identification unit 60, a display unit 70, and a sensor 80.

[0079] The monitoring and control system 400 includes the components of the monitoring and control devices 100 to 100E, as well as a plurality of sensors 80 installed at various locations in the plant.

[0080] By constructing such a monitoring and control system 400, it is possible to identify the causal relationship of the occurrence of an abnormality and to identify the cause of the occurrence of the abnormality detected by the sensor 80.

[0081] Although the present disclosure has been described in detail, the above description is illustrative in all respects and does not limit the present disclosure to the above. It is understood that countless variations not illustrated can be envisioned without departing from the scope of the present disclosure.

[0082] It should be noted that, within the scope of the present disclosure, the embodiments can be freely combined, and the embodiments can be modified or omitted as appropriate.

Claims

1. A monitoring control device that monitors a plurality of monitoring items that are monitoring targets, an association definition section that defines associations between the plurality of monitor items; a relational model management database that manages a plurality of relational models, the plurality of related monitoring items defined in the relation definition unit being regarded as relational models; a monitoring data management database for managing the monitoring data of the plurality of monitoring items; a causal relationship calculation unit that, when an abnormality is detected in at least one of the plurality of monitoring items, calculates, based on the plurality of related models managed in the related model management database and the monitoring data managed in the monitoring data management database, which monitoring item of the plurality of related models has a causal relationship with the occurrence of the abnormality; a cause identification unit that identifies a cause of the abnormality occurrence based on the monitoring items having the causal relationship calculated by the causal relationship calculation unit, The causal relationship calculation unit calculating the monitoring items that have the causal relationship with the occurrence of the abnormality based on time-series changes in the monitoring data before and after the occurrence of the abnormality; The association definition section The relationship between the monitoring items is as follows: A supervisory control device that defines a system relationship between a supervisory control system having a plurality of sensors in the supervisory control device and an equipment management system that manages equipment in a plant.

2. A monitoring control device that monitors a plurality of monitoring items that are monitoring targets, an association definition section that defines associations between the plurality of monitor items; a relational model management database that manages a plurality of relational models, the plurality of related monitoring items defined in the relation definition unit being regarded as relational models; a monitoring data management database for managing the monitoring data of the plurality of monitoring items; a causal relationship calculation unit that, when an abnormality is detected in at least one of the plurality of monitoring items, calculates, based on the plurality of related models managed in the related model management database and the monitoring data managed in the monitoring data management database, which monitoring item of the plurality of related models has a causal relationship with the occurrence of the abnormality; a cause identification unit that identifies a cause of the abnormality occurrence based on the monitoring items having the causal relationship calculated by the causal relationship calculation unit, The causal relationship calculation unit calculating the monitoring items that have the causal relationship with the occurrence of the abnormality based on time-series changes in the monitoring data before and after the occurrence of the abnormality; The causal relationship calculation unit A monitoring control device that calculates a monitoring item having a causal relationship with the occurrence of the abnormality if the monitoring item in which the abnormality occurrence was detected is similar to the monitoring item in which the time series changes in the monitoring data before and after the occurrence of the abnormality.

3. The causal relationship calculation unit 3. The monitoring control device according to claim 2, wherein, among the monitoring data of the plurality of monitoring items managed in the monitoring data management database, the monitoring item having a change amount similar to the change amount between the previous detection value and the current detection value of the monitoring item that detected the occurrence of the abnormality is determined to be the monitoring item that is causally related to the occurrence of the abnormality.

4. A monitoring control device that monitors a plurality of monitoring items that are monitoring targets, an association definition section that defines associations between the plurality of monitor items; a relational model management database that manages a plurality of relational models, the plurality of related monitoring items defined in the relation definition unit being regarded as relational models; a monitoring data management database for managing the monitoring data of the plurality of monitoring items; a causal relationship calculation unit that, when an abnormality is detected in at least one of the plurality of monitoring items, calculates, based on the plurality of related models managed in the related model management database and the monitoring data managed in the monitoring data management database, which monitoring item of the plurality of related models has a causal relationship with the occurrence of the abnormality; a cause identification unit that identifies a cause of the abnormality occurrence based on the monitoring items having the causal relationship calculated by the causal relationship calculation unit, The causal relationship calculation unit calculating the monitoring items that have the causal relationship with the occurrence of the abnormality based on time-series changes in the monitoring data before and after the occurrence of the abnormality; The causal relationship calculation unit When a relational model having a high causal relationship with the occurrence of the abnormality is known in advance from among the plurality of relational models defined in the relation definition unit, weighting is performed on the monitoring items of the relational model; A monitoring control device calculates the monitoring items that are causally related to the occurrence of the abnormality, taking into consideration the weight.

Images