JP2023155731A - Monitoring controller, monitoring control method, and monitoring control program - Google Patents

Abstract

To provide a monitoring controller capable of presenting a correlation between signals representing the condition of a facility.SOLUTION: A monitoring controller 1A includes a signal data acquisition unit 13 that acquires signal data representing the condition of a facility, a correlation learning unit 14 that acknowledges a correlation, in which a signal value of one signal varies through linkage with a variation in a signal value of the other signal, of signals on the basis of signal ledger data which represents a collection of signal attributes, outputs correlation data representing a result of the acknowledgement, and obtains a degree of correlation between the signals through learning based on the signal data and the signal ledger data, a conversion processing unit 15 that performs conversion processing for displaying a network structure, in which symbols representing the signals having the correlation are tied in a network manner, on the correlation data, and performs processing for displaying the degree of correlation together with the network structure, and a correlation editing unit 16 that edits the correlation indicated with the network structure according to an editing manipulation.SELECTED DRAWING: Figure 2

Description

The present disclosure relates to a supervisory control device, a supervisory control method, and a supervisory control program that monitor and control each of a plurality of facilities.

A monitoring and control device that acquires signals representing the status of each piece of equipment and collectively monitors the status of multiple pieces of equipment installed in a building or other building, such as power equipment, elevators, and air conditioning equipment. Are known. The supervisory control device also controls each piece of equipment by sending commands to each piece of equipment. Such monitoring and control equipment not only monitors the status of equipment from the signals of each equipment, but also understands the correlation between the signals being monitored in advance, which is useful for investigating the cause when an abnormality occurs. Attempts are being made. Even when there is a complex correlation between a plurality of signals, the supervisory control device can present the correlation in an easy-to-understand manner by displaying the correlation on the screen.

Patent Document 1 discloses that in a monitoring and control device that monitors and controls an electric power system, it is possible to generate related information representing the relationship between equipment constituting the electric power system and to control the electric power system through calculations using the related information. Disclosed. According to the technology disclosed in Patent Document 1, the hierarchy of each piece of equipment is identified from the hierarchical structure of the power system, and an equipment code for individually identifying each piece of equipment within the power system is set by coding according to rules. . The monitoring control device according to Patent Document 1 stores equipment data including an equipment code and attribute information representing attributes of the equipment, and generates related information based on the equipment data.

Japanese Patent Application Publication No. 2001-251763

According to the technique disclosed in Patent Document 1, it is necessary to determine in advance a rule for specifying the hierarchy of each equipment from the hierarchical structure of the power system regarding the equipment code. Determining the rules for specifying the hierarchy requires specialized knowledge about the configuration of the power system. Furthermore, according to the technique disclosed in Patent Document 1, if the hierarchical structure deviates even slightly from predetermined rules, related information cannot be generated. Therefore, according to the technique of Patent Document 1, there is a problem that it may not be possible to present the correlation between signals representing the state of the equipment.

The present disclosure has been made in view of the above, and an object of the present disclosure is to obtain a monitoring and control device that can present correlations between signals representing the state of equipment.

In order to solve the above-mentioned problems and achieve the objectives, a supervisory control device according to the present disclosure collects signal data including signal values of signals representing the state of the equipment for each of a plurality of equipment that is a target of monitoring and control. and a signal data collection unit that collects signals included in the plurality of signals based on the signal ledger data that summarizes the signal attributes of each of the plurality of signals. Recognizes correlations in which signal values change, outputs correlation data indicating the results of the recognition, and calculates the degree of correlation between signals other than the signals for which correlations have been determined based on the signal data and signal ledger data. A correlation learning unit that calculates the correlation by learning based on the correlation data, performs conversion processing on the correlation data to display a network structure in which symbols of signals having a correlation are connected in a network, and calculates the degree of correlation along with the network structure. and a correlation editing section that edits the correlation shown in the network structure according to an editing operation.

The monitoring and control device according to the present disclosure has the effect of being able to present a correlation between signals representing the state of equipment.

A diagram illustrating a configuration example of a supervisory control system including a supervisory control device according to Embodiment 1. A diagram showing a configuration example of a monitoring control device according to Embodiment 1. A diagram for explaining correlations certified by the supervisory control device according to the first embodiment A diagram showing an example of signal data collected in the supervisory control device according to Embodiment 1. A diagram illustrating an example of signal ledger data stored in the monitoring and control device according to Embodiment 1. A diagram showing an example of equipment ledger data input to the monitoring control device according to the first embodiment A diagram showing an example of a network structure converted from correlation data by the supervisory control device according to the first embodiment. A diagram for explaining the display of the correlation degree by the processing of the supervisory control device and the editing of the correlation by the supervisory control device according to the first embodiment. Flowchart showing the operation procedure of the supervisory control device according to the first embodiment A diagram showing a configuration example of a monitoring control device according to a second embodiment A diagram showing a first example of a graph displayed according to Embodiment 2 A diagram showing a second example of a graph displayed according to Embodiment 2 Diagram for explaining graph switching in Embodiment 2 A diagram showing a configuration example of a monitoring control device according to Embodiment 3 A diagram showing a configuration example of a monitoring control device according to Embodiment 4 A diagram showing a configuration example of a monitoring control device according to a fifth embodiment A diagram showing an example of the hardware configuration of the monitoring control device according to Embodiments 1 to 5.

Below, a supervisory control device, a supervisory control method, and a supervisory control program according to an embodiment will be described in detail based on the drawings.

Embodiment 1.
FIG. 1 is a diagram illustrating a configuration example of a supervisory control system including a supervisory control device 1A according to the first embodiment. The monitoring and control device 1A monitors and controls each of the plurality of facilities 2. In the first embodiment, the plurality of facilities 2 that are the targets of monitoring and control by the supervisory control device 1A are facilities installed in buildings such as buildings. The plurality of facilities 2 include, for example, power facilities, elevators, air conditioning facilities, and the like.

The supervisory control device 1A is configured by, for example, one or more cloud servers. A cloud server is a server built in a cloud environment that includes computer resources provided in a cloud service platform. Note that the monitoring control device 1A may be a server other than a cloud server, and may be an on-premises server, for example.

The supervisory control device 1A and the terminal 3 constitute a supervisory control system. The terminal 3 is a terminal device used by a user of the supervisory control system. The user is a person who performs monitoring and control work for each facility 2 using the monitoring and control system. It is assumed that the number of terminals 3 connected to the supervisory control device 1A is arbitrary.

The terminal 3 is communicably connected to the supervisory control device 1A via a network, and transmits and receives information to and from the supervisory control device 1A. The network is, for example, a WAN (Wide Area Network) such as the Internet, but may also be a LAN (Local Area Network).

The storage device 4 is a device external to the supervisory control system. The storage device 4 is, for example, a device of a business that owns the equipment 2. In the first embodiment, the business operator who owns the equipment 2 is a person other than the owner of the building where the equipment 2 is installed. The storage device 4 is communicatively connected to the supervisory control device 1A via a network. The storage device 4 transmits equipment ledger data stored in the storage device 4 to the monitoring and controlling device 1A in response to a request from the monitoring and controlling device 1A. The equipment ledger data will be described later. A plurality of storage devices 4 storing equipment ledger data regarding mutually different equipment 2 may be connected to the supervisory control device 1A. It is assumed that the number of storage devices 4 connected to the supervisory control device 1A is arbitrary. Note that the business owner of the equipment 2 may be the same as the owner of the building.

The monitoring control device 1A monitors the state of each of the plurality of facilities 2 by collecting signal data including signal values of signals representing the state of the facility 2 for each of the plurality of facilities 2. The monitoring control device 1A performs processing for visualizing and displaying the status of each facility 2, and transmits data for display to the terminal 3. The terminal 3 displays images representing the status of each facility 2. Further, the supervisory control device 1A generates a command according to the user's input operation on the terminal 3, and transmits the command to each facility 2. The supervisory control device 1A controls each piece of equipment 2 by transmitting a command to each piece of equipment 2.

The supervisory control device 1A identifies the correlation between the signals collected from the plurality of facilities 2 based on the signal ledger data stored inside the supervisory control device 1A. The signal ledger data will be described later. Further, the supervisory control device 1A reads equipment ledger data from the storage device 4, and identifies the correlation between the equipment 2 and the signal based on the signal ledger data. The supervisory control device 1A performs processing for displaying a network structure representing the certified correlation. The terminal 3 receives network structure data from the supervisory control device 1A and displays the network structure. Details of the network structure will be described later.

The supervisory control device 1A determines the degree of correlation between signals other than the signals for which correlation has been determined by learning based on signal data and signal ledger data. In addition, the supervisory control device 1A determines the degree of correlation between the equipment 2 and signals by learning based on signal data, signal ledger data, and equipment ledger data regarding equipment 2 and signals other than the equipment 2 and signals for which the correlation has been certified. seek. The supervisory control device 1A performs processing for displaying the calculated degree of correlation together with the network structure. The terminal 3 displays the degree of correlation as well as the network structure.

The terminal 3 accepts editing operations by the user. The editing operation is an operation for editing the correlation shown in the network structure. The supervisory control device 1A edits the display regarding the correlation in the network structure according to the editing operation.

FIG. 2 is a diagram illustrating a configuration example of the supervisory control device 1A according to the first embodiment. FIG. 2 shows a supervisory control device 1A and a storage device 4 connected to the supervisory control device 1A. The supervisory control device 1A includes a communication unit 10 that communicates with devices external to the supervisory control device 1A, a processing unit 11 that performs various processes, and a storage unit 12 that stores information. The processing section 11 includes a signal data collection section 13 , a correlation learning section 14 , a conversion processing section 15 , and a correlation editing section 16 .

A signal representing the state of the equipment 2 is transmitted from the equipment 2 or from a sensor that detects the state of the equipment 2 to the monitoring control device 1A. The sensors include sensors provided in the equipment 2 and sensors installed outside the equipment 2. The communication unit 10 successively receives signals representing the state of the equipment 2. The signal data collection unit 13 collects signal data including the signal value of a signal representing the state of the equipment 2 for each of the plurality of equipment 2 to be monitored and controlled. The signals to be collected by the signal data collection unit 13 include signals representing environmental conditions such as the temperature or humidity of the location where the equipment 2 is installed. The collected signal data is stored in the storage unit 12. The collected signal data includes information about the state of the controller that controls the equipment 2. For example, for an air conditioner, information about the on or off state of the air conditioner, information about the temperature setting, information about the operating mode, etc. may be included.

The correlation learning unit 14 reads out the signal ledger data stored in the storage unit 12, and determines the correlation between the signals included in the plurality of signals based on the signal ledger data. The correlation between the signals included in the plurality of signals is a relationship between the signals collected by the signal data collection unit 13, and is a relationship in which a change in the value of one signal causes a change in the value of the other signal. . The signal ledger data is data that summarizes signal attributes for each of a plurality of signals.

The correlation learning unit 14 acquires the equipment ledger data from the storage device 4, and identifies the correlation between the equipment 2 included in the plurality of equipment 2 based on the equipment ledger data. Alternatively, the correlation learning unit 14 recognizes the correlation between the equipment 2 included in the plurality of equipment 2 and the signal included in the plurality of signals based on the equipment ledger data. The correlation between equipment 2 is the relationship between a signal owned within one equipment 2 and a signal owned within the other equipment 2, and is linked to a change in the signal value of one equipment 2. This is a relationship in which the signal value changes. The correlation between the equipment 2 and the signals is the relationship between the signals owned within the equipment 2 and the signals collected by the signal data collection unit 13, and the correlation between the signals owned by the equipment 2 and the signals collected by the signal data collection unit 13 is linked to changes in the value of one signal. This is a relationship in which the signal value of changes. A signal owned within the equipment 2 is a signal that is monitored or generated within the equipment 2 for the purpose of controlling the equipment 2 . The signals owned within the equipment 2 include signals that are targets of collection by the signal data collector 13 and signals that are not targets of collection by the signal data collector 13.

FIG. 3 is a diagram for explaining the correlation certified by the supervisory control device 1A according to the first embodiment. FIG. 3 shows an example in which a chain of correlations between a plurality of equipment 2 and a plurality of signals is systematically developed and diagrammed. “XX Building” shown in FIG. 3 is an example of a building equipped with a plurality of facilities 2 that are monitored and controlled by the monitoring and control device 1A.

Power equipment and elevators are examples of equipment 2 provided in the XX building. The power equipment includes power receiving equipment, substation equipment, power distribution board A, power distribution board B, and power distribution board C equipment 2. The elevator includes each equipment 2 of a control panel and a landing operation panel. The platform operation panel includes each of the facilities 2, including a platform control panel installed on the first floor of the XX Building and a platform control panel installed on the second floor of the XX Building. Inside the distribution board A, a power consumption signal indicating the amount of power consumed by the distribution board A is owned. Inside the elevator, there are a number of passengers signal indicating the number of passengers in the elevator and a power consumption signal indicating the amount of power consumed by the elevator.

In the first embodiment, the correlation includes three relationships: a dependency relationship, an ownership relationship, and a connection relationship. A dependent relationship is a relationship between signals when control based on one signal changes the other signal. The ownership relationship is the relationship between the equipment 2 and the signals owned within the equipment 2. Connection relationships are relationships other than dependency relationships and ownership relationships. In FIG. 3, equipment 2 having a dependent relationship is represented by a solid line. Equipment 2 and signals that have an ownership relationship are represented by broken lines. Equipment 2 having a connection relationship is represented by a dashed line.

Since each of the power equipment and the elevator is controlled by the supervisory control device 1A provided in the XX building, there is a dependent relationship between the XX building and the power equipment, and there is a relationship between the XX building and the elevator. It can be said that there is a dependent relationship. The power equipment, the power receiving equipment, the substation equipment, the power distribution board A, the power distribution board B, and the power distribution board C constitute a hierarchical structure based on a dependent relationship. The distribution board A and the power consumption signal have an ownership relationship. The elevator, control panel, and landing operation panel form a hierarchical structure based on dependent relationships. There is an ownership relationship between the elevator and the signals for the number of passengers and power consumption.

It is assumed that the landing operation panel installed on the first floor is connected to the distribution board A and receives power from the distribution board A. In this case, the relationship between the distribution board A and the landing operation panel installed on the first floor is neither a dependent relationship nor an ownership relationship, and is therefore a connected relationship. The distribution board A and the landing operation panel installed on the first floor have a connection relationship. Since the landing operation panel installed on the second floor receives power from the distribution board B, the distribution panel B and the landing operation panel installed on the second floor have a connection relationship. Since the control panel receives power from the distribution panel C, the distribution panel C and the control panel have a connection relationship.

The correlation learning unit 14 identifies correlations that are obvious from the contents of the signal ledger data or the contents of the equipment ledger data by referring to the signal ledger data or the equipment ledger data. The correlation learning unit 14 outputs correlation data indicating the result of certifying the correlation. The correlation data is written to the storage unit 12.

The correlation learning unit 14 learns the correlation between signals in which the presence or absence of a correlation is not obvious in the signal ledger data or the equipment ledger data, and calculates the degree of correlation between the signals based on the learning result. The correlation learning unit 14 learns the correlation between the equipment 2 for which the presence or absence of correlation is not obvious in the signal ledger data or the equipment ledger data, and calculates the degree of correlation between the equipment 2 based on the learning result. calculate. The correlation learning unit 14 learns the correlation between the equipment 2 and the signal in which the presence or absence of the correlation is not obvious in the signal ledger data or the equipment ledger data, and calculates the degree of correlation between the equipment 2 and the signal based on the learning result. calculate.

The correlation learning unit 14 reads out the signal data stored in the storage unit 12, and calculates the degree of correlation between signals other than the signals whose correlation has been recognized by learning based on the signal data and the signal ledger data. That is, the correlation learning unit 14 determines the degree of correlation between the signals that represent the state of the equipment 2 and are collected by the signal data collection unit 13. For example, in the example shown in FIG. 3, it is assumed that the signal of the power consumption of the distribution board C and the signal of the power consumption of the control board are each collected by the signal data collection unit 13. In this case, the correlation learning unit 14 determines the degree of correlation between the power consumption signal of the distribution board C and the power consumption signal of the control panel.

Alternatively, the correlation learning unit 14 determines the degree of correlation between the equipment 2 included in the plurality of equipment 2 by learning based on signal data, signal ledger data, and equipment ledger data. The degree of correlation between the facilities 2 is the degree of correlation between a signal owned by one facility 2 and a signal owned by the other facility 2. For example, in the example shown in FIG. 3, the power consumption signal of distribution board A is a signal owned by distribution board A, and the signal indicating the number of passengers in an elevator is a signal owned by the elevator. do. In this case, the correlation learning unit 14 determines the degree of correlation between the power consumption signal of the distribution board A and the signal of the number of passengers in the elevator.

Alternatively, the correlation learning unit 14 determines the degree of correlation between the equipment 2 included in the plurality of equipment 2 and the signals included in the plurality of signals by learning based on signal data, signal ledger data, and equipment ledger data. That is, the correlation learning unit 14 determines the degree of correlation between the signals owned by the equipment 2 and the signals collected by the signal data collection unit 13. For example, in the example shown in FIG. Let the signal be collected. In this case, the correlation learning unit 14 determines the degree of correlation between the power consumption signal of the power distribution board A and the power consumption signal of the power distribution board C.

Here, learning by the correlation learning section 14 will be explained. Here, a case will be exemplified in which the degree of correlation between signals collected by the signal data collection unit 13 is determined. The correlation learning unit 14 observes a training data set including signal data and signal ledger data as a state variable. The correlation learning unit 14 learns, with respect to the signals collected by the signal data collection unit 13, the tendency of changes in one signal with respect to changes in the other signal, according to the training data set. The correlation learning unit 14 generates a model for calculating the degree of correlation, which is an index representing the tendency of changes in one signal with respect to changes in the other signal.

In the first embodiment, the degree of correlation is a numerical value representing whether or not the manner of change between signals is similar. The correlation value is a value that takes into account the presence or absence of a change in the other signal when one signal changes, and the difference in the fluctuation range of the other signal value with respect to the fluctuation range of one signal value. . The correlation learning unit 14 uses the generated model to calculate the degree of correlation from the input signal data and signal ledger data. In addition, the correlation learning unit 14 learns the main signal and the subordinate signal based on the tendency that the other signal changes with a delay from a change in one signal regarding signals having a dependent relationship. .

Any learning algorithm may be used by the correlation learning unit 14. As an example, a case will be described in which reinforcement learning is applied to the learning algorithm used by the correlation learning unit 14. Reinforcement learning is a method in which an agent in an environment observes the current state and decides what action to take. Agents obtain rewards from the environment by selecting actions, and through a series of actions, they learn strategies that will yield the most rewards. Q-learning, TD-learning, and the like are known as representative methods of reinforcement learning.

When determining the degree of correlation between equipment 2 included in a plurality of equipment 2, the correlation learning unit 14 observes a training data set including signal data, signal ledger data, and equipment ledger data as a state variable. The correlation learning unit 14 learns the tendency of the change in the other signal with respect to the change in one signal with respect to the signal owned by one equipment 2 and the signal owned by the other equipment 2 according to the training data set. . In addition, when determining the degree of correlation between the equipment 2 included in the plurality of equipment 2 and the signals collected by the signal data collection unit 13, the correlation learning unit 14 includes signal data, signal ledger data, and equipment ledger data. Observe the training dataset as a state variable. The correlation learning unit 14 learns the tendency of changes in one signal with respect to changes in the other signal, with respect to the signals owned by the equipment 2 and the signals collected by the signal data collection unit 13, according to the training data set.

The correlation learning unit 14 may perform learning using a sparse modeling method, for example. Learning algorithms other than reinforcement learning may be applied to the learning algorithm used by the correlation learning unit 14. Learning such as supervised learning or semi-supervised learning may be applied to the learning algorithm. The correlation learning unit 14 may perform machine learning using a learning algorithm such as deep learning, neural network, genetic programming, inductive logic programming, or support vector machine.

The conversion processing unit 15 reads the correlation data stored in the storage unit 12. The conversion processing unit 15 performs conversion processing on the correlation data to display the network structure. The network structure includes symbols representing the signals collected by the signal data collection unit 13 and symbols representing the equipment 2. In a network structure, symbols of one signal and symbols of the other signal are connected for signals having a correlation. In the network structure, for equipment 2 having a correlation, the symbol of one equipment 2 and the symbol of the other equipment 2 are connected. In the network structure, the symbol representing the equipment 2 and the symbol representing the signal are connected with respect to the equipment 2 and the signal that have a correlation. That is, in the network structure, regarding a plurality of signals and a plurality of facilities 2, the symbols of the signals having a correlation, the symbols of the facilities 2 having a correlation, the symbols of the facilities 2 having a correlation, and the symbols of the signals. are connected in a network.

In the correlation data, for signals included in a plurality of signals, the signal name of each signal and information indicating the presence or absence of a correlation are associated with each other. In the correlation data, for the equipment 2 included in the plurality of equipment 2, the equipment name of each equipment 2 and information indicating the presence or absence of correlation are associated. In the correlation data, for the equipment 2 included in the plurality of equipment 2 and the signals included in the plurality of signals, the signal name of the signal, the equipment name of the equipment 2, and information indicating the presence or absence of correlation are associated. There is. The conversion processing unit 15 converts the correlation data into, for example, a graph database data format. Note that the data format is not limited to a graph database. Correlation data may be converted to data formats other than graph databases.

By converting the correlation data into a network structure, the supervisory control device 1A can present the correlations to the user in an easy-to-understand manner even when a plurality of signals and a plurality of facilities 2 have complex correlations. can. Furthermore, when a hierarchical structure having a plurality of layers based on correlation is constructed, the supervisory control device 1A can present the hierarchical structure to the user in an easy-to-understand manner.

The correlation learning unit 14 outputs the result of determining the degree of correlation to the conversion processing unit 15. The conversion processing unit 15 performs processing for displaying the degree of correlation as well as the network structure. The correlation learning unit 14 outputs data on the network structure and data for displaying the degree of correlation. The communication unit 10 transmits data on the network structure and data for displaying the degree of correlation to the terminal 3 shown in FIG. The terminal 3 displays the network structure indicated in the received data. The terminal 3 displays the degree of correlation as well as the network structure.

The user instructs editing of the correlation in the network structure by operating the terminal 3 while checking the network structure and degree of correlation displayed on the terminal 3. The terminal 3 transmits a signal indicating the content of the editing operation to the supervisory control device 1A. When the communication unit 10 receives a signal indicating the content of the editing operation, the correlation editing unit 16 edits the correlation shown in the network structure according to the editing operation. The correlation editing unit 16 updates the correlation data by reflecting the edited correlation in the correlation data stored in the storage unit 12.

Next, details of the signal data collected by the supervisory control device 1A will be explained. FIG. 4 is a diagram showing an example of signal data collected in the supervisory control device 1A according to the first embodiment. FIG. 4 shows, as an example of signal data, signal values collected for the equipment 2 with the equipment name "A1" among the multiple equipment 2 that is the target of monitoring and control by the supervisory control device 1A, and the signal value collected for the equipment 2 with the equipment name "B1". ” indicates the signal value collected for equipment 2. Hereinafter, the equipment 2 with the equipment name "A1" will be referred to as equipment A1, and the equipment 2 with the equipment name "B1" will be referred to as equipment B1.

The signals with the signal names "a11", "a12", "a13", "a14", and "a15" are the signals to be collected by the signal data collection unit 13 for the equipment A1. Hereinafter, the signals with signal names "a11", "a12", "a13", "a14", and "a15" are referred to as signal a11, signal a12, signal a13, signal a14, and signal a15. The signals with the signal names "b11", "b12", "b13", and "b14" are the signals that are collected by the signal data collection unit 13 for the equipment B1. Hereinafter, the signals with signal names "b11", "b12", "b13", and "b14" are referred to as signal b11, signal b12, signal b13, and signal b14.

The signal data includes at least a timestamp, which is date and time information when the supervisory control device 1A acquired the signal value, a signal name, and a signal value. In the example shown in FIG. 4, the signal data includes the equipment name. In the example shown in FIG. 4, the signal value is a numerical value or information indicating the on or off state of the signal. The signal data may include information other than the information used to recognize the correlation in the first embodiment or information other than the information used to learn the degree of correlation in the first embodiment.

Next, details of the signal ledger data stored in the supervisory control device 1A will be explained. FIG. 5 is a diagram showing an example of signal ledger data stored in the supervisory control device 1A according to the first embodiment. The signal ledger data is a database held in the supervisory control device 1A in order for the supervisory control device 1A to manage signals input from a plurality of facilities 2.

The signal ledger data includes at least a signal name and information indicating the data type of the signal value. In the example shown in FIG. 5, the signal ledger data includes information indicating the type of equipment 2, a floor name, a distribution board ID, an equipment ID, and notes. The floor name is the name of the floor where the equipment 2 is installed. The distribution board ID is an identifier attached to a distribution board that supplies power to the equipment 2. The equipment ID is an identifier given to the equipment 2. Supplementary information about the signal is described in the remarks section. The supplementary information may be information about the signal's unique arrangements or information about the object being monitored by the signal. The correlation learning unit 14 identifies the ownership relationship between the equipment 2 and the signals owned within the equipment 2 based on the signal name and equipment ID included in the signal ledger data. The signal ledger data may include information other than the information used to recognize the correlation in Embodiment 1, or information other than the information used to learn the degree of correlation in Embodiment 1. .

Next, details of the equipment ledger data input to the supervisory control device 1A will be explained. FIG. 6 is a diagram showing an example of equipment ledger data input to the monitoring and control device 1A according to the first embodiment. The equipment ledger data is a database compiled by the owner of the equipment 2 for the purpose of constructing the equipment 2 installed in the building. The equipment ledger data may be updated in response to maintenance such as replacement of the equipment 2.

The equipment ledger data includes at least an equipment name and an equipment ID. In the example shown in FIG. 6, the equipment ledger data includes information indicating the type of equipment 2, a floor name, a distribution board ID, and information on a collection protocol. The collection protocol information is information about the communication standard for collecting signals. The equipment ledger data may include information other than the information used to recognize the correlation in Embodiment 1, or information other than the information used to learn the degree of correlation in Embodiment 1. . The correlation learning unit 14 may recognize the ownership relationship between the equipment 2 and the signals owned within the equipment 2 based on the signal ledger data and the equipment ledger data.

Next, details of the network structure will be explained. FIG. 7 is a diagram showing an example of a network structure converted from correlation data by the supervisory control device 1A according to the first embodiment. In the network structure shown in FIG. 7, the symbol representing equipment 2 is an ellipse with the equipment name written thereon. The symbol representing a signal is an ellipse with the signal name written on it. In the network structure shown in FIG. 7, the arrow with the character string "has" represents the ownership relationship between the equipment 2 and the signal. In the example of the network structure shown in FIG. 7, equipment A1 has an ownership relationship with each of the signals a11, a12, a13, a14, and a15, and equipment B1 has an ownership relationship with each of the signals b11, b12, b13, and b14. It means having.

Next, the display of the degree of correlation and the editing of the displayed correlation will be explained. FIG. 8 is a diagram for explaining the display of the correlation degree by the processing of the supervisory control device 1A according to the first embodiment and the editing of the correlation by the supervisory control device 1A. FIG. 8 shows an example of a screen displayed on the terminal 3. In the example shown in FIG. 8, in addition to the display of the network structure shown in FIG. 7, the degree of correlation between equipment A1 and equipment B1 is displayed.

A broken line connecting the symbol of equipment A1 and the symbol of equipment B1 is an object indicating that the correlation degree is to be calculated. Moreover, a character string "correlation degree 56.7%" indicating the calculation result of the correlation degree between equipment A1 and equipment B1 is attached to the broken line. The user can judge whether there is a correlation between the equipment A1 and the equipment B1 by referring to the display regarding the degree of correlation between the equipment A1 and the equipment B1.

The display of the degree of correlation may be any display that allows the user to recognize the height of the degree of correlation, and is not limited to the display of the value of the degree of correlation. The display of the degree of correlation may be, for example, a display of objects in which the height of the degree of correlation is expressed by color classification or color shading.

When a signal symbol is selected by the user from the network structure displayed on the screen, a graph representing the transition of the signal value for the selected signal is displayed on the screen. In the example shown in FIG. 8, when the signal b14 is selected, a graph showing the transition of the signal value for the signal b14 is displayed. The vertical axis of the graph represents signal values, and the horizontal axis of the graph represents time. The user can check the transition of signal values by selecting any signal from the network structure. The user can check whether there is an abnormality in the signal value from the change in the signal value. Furthermore, if an abnormality occurs, the user can confirm the time point at which the abnormality occurred.

When the signal b14 is selected, the symbol of the signal b14 is displayed in a different color from the other symbols so that it can be distinguished from the other symbols. The symbol of the selected signal is not limited to being displayed in a different color from other symbols, but may be displayed in a manner that allows it to be distinguished from other symbols.

When the user determines that there is a correlation between equipment A1 and equipment B1, the user performs an editing operation to add a correlation between equipment A1 and equipment B1 in the network structure. The correlation editing unit 16 adds information indicating the correlation between the equipment A1 and the equipment B1 to the correlation data stored in the storage unit 12 in response to an editing operation for adding a correlation. . The information indicating the correlation added by the editing operation is attached with information for identifying it from the correlation determined to be obvious from the signal ledger data or the equipment ledger data. In the network structure displayed on the screen of the terminal 3, correlations added by editing operations are displayed so as to be distinguishable from correlations determined to be obvious. An object indicating a correlation added by an editing operation is a different object from an object indicating a correlation determined to be obvious. For example, an object indicating a correlation determined to be obvious is a solid arrow, and a correlation added by an editing operation is a dashed arrow.

The user can also perform an editing operation to delete added correlations. The correlation editing unit 16 deletes information indicating the correlation to be deleted from the correlation data in response to an editing operation for deleting the correlation.

The supervisory control device 1A may record the history of editing by the correlation editing unit 16. If each of a plurality of users can perform an editing operation, the editing history may include information about the user who performed the editing. By checking the editing history, the user can perform editing work by utilizing the contents of past editing. If there was an error in past editing, you can check the editing history at the time of the error. Furthermore, by checking the editing history, it is possible to check whether or not there has been any tampering. The editing history may be stored in a device external to the supervisory control device 1A.

If each of a plurality of users can perform an editing operation, the correlation added by the editing operation may be weighted according to the user. Weighting is set for each user based on preset conditions regarding the user's attributes, such as a management company with specialized knowledge or the owner of a building or equipment 2, etc., and the upper weighting is set. Correlation input and determined by a certain user may be set with priority.

Next, the operation of the supervisory control device 1A will be explained. FIG. 9 is a flowchart showing the operation procedure of the supervisory control device 1A according to the first embodiment.

In step S1, the supervisory control device 1A collects signal data in the signal data collection unit 13. The collected signal data is stored in the storage unit 12.

In step S2, the supervisory control device 1A determines in the correlation learning unit 14 whether correlation data is stored in the storage unit 12. If the correlation data is stored (step S2, Yes), the supervisory control device 1A advances the procedure to step S3. If the correlation data is not stored (step S2, No), the supervisory control device 1A advances the procedure to step S4.

In step S4, the supervisory control device 1A causes the correlation learning unit 14 to perform new learning of the correlation. The correlation learning unit 14 reads signal ledger data from the storage unit 12. Further, the correlation learning unit 14 acquires equipment ledger data from the storage device 4. The correlation learning unit 14 identifies the correlation between signals based on the signal ledger data. The correlation learning unit 14 identifies the correlation between the pieces of equipment 2 based on the equipment ledger data. The correlation learning unit 14 identifies the correlation between the equipment 2 and the signal based on the equipment ledger data. The correlation learning unit 14 outputs correlation data indicating the certification result to the storage unit 12. Further, the correlation learning unit 14 learns the correlation between signals, and calculates the degree of correlation between the signals based on the learning result. The correlation learning unit 14 learns the correlation between the equipment 2 and calculates the degree of correlation between the equipment 2 based on the learning result. The correlation learning unit 14 learns the correlation between the equipment 2 and the signal, and calculates the degree of correlation between the equipment 2 and the signal based on the learning result.

In step S3, the supervisory control device 1A causes the correlation learning unit 14 to relearn the correlation. The correlation learning unit 14 re-certifies the correlation between signals based on the signal ledger data. The correlation learning unit 14 re-certifies the correlation between the equipment 2 based on the equipment ledger data. The correlation learning unit 14 recertifies the correlation between the equipment 2 and the signal based on the equipment ledger data. The correlation learning unit 14 outputs correlation data indicating the certification result to the storage unit 12. Further, the correlation learning unit 14 relearns the correlation between the signals, and calculates the degree of correlation between the signals based on the result of the relearning. The correlation learning unit 14 relearns the correlation between the pieces of equipment 2 and calculates the degree of correlation between the pieces of equipment 2 based on the result of the relearning. The correlation learning unit 14 relearns the correlation between the equipment 2 and the signal, and calculates the degree of correlation between the equipment 2 and the signal based on the relearning result.

In step S5 after step S3 or step S4, the monitoring and control device 1A causes the conversion processing unit 15 to execute a conversion process on the correlation data. The conversion processing unit 15 performs conversion processing on the correlation data to display the network structure. The conversion processing unit 15 also performs processing for displaying the degree of correlation as well as the network structure.

In step S6, the supervisory control device 1A transmits network structure data, which is data indicating the network structure, to the terminal 3. The supervisory control device 1A transmits data for displaying the degree of correlation to the terminal 3 along with the network structure data. The terminal 3 displays the network structure indicated by the network structure data on the screen. Further, the terminal 3 displays the degree of correlation according to the data for displaying the degree of correlation.

The correlation editing unit 16 reads correlation data from the storage unit 12. In step S7, the supervisory control device 1A determines in the correlation editing unit 16 whether an editing operation has been performed on the terminal 3. If there is an editing operation (step S7, Yes), the supervisory control device 1A advances the procedure to step S8. If there is no editing operation (step S7, No), the supervisory control device 1A advances the procedure to step S9.

In step S8, the supervisory control device 1A uses the correlation editing unit 16 to edit the correlation shown in the network structure according to the editing operation, and stores the correlation data in which the edited content is reflected in the storage unit 12. The correlation editing unit 16 reflects the edited content on the correlation data read from the storage unit 12 and writes the correlation data reflecting the edited content into the storage unit 12.

In step S9, the supervisory control device 1A stores the correlation data in the storage unit 12 by the correlation editing unit 16. The correlation editing unit 16 writes the read correlation data to the storage unit 12 as is without making any changes to the correlation data read from the storage unit 12. The supervisory control device 1A completes the operation according to the procedure shown in FIG. 9 by completing step S8 or step S9.

According to the first embodiment, the supervisory control device 1A identifies the correlation between the signals that are the targets of collection in the signal data collection unit 13 based on the signal ledger data. The supervisory control device 1A determines the degree of correlation between signals through learning based on the collected signal data and signal ledger data. Furthermore, the supervisory control device 1A identifies the correlation between the equipment 2 or the correlation between the equipment 2 and the signal based on the equipment ledger data. The supervisory control device 1A determines the degree of correlation between the pieces of equipment 2 or the degree of correlation between the pieces of equipment 2 and the signal through learning based on the collected signal data, signal ledger data, and equipment ledger data.

Even if the user does not have specialized knowledge about the hierarchical structure consisting of multiple pieces of equipment 2 and multiple signals, the supervisory control device 1A can calculate correlations based on signal data, signal ledger data, and equipment ledger data. can be presented. Furthermore, since there is no need to predetermine rules for specifying the hierarchy of each piece of equipment 2, the supervisory control device 1A can present correlations when the hierarchical structure deviates from predetermined rules. It is possible to avoid the situation where it is not possible. As described above, the supervisory control device 1A has the effect of being able to present the correlation between signals representing the state of the equipment 2. Moreover, the supervisory control device 1A has the effect of being able to present the correlation between the equipment 2 or the correlation between the equipment 2 and a signal.

Embodiment 2.
FIG. 10 is a diagram illustrating a configuration example of a supervisory control device 1B according to the second embodiment. FIG. 10 shows a supervisory control device 1B and a storage device 4 connected to the supervisory control device 1B. The supervisory control device 1B includes the same configuration as the supervisory control device 1A according to the first embodiment, and a label creation section 17. In Embodiment 2, the same components as in Embodiment 1 described above are given the same reference numerals, and configurations that are different from Embodiment 1 will be mainly explained.

The label creation unit 17 automatically creates a label representing an attribute of a signal when displaying a graph representing a change in a signal representing the state of the equipment based on the correlation data. In the terminal 3, two or more signals are narrowed down from among the plurality of signals to be collected by the signal data collection unit 13, and graphs representing each of the narrowed down signals are displayed at the same time. The label represents an attribute used to narrow down the signal.

The label creation unit 17 reads correlation data from the storage unit 12. The label creation unit 17 determines an attribute to be used as a label based on the correlation between the signals shown in the correlation data. The label creation unit 17 may perform clustering of signals and determine an attribute that is common to signals determined to belong to the same cluster as an attribute to be used as a label.

For example, when displaying a graph of power consumption for each floor of a building, the labels are power consumption and building floor. When displaying a graph of power consumption for each type of equipment 2, the labels are the power consumption and the type of equipment 2. When displaying a graph of power consumption for each rated voltage of equipment 2, the labels are the power consumption and the rated voltage of equipment 2.

Here, an example of a method for automatically creating a label based on correlation data will be described. For example, it is assumed that a common keyword is included in the signal name of each signal that has a correlation with each other. The label creation unit 17 determines that the common keyword is an attribute that is used as a label. As a method for determining whether a common keyword is included, first, the signal name of each signal is divided into words of character strings shorter than the signal name. For example, natural language processing techniques such as morphological analysis can be applied to signal name division. Next, by evaluating the similarity of the character strings for each divided word, it is determined whether a common keyword is included. For example, a method such as the Levenshtein distance method or Gestalt pattern matching can be applied to evaluate the similarity of character strings. The label creation unit 17 can automatically create a label by extracting words determined to be common keywords from the signal names.

FIG. 11 is a diagram showing a first example of a graph displayed according to the second embodiment. The first example shown in FIG. 11 is an example of a graph showing changes in power consumption for each floor of a building. In the first example, the graph representing the change in power consumption on the entire first floor of the building and the graph representing the change in power consumption on the entire second floor of the building use the same vertical and horizontal axes. will be displayed. That is, graphs of power consumption on each floor are displayed simultaneously.

FIG. 12 is a diagram showing a second example of a graph displayed according to the second embodiment. The second example shown in FIG. 12 is an example of a graph showing changes in power consumption for each type of equipment 2. In the second example, the graph showing the change in power consumption of all the electric power equipment installed in the building and the graph showing the change in power consumption of all the elevators installed in the building are the same. Displayed using vertical and horizontal axes. That is, graphs of power consumption of each type of equipment 2 are displayed at the same time.

The displayed graph may be switchable by selecting a label from a list of multiple labels. FIG. 13 is a diagram for explaining graph switching in the second embodiment. FIG. 13 shows an example of a pull-down menu displayed on the screen of the terminal 3 when a label is selected. The pull-down menu shown in FIG. 13 is displayed by the user's operation on the terminal 3. The example shown in FIG. 13 is an example of a pull-down menu for further narrowing down the labels when displaying a graph of power consumption. In FIG. 13, the "by floor" option represents the floor of the building. The “by voltage” option represents the rated voltage of the equipment 2. The option “by use” represents the type of equipment 2.

Each of the plurality of labels that are options is created by the label creation unit 17. When the user selects a label as an option from the pull-down menu, a graph corresponding to the selected label is displayed on the screen. In addition. Means other than a pull-down menu may be used to select a label.

According to the second embodiment, the supervisory control device 1B can eliminate the need for the user's manual work to create labels by automatically creating labels based on correlation data.

Embodiment 3.
FIG. 14 is a diagram illustrating a configuration example of a supervisory control device 1C according to the third embodiment. FIG. 14 shows a supervisory control device 1C and a storage device 4 connected to the supervisory control device 1C. The supervisory control device 1C includes the same configuration as the supervisory control device 1A according to the first embodiment, and an abnormality detection section 18. In Embodiment 3, the same components as in Embodiment 1 or 2 described above are given the same reference numerals, and configurations that are different from Embodiment 1 or 2 will be mainly explained.

The calculation result of the degree of correlation by the correlation learning unit 14 is input to the abnormality detection unit 18 . The anomaly detection unit 18 monitors the calculation result of the correlation degree by the correlation learning unit 14. The abnormality detection unit 18 may obtain past calculation results of the degree of correlation from the correlation data stored in the storage unit 12. The anomaly detection unit 18 detects an abnormality in the tendency of a change in one signal relative to a change in the other signal with respect to the signals that are the targets of collection by the signal data collection unit 13, based on a change in the calculation result of the degree of correlation. Detection based on Thereby, the abnormality detection unit 18 automatically detects the equipment 2 or the signal that is an element indicating abnormal behavior among the correlations that are grasped in advance.

The abnormality detection unit 18 detects an abnormality, for example, when the fluctuation range of the correlation degree calculation result exceeds a preset threshold. When detecting an abnormality, the abnormality detection unit 18 outputs an alert indicating that an abnormality has occurred. The communication unit 10 transmits the alert output by the abnormality detection unit 18 to the terminal 3. When the terminal 3 receives the alert, it displays the alert on the screen. For example, the terminal 3 displays on the screen a message instructing inspection of the element in which an abnormality has been detected. This enables immediate response to abnormalities.

The abnormalities detected by the abnormality detection unit 18 include abnormalities caused by troubles such as a failure of the equipment 2, a disconnection, clogging of piping, or water leakage. The abnormality detected by the abnormality detection unit 18 is not limited to one caused by trouble. For example, a case where there is a change that cannot be confirmed from various data that can be obtained by the monitoring and control device 1C, such as a case where the connection mode of a plurality of facilities 2 and a plurality of signals is changed, is also included in the abnormality.

According to the third embodiment, the supervisory control device 1C automatically detects an abnormality in the tendency of a change in one signal to a change in the other signal based on a change in the calculation result of the degree of correlation. Early detection of abnormalities becomes possible. The user can quickly respond to abnormalities.

Embodiment 4.
FIG. 15 is a diagram illustrating a configuration example of the supervisory control device 1D according to the fourth embodiment. FIG. 15 shows a supervisory control device 1D and a storage device 4 connected to the supervisory control device 1D. The supervisory control device 1D includes the same configuration as the supervisory control device 1A according to the first embodiment, and a network structure learning section 19. In Embodiment 4, the same components as in Embodiments 1 to 3 described above are given the same reference numerals, and configurations that are different from Embodiments 1 to 3 will be mainly explained.

The network structure learning unit 19 learns characteristics of a plurality of network structures. The supervisory control device 1D collects correlation data for each site, such as each of a plurality of buildings or each of a plurality of floors within a building. The collected correlation data is stored in the storage unit 12. The network structure learning unit 19 uses the collected correlation data to learn a characteristic structure from the network structure shown in each correlation data. The network structure learning unit 19 estimates the network structure of a site other than the site where the correlation data was collected based on the learning results.

The characteristics of the network structure that the network structure learning unit 19 learns include the configuration of the hierarchical structure or the tendency of correlation. For example, the network structure learning unit 19 learns a rule that signals having a specific character string in their signal names have a dependent relationship from the collected correlation data. Based on the result of the learning, the network structure learning unit 19 verifies whether the rule holds true even in a field where the correlation between signals is not understood.

The network structure learning unit 19 may estimate correlations that are not understood at a certain site based on correlations determined by network structures at other sites. Here, an example of estimating an unknown correlation will be described. “Building X” and “Building Y” are each buildings included in a plurality of buildings. The signal ledger data of "Building X" indicates that a signal collection device is installed for each communication protocol, and the network structure of "Building Assume that an ownership relationship is established. On the other hand, in "Building Y", a signal collection device is provided for each communication protocol, but it is assumed that the signal collection device is treated as one of the plurality of facilities 2. In such a case, the network structure learning unit 19 estimates that the ownership relationship between the signal collection device of “Building X” and equipment 2 also holds true between the signal collection device of “Building Y” and equipment 2.

Based on this estimation, the network structure learning unit 19 determines that the ownership relationship in which the signal collecting device owns the equipment 2 corresponding to the communication protocol of the signal collecting device is between the signal collecting device of “Building Y” and the equipment 2. The user of the supervisory control device 1D installed in "Building Y" is inquired as to whether this holds true. If the user who received the inquiry approves that the ownership relationship is established, the network structure learning unit 19 makes a correction to add the ownership relationship in which the signal collection device owns the equipment 2 to the correlation data of "Building Y". conduct. In this manner, the network structure learning unit 19 corrects the correlation data after confirming that the correlation holds true by estimating the correlation.

According to the fourth embodiment, the supervisory control device 1D learns the characteristics of a plurality of network structures, and uses the learning results to identify the network structure of a site other than the site where the correlation data was collected. can do.

As an application of the fourth embodiment, a cloud center connected to a plurality of supervisory control devices 1D may be provided, and the cloud center may collect rules obtained through learning by each supervisory control device 1D regarding the characteristics of the network structure. . The cloud center may systematize the collected rules and distribute the systemized rules to each monitoring control device 1D. Thereby, each supervisory control device 1D can specify the network structure based on the systemized rules.

Embodiment 5.
FIG. 16 is a diagram illustrating a configuration example of a supervisory control device 1E according to the fifth embodiment. The supervisory control device 1E receives inspection and maintenance data regarding a plurality of pieces of equipment 2, and learns the degree of correlation between items of the inspection and maintenance data and signals. In Embodiment 5, the same components as those in Embodiments 1 to 4 described above are given the same reference numerals, and configurations that are different from Embodiments 1 to 4 will be mainly described. The inspection and maintenance data includes at least one of the results of inspecting the equipment 2 and the results of performing maintenance work on the equipment 2. Maintenance work includes all work performed to continue using the equipment 2, such as repair, parts replacement, and cleaning. Hereinafter, inspection and maintenance refers to at least one of inspection and maintenance.

The storage device 5 is a device external to the supervisory control system. The storage device 5 is, for example, a device of a company that performs inspection and maintenance on a plurality of facilities 2. In the first embodiment, the business operator who performs inspection and maintenance is a person other than the owner of the building in which the equipment 2 is installed. The storage device 5 is communicatively connected to the supervisory control device 1E via a network. The storage device 5 transmits inspection and maintenance data stored in the storage device 5 to the monitoring and control device 1E in response to a request from the monitoring and control device 1E. FIG. 16 shows a supervisory control device 1E, a storage device 4 connected to the supervisory control device 1E, and a storage device 5 connected to the supervisory control device 1E.

The correlation learning unit 14 performs learning similar to that in the first embodiment. In the fifth embodiment, the correlation learning unit 14 further determines the degree of correlation between the inspection and maintenance items and the signal representing the state of the equipment 2 by learning based on the inspection and maintenance data and the signal data.

The correlation learning unit 14 acquires inspection and maintenance data from the storage device 5. The correlation learning unit 14 observes a training data set including signal data and inspection/maintenance data as a state variable. The correlation learning unit 14 learns the tendency of signal changes with respect to changes in the contents of inspection and maintenance items according to the training data set. The correlation learning unit 14 generates a model for calculating the degree of correlation, which is an index representing the tendency of signal changes with respect to changes in the contents of inspection and maintenance items. The correlation learning unit 14 outputs the result of determining the degree of correlation between the inspection and maintenance items and the signal to the conversion processing unit 15.

The conversion processing unit 15 performs processing for displaying the degree of correlation, as in the first embodiment. In the fifth embodiment, the conversion processing unit 15 further performs processing for displaying the degree of correlation between inspection and maintenance items and signals. On the screen of the terminal 3, in addition to the same display as in the first embodiment, a display regarding the degree of correlation between inspection and maintenance items and signals is added.

When the user determines that there is a correlation between the inspection and maintenance item and the signal, the user performs an editing operation to add the correlation between the inspection and maintenance item and the signal in the network structure. The correlation editing unit 16 adds information indicating the correlation between the inspection and maintenance items and the signal to the correlation data stored in the storage unit 12 in response to an editing operation for adding a correlation. do.

According to the fifth embodiment, the supervisory control device 1E determines the degree of correlation between inspection and maintenance items and signals representing the state of the equipment 2 by learning based on inspection and maintenance data and signal data. Therefore, when an abnormality is found in the collected signal data, the user can search for the cause of the abnormality by considering inspection and maintenance items. In addition, by adding a display regarding the degree of correlation between inspection and maintenance items and signals, users can determine that an abnormality may have occurred when a change is observed in the signal, and perform inspection. You can request maintenance.

The supervisory control device 1E outputs an alert prompting inspection and maintenance when the fluctuation range of the signal value exceeds a preset threshold for inspection and maintenance items and signals for which a correlation has been added to the network structure. Also good. The communication unit 10 transmits the alert output by the abnormality detection unit 18 to the terminal 3. When the terminal 3 receives the alert, it displays the alert on the screen. For example, the terminal 3 displays on the screen a message instructing inspection of the element in which an abnormality has been detected. This enables immediate response to abnormalities.

Next, the hardware configurations of the supervisory control devices 1A, 1B, 1C, 1D, and 1E according to the first to fifth embodiments will be described. FIG. 17 is a diagram showing an example of the hardware configuration of the supervisory control devices 1A, 1B, 1C, 1D, and 1E according to the first to fifth embodiments. The supervisory control devices 1A, 1B, 1C, 1D, and 1E are realized by computer systems including a processing circuit 30 and a communication device 31. Processing circuit 30 includes a processor 32 and memory 33. Processing circuit 30 is a circuit on which processor 32 executes software.

The processing units 11 of the supervisory control devices 1A, 1B, 1C, 1D, and 1E are realized by software, firmware, or a combination of software and firmware. Software or firmware is written as a program and stored in memory 33. In the processing circuit 30, each function of the processing section 11 is realized by the processor 32 reading out and executing the monitoring control program, which is the program stored in the memory 33. That is, the processing circuit 30 includes a memory 33 for storing a supervisory control program that results in the processing of the supervisory control devices 1A, 1B, 1C, 1D, and 1E being executed. It can also be said that the supervisory control program causes a computer to execute the procedures and methods of the supervisory control devices 1A, 1B, 1C, 1D, and 1E.

The processor 32 is a CPU (Central Processing Unit, also referred to as a central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, processor, or DSP (Digital Signal Processor)). The memory 33 is a nonvolatile memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), and EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory). Alternatively, volatile semiconductor memory, magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disc), etc. are applicable. The storage unit 12 of the supervisory control devices 1A, 1B, 1C, 1D, and 1E is realized by a memory 33. The communication unit 10 of the supervisory control devices 1A, 1B, 1C, 1D, and 1E is realized by a communication device 31. Note that the supervisory control devices 1A, 1B, 1C, 1D, and 1E may include integrated circuits such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array). The supervisory control program may be stored in a recording medium such as a CD (Compact Disc)-ROM or DVD-ROM, and the recording medium may be provided to realize each embodiment.

The supervisory control devices 1A, 1B, 1C, 1D, and 1E may be composed of two or more devices, for example, two or more servers. The monitoring and control devices 1A, 1B, 1C, 1D, and 1E may be composed of a processing server and a data server. When the supervisory control devices 1A, 1B, 1C, 1D, and 1E are composed of two or more devices, each of the two or more devices has the hardware configuration shown in FIG. 17, for example. Note that communication between two or more devices is performed via the communication device 31.

The terminal 3 is realized by a hardware configuration similar to that shown in FIG. 17. The terminal 3 further includes an input device operated by a user and a display device that displays a screen. Input devices include, for example, a keyboard, mouse, keypad, or touch panel. The display device is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

The configurations shown in each of the embodiments above are examples of the contents of the present disclosure. The configuration of each embodiment can be combined with other known techniques. The configurations of each embodiment may be combined as appropriate. It is possible to omit or change a part of the configuration of each embodiment without departing from the gist of the present disclosure.

Hereinafter, various aspects of the present disclosure will be collectively described as supplementary notes.

(Additional note 1)
a signal data collection unit that collects signal data including a signal value of a signal representing a state of the equipment for each of the plurality of equipment to be monitored and controlled;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The desired correlation learning section,
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a conversion processing unit that performs processing;
a correlation editing unit that edits the correlation shown in the network structure according to an editing operation;
A supervisory control device comprising:

(Additional note 2)
The correlation learning unit acquires equipment ledger data that summarizes the attributes of the equipment for each of the plurality of equipment, and learns the correlation between the equipment included in the plurality of equipment, or the correlation between the equipment included in the plurality of equipment. The monitoring and control device according to Supplementary Note 1, characterized in that the correlation between the equipment and the signals included in the plurality of signals is certified based on the equipment ledger data.

(Additional note 3)
The correlation learning unit calculates the degree of correlation between equipment included in the plurality of equipment, or the degree of correlation between the equipment included in the equipment and the signal included in the plurality of signals, based on the signal data. The monitoring and control device according to appendix 2, wherein the monitoring control device is obtained by learning based on the signal ledger data and the equipment ledger data.

(Additional note 4)
The correlation includes a dependent relationship, which is a relationship between signals when control based on one signal changes another signal, and an ownership relationship, which is a relationship between the equipment and the signals owned within the equipment. 4. The supervisory control device according to any one of Supplementary Notes 1 to 3, characterized in that the monitoring and control device includes a relationship, and a connection relationship that is a relationship other than the dependent relationship and the ownership relationship.

(Appendix 5)
From Supplementary Note 1, further comprising a label creation unit that automatically creates a label representing an attribute of the signal based on the correlation data when displaying a graph representing a change in the signal representing the state of the equipment. 4. The supervisory control device according to any one of 4.

(Appendix 6)
Supplementary Notes 1 to 4, further comprising an abnormality detection unit that detects an abnormality in the tendency of a change in one signal to a change in the other signal based on a change in the calculation result of the correlation degree. The monitoring control device according to any one of the above.

(Appendix 7)
5. The supervisory control device according to any one of Supplementary Notes 1 to 4, further comprising a network structure learning unit that learns characteristics of a plurality of network structures.

(Appendix 8)
The correlation learning unit further learns inspection or maintenance items by learning based on the signal data and inspection and maintenance data including at least one of the results of inspecting the equipment and the results of maintenance work on the equipment. 5. The monitoring and control device according to any one of Supplementary Notes 1 to 4, characterized in that the degree of correlation between the signal and the signal representing the state of the equipment is determined.

(Appendix 9)
A supervisory control method for monitoring and controlling each of a plurality of facilities using a supervisory control device, the method comprising:
collecting, for each of the plurality of facilities, signal data including a signal value of a signal representing a state of the facility;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The steps you are looking for and
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a step of processing;
editing the correlation shown in the network structure according to an editing operation;
A supervisory control method characterized by comprising:

(Appendix 10)
In the step of outputting the correlation data and determining the degree of correlation by the learning, equipment ledger data summarizing the attributes of the equipment is acquired for each of the plurality of equipment, and equipment included in the plurality of equipment is acquired. Supplementary Note 9, characterized in that the correlation between equipment or the correlation between equipment included in a plurality of the equipment and signals included in a plurality of the signals is certified based on the equipment ledger data. Supervisory control method.

(Appendix 11)
In the step of outputting the correlation data and determining the degree of correlation by the learning, the degree of correlation between the equipment included in the plurality of equipment, or the correlation between the equipment included in the plurality of equipment and the plurality of the equipment is determined. 11. The monitoring control method according to appendix 10, wherein the degree of correlation with the signal included in the signal is determined by learning based on the signal data, the signal ledger data, and the equipment ledger data.

(Appendix 12)
The correlation includes a dependent relationship, which is a relationship between signals when control based on one signal changes another signal, and an ownership relationship, which is a relationship between the equipment and the signals owned within the equipment. 12. The supervisory control method according to any one of appendices 9 to 11, characterized in that the method includes a relationship and a connection relationship that is a relationship other than the dependent relationship and the ownership relationship.

(Appendix 13)
Supplementary notes 9 to 12, characterized in that the method includes a step of automatically creating a label representing an attribute of the signal when displaying a graph representing a change in the signal representing the state of the equipment based on the correlation data. The monitoring control method according to any one of the above.

(Appendix 14)
Any one of appendices 9 to 12, characterized in that the method includes the step of detecting an abnormality in the tendency of a change in one of the signals relative to a change in the other signal based on a change in the calculation result of the degree of correlation. 1. The monitoring control method according to item 1.

(Appendix 15)
13. The supervisory control method according to any one of appendices 9 to 12, comprising the step of learning characteristics of a plurality of the network structures.

(Appendix 16)
In the step of outputting the correlation data and determining the degree of correlation by the learning, the step further includes inspection and maintenance data including at least one of the results of inspecting the equipment and the results of maintenance work for the equipment. 13. The supervisory control method according to any one of appendices 9 to 12, characterized in that the degree of correlation between an inspection or maintenance item and a signal representing the state of the equipment is determined by learning based on the signal data.

(Appendix 17)
Collecting signal data including a signal value of a signal representing a state of the equipment for each of the plurality of equipment to be monitored and controlled;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The steps you are looking for and
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a step of processing;
editing the correlation shown in the network structure according to an editing operation;
A supervisory control program that causes a computer to execute.

1A, 1B, 1C, 1D, 1E supervisory control device, 2 equipment, 3 terminal, 4, 5 storage device, 10 communication section, 11 processing section, 12 storage section, 13 signal data collection section, 14 correlation learning section, 15 Conversion processing section, 16 Correlation editing section, 17 Label creation section, 18 Anomaly detection section, 19 Network structure learning section, 30 Processing circuit, 31 Communication device, 32 Processor, 33 Memory.

Claims (17)

a signal data collection unit that collects signal data including a signal value of a signal representing a state of the equipment for each of the plurality of equipment to be monitored and controlled;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The desired correlation learning section,
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a conversion processing unit that performs processing;
a correlation editing unit that edits the correlation shown in the network structure according to an editing operation;
A supervisory control device comprising: The correlation learning unit acquires equipment ledger data that summarizes the attributes of the equipment for each of the plurality of equipment, and learns the correlation between the equipment included in the plurality of equipment, or the correlation between the equipment included in the plurality of equipment. The monitoring and control device according to claim 1, wherein a correlation between equipment and signals included in the plurality of signals is recognized based on the equipment ledger data. The correlation learning unit calculates the degree of correlation between equipment included in the plurality of equipment, or the degree of correlation between the equipment included in the equipment and the signal included in the plurality of signals, based on the signal data. 3. The monitoring and control device according to claim 2, wherein the information is determined by learning based on the signal ledger data and the equipment ledger data. The correlation includes a dependent relationship, which is a relationship between signals when control based on one signal changes another signal, and an ownership relationship, which is a relationship between the equipment and the signals owned within the equipment. 3. The supervisory control device according to claim 1, further comprising a relationship and a connection relationship that is a relationship other than the dependent relationship and the ownership relationship. Claim 1, further comprising a label creation unit that automatically creates a label representing an attribute of the signal when displaying a graph representing a change in the signal representing a state of the equipment based on the correlation data. Or the monitoring control device according to 2. 3. The apparatus of claim 1, further comprising an anomaly detection unit that detects an anomaly in a tendency of a change in one of the signals relative to a change in the other signal based on a change in the calculation result of the correlation degree. The supervisory control device described in . The supervisory control device according to claim 1 or 2, further comprising a network structure learning unit that learns characteristics of a plurality of network structures. The correlation learning unit further learns inspection or maintenance items by learning based on the signal data and inspection and maintenance data including at least one of the results of inspecting the equipment and the results of maintenance work on the equipment. The monitoring and control device according to claim 1 or 2, wherein the degree of correlation between the signal indicating the state of the equipment and the signal representing the state of the equipment is determined. A supervisory control method for monitoring and controlling each of a plurality of facilities using a supervisory control device, the method comprising:
collecting, for each of the plurality of facilities, signal data including a signal value of a signal representing a state of the facility;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The steps you are looking for and
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a step of processing;
editing the correlation shown in the network structure according to an editing operation;
A supervisory control method characterized by comprising: In the step of outputting the correlation data and determining the degree of correlation by the learning, equipment ledger data summarizing the attributes of the equipment is acquired for each of the plurality of equipment, and equipment included in the plurality of equipment is acquired. 10. The method according to claim 9, wherein a correlation between equipment or a correlation between equipment included in a plurality of the equipment and signals included in a plurality of the signals is certified based on the equipment ledger data. supervisory control method. In the step of outputting the correlation data and determining the degree of correlation by the learning, the degree of correlation between the equipment included in the plurality of equipment, or the correlation between the equipment included in the plurality of equipment and the plurality of the equipment is determined. 11. The monitoring control method according to claim 10, wherein the degree of correlation with the signal included in the signal is determined by learning based on the signal data, the signal ledger data, and the equipment ledger data. The correlation includes a dependent relationship, which is a relationship between signals when control based on one signal changes another signal, and an ownership relationship, which is a relationship between the equipment and the signals owned within the equipment. 11. The supervisory control method according to claim 9, further comprising a relationship and a connection relationship that is a relationship other than the dependent relationship and the ownership relationship. 11. The method according to claim 9, further comprising the step of automatically creating a label representing an attribute of the signal when displaying a graph representing a change in the signal representing a state of the equipment based on the correlation data. The supervisory control method described in . 11. The method according to claim 9, further comprising the step of detecting an abnormality in a tendency of a change in one of the signals relative to a change in the other signal based on a change in the calculation result of the correlation degree. supervisory control method. The supervisory control method according to claim 9 or 10, further comprising the step of learning characteristics of a plurality of the network structures. In the step of outputting the correlation data and determining the degree of correlation by the learning, the step further includes inspection and maintenance data including at least one of the results of inspecting the equipment and the results of maintenance work for the equipment. 11. The supervisory control method according to claim 9, wherein a degree of correlation between an inspection or maintenance item and a signal representing the state of the equipment is determined by learning based on the signal data. Collecting signal data including a signal value of a signal representing a state of the equipment for each of the plurality of equipment to be monitored and controlled;
A correlation in which the signal value of one signal changes in conjunction with a change in the signal value of the other signal among the signals included in the plurality of signals, based on signal ledger data that summarizes the attributes of the signal for each of the plurality of signals. certify the relationship, output correlation data indicating the result of the certification, and determine the degree of correlation between signals other than the signals for which the correlation has been determined by learning based on the signal data and the signal ledger data. The steps you are looking for and
performing a conversion process on the correlation data to display a network structure in which symbols of the signal having the correlation are connected in a network, and displaying the degree of correlation together with the network structure; a step of processing;
editing the correlation shown in the network structure according to an editing operation;
A supervisory control program that causes a computer to execute.

Images