KR20230015134A - Apparatus and method for controling automation of plant - Google Patents

Abstract

According to a proposed embodiment of the present invention, provided are an apparatus and method for controlling the automation of a plant, which are highly usable, highly convenient, highly reliable, and low cost. The method comprises: receiving state information about at least one facility in an energy plant; generating at least one piece of operation procedure information corresponding to the state information by inputting the state information into a first learning model; performing virtual control by inputting the generated at least one piece of operation procedure information into a second learning model; and when performing virtual control of an operation procedure according to at least one state information, when it is identified that there is no problem with a facility corresponding to the operation procedure information, dynamically controlling the facility according to a user's request. Therefore, an energy plant composed of a plurality of facilities is controlled and monitored in an integrated manner according to operation procedure information, and the cognitive load of an operator, who is a user, is minimized to prevent accidents or misjudgments that may occur during operation. Furthermore, duties of the operator are minimized and optimized to provide cost savings for operation and maintenance of the energy plant.

Description

Plant automation control device and method {APPARATUS AND METHOD FOR CONTROLING AUTOMATION OF PLANT}

The present invention relates to a computer-based plant automation control apparatus and method, and more particularly to a computer-based plant automation control apparatus and method for integrally monitoring and controlling an energy plant and integrally providing computer-based operation procedure information.

In general, a power plant has various types of equipment complexly concentrated in a vast space.

The operating procedure, which is a standard document required for power plant operation, is preserved as a printed document or a document in the form of a simple scan, so it is difficult to learn in response to various operating conditions of the operating procedure according to the interconnection of complex systems.

Accordingly, conventionally, operating procedures for plant operation have been changed from paper-based procedures to computer-based procedures to provide operation procedure information to operators in the form of a separate medium.

However, the computer-based operating procedures provided in a conventional separate medium are provided as a dual medium with the instrumentation and control system for facility control, thereby giving a cognitive burden to the user, the operator, and resulting in errors, resulting in low precision. There are downsides.

An object of the present invention to solve the above problems is to provide a plant automation control device with high utilization, high convenience, high reliability and low cost.

Another object of the present invention to solve the above problems is to provide a plant automation control method of high utilization, high convenience, high reliability and low cost.

In order to achieve the above object, a plant automation control method for dynamically controlling at least one facility in an energy plant according to an embodiment of the present invention includes the steps of receiving status information about the at least one facility; generating at least one piece of driving procedure information corresponding to the state information by inputting the information into a learning model; performing virtual control by inputting the generated at least one piece of driving procedure information into a second learning model; When it is confirmed that there is no abnormality in the facility corresponding to the driving procedure information when performing virtual control of the driving procedure according to one state information, dynamically controlling the facility according to the user's request.

In this case, the first learning model may be pre-learned based on control history data of the user according to driving procedure information.

In addition, the second learning model may be learned using at least one facility control history data performed without malfunction for each driving procedure according to driving procedure information.

Also, the state information of the at least one facility may include one of environment information of the energy plant and state information of at least one facility in the energy plant.

In addition, the plant automation control method further comprises the step of analyzing the at least one state information by data mining and storing it in a database according to the degree of association after the step of receiving the state information on the at least one facility. can do.

In addition, the operation procedure information updates update information of at least one operation procedure information according to a change of at least one information about the energy plant, and the at least one information includes a change in attribute information of energy plant facilities, energy plant facility operation It may include at least one information among institutional changes according to.

In order to achieve the above object, a plant automation control apparatus for dynamically controlling at least one facility in an energy plant according to another embodiment of the present invention includes a memory and a processor executing at least one command stored in the memory. ), wherein the at least one command includes a command to receive state information on the at least one facility, and at least one operation procedure corresponding to the state information by inputting the state information to a first learning model. When performing virtual control of a driving procedure according to a command to generate information, a command to input the generated at least one driving procedure information to a second learning model and perform virtual control, and the at least one state information, driving When it is confirmed that there is no abnormality in the facility corresponding to the procedure information, a command for dynamically controlling the facility according to the user's request is included.

In this case, the first learning model may be pre-learned based on control history data of the user according to driving procedure information.

In addition, the second learning model may be learned using at least one facility control history data performed without malfunction for each driving procedure according to driving procedure information.

Also, the state information of the at least one facility may include one of environment information of the energy plant and state information of at least one facility in the energy plant.

In addition, the at least one command may further include a command for analyzing the at least one state information by data mining and storing it in a database according to a degree of association.

In addition, the operation procedure information updates update information of at least one operation procedure information according to a change of at least one information about the energy plant, and the at least one information includes a change in attribute information of energy plant facilities, energy plant facility operation It may include at least one information among institutional changes according to.

An apparatus and method for controlling plant automation according to an embodiment of the present invention receive state information on at least one facility in an energy plant, input the state information to a first learning model, and perform at least one operation corresponding to the state information. Generating procedure information, inputting the generated at least one driving procedure information to the second learning model to perform virtual control, and performing virtual control of the driving procedure according to at least one state information, corresponding to the driving procedure information When it is confirmed that there is no abnormality in the facility, the facility is dynamically controlled according to the user's request, and the energy plant composed of a plurality of facilities is integratedly controlled and monitored based on operation procedure information, and the operator's cognitive load is minimized during operation. A high utilization, high convenience, high reliability and low cost plant automation control device that prevents accidents and misjudgments that may occur, and further minimizes and optimizes the operator's duties to provide cost savings for operation and maintenance of energy plants. and methods can be provided.

1 is a block diagram illustrating a plant automation control device according to an embodiment of the present invention.
2 is a block diagram illustrating hardware configurations of a plant automation control device according to an embodiment of the present invention.
3 is a flowchart of a plant automation control method according to an embodiment of the present invention.

Since the present invention can have various changes and various embodiments, it will be described in detail by exemplifying specific embodiments in the drawings. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms such as first, second, A, and B may be used to describe various components, but each component should not be limited by the terms used. The terms used are used only for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The term “and/or” includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when a component is referred to as “directly connected” or “directly connected” to another component, it should be understood that no other component exists in the middle.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in more detail. In order to facilitate overall understanding in the description of the present invention, the same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

1 is a block diagram illustrating a plant automation control device according to an embodiment of the present invention.

Referring to FIG. 1 , a plant automation control device 1000 may integrally monitor and control an energy plant and dynamically provide computer-based operation procedure information. Here, the driving procedure information may include at least one piece of information such as precautions, instructions, monitoring items, confirmation items, and control items when driving.

Conventionally, functions to monitor and control energy plants and operating procedures providing information on operating procedures have been provided as separate dual media. Accordingly, the user had difficulty in checking both media for efficient operation and management of the energy plant.

On the other hand, the plant automation control device 1000 according to an embodiment of the present invention unifies and provides monitoring and control functions of an energy plant and computer-based operation procedure information, thereby providing a dualized medium and causing user's cognitive errors that may occur. It can minimize the possibility of occurrence and provide convenience.

If the plant automation control device 1000 is described in more detail for each software configuration, it will include a plant control unit 1100, a data storage unit 1300, a learning control unit 1500, a procedure correction unit 1700, and a monitoring unit 1900. can

The plant control unit 1100 may receive at least one plant state information for controlling the plant system from at least one plant system in an energy power plant.

According to the embodiment, the plant control unit 1100 corresponds to a conventional instrumentation and control system and can obtain plant state information from at least one plant system.

Thereafter, the plant control unit 1100 may transmit at least one piece of plant state information to the data storage unit 1300 to be described later.

Conventional instrumentation and control systems provide at least one piece of plant state information obtained from a plant system to a user, that is, an operator, through a main monitor. Accordingly, the operator controlled the plant system for energy generation by referring to an operating procedure provided as a separate system based on at least one piece of plant state information.

On the other hand, the plant automation control device 1000 according to an embodiment of the present invention inputs at least one plant state information obtained into a learning model based on an artificial intelligence algorithm and outputs a control command in which operation procedure information is reflected, so that the plant's dynamic management may be possible.

The data storage unit 1300 may store at least one piece of plant state information received from the plant control unit 1100 . For example, at least one piece of plant state information may be big data.

The data storage unit 1300 may perform data mining on at least one piece of stored plant state information. Accordingly, the data storage unit 1300 may identify, store, and manage a physical or mechanical data correlation from at least one piece of state information.

The data storage unit 1300 may transmit the stored at least one piece of plant state information to the learning control unit 1500 to be described later. The learning control unit 1500 will be described in more detail with reference to FIG. 2 below.

The learning control unit 1500 may provide a learning model based on an artificial intelligence (AI) algorithm. Accordingly, the learning controller 1500 may dynamically control energy and at least one facility of the plant by selecting appropriate operation procedure information according to the real-time state information of the plant.

More specifically, the learning controller 1500 may include a first learning controller 1510 and a second learning controller 1550 .

The first learning control unit 1510 may output at least one piece of plant control information based on driving procedure information by using a pre-trained first learning model.

In other words, the first learning control unit 1510 may generate real-time operation procedure information for dynamic control of energy plant facilities according to at least one piece of plant state information received from the data storage unit 1300 . In this case, the operation procedure information may be at least one facility control information according to the plant state.

Here, the first learning model may be a model pre-trained based on at least one control history data of an operator pre-executed on a case-by-case basis according to driving procedure information. For example, the first learning model is a pre-learned machine learning model using pre-selected driving procedure information as input data and previously performed driver control history data corresponding to the input driving procedure information as label data. can be

In other words, the first learning model may be a model pre-learned based on user control history data according to driving procedure information.

Accordingly, the first learning controller 1510 may input real-time state information of the plant to the pre-learned first learning model to generate operation procedure information considering the real-time state information of the plant.

In addition, the first learning controller 1510 may generate a control signal including the generated driving procedure information and transmit it to a second learning controller 1550 to be described later.

For example, the second learning controller 1550 may simulate plant equipment operation according to the driving procedure information based on the control signal received from the first learning controller 1510 .

More specifically, the second learning controller 1550 may perform a simulation according to the control signal transmitted from the first learning controller 1510 using the pretrained second learning model. In other words, the second learning controller 1550 may provide a control result history of virtual control based on the control signal transmitted from the first learning controller 1510 . For example, the second learning model may be a model that predicts a simulation result according to input driving procedure information. In other words, the second learning model may be a model learned using at least one facility control history data performed without malfunction according to driving procedure information.

Thereafter, the second learning control unit 1550 may transmit a control signal having no abnormality to the corresponding energy plant facility based on the predicted simulation information. Accordingly, at least one plant facility may dynamically perform an appropriate driving operation considering the state and situation of the energy plant.

In the plant automation control apparatus 1000 according to an embodiment of the present invention, the second learning control unit 1550 receives at least one piece of information received from the first learning control unit 1510 to prevent plant equipment from malfunctioning due to a control signal error. By preventing, dynamic management of high-safety and high-reliability plant equipment can be possible.

The procedure modifying unit 1700 may initially store operation procedure information of an energy plant input by a user.

Also, the procedure modifying unit 1700 may update update information of at least one piece of driving procedure information according to a change in at least one piece of information about an energy plant, based on a user input. Here, the at least one information change may include a change in property information of energy plant facilities, institutional changes according to energy plant facility operation, and the like.

The monitoring unit 1900 may analyze and provide at least one piece of information related to the energy plant system to a user.

More specifically, the monitoring unit 1900 analyzes at least one piece of information for each operation procedure processed by the plant control unit 1100, the data storage unit 1300, the learning control unit 1500, and the procedure correction unit 1700, can be provided in real time.

According to an embodiment, the monitoring unit 1900 outputs at least one of real-time trend information of a power plant system related to energy plant facilities, plant facility operation prediction information, plant facility control information, plant facility execution information, and plant facility operation information so as to provide a user It can be provided to human operators or AI devices.

For example, in more detail, the monitoring unit 1900 may provide result data expected from the execution of the corresponding procedure received from the second learning control unit 1550 prior to performing the driving procedure at the request of the user.

In addition, when the monitoring unit 1900 receives an automatic control signal for automatically executing a procedure in a certain section from a user and dynamically performs plant facilities according to operation procedure information, the automatic execution of plant facilities is stopped according to safety standards. can do.

In addition, the monitoring unit 1900 outputs display information for changing the control subject using an artificial intelligence device to request information on automatic or manual operation control from the user, or history of automatic execution and manual execution related to driving procedures. can be made to learn. Accordingly, the monitoring unit 1900 may generate and provide the learned control information to the user.

In addition, the monitoring unit 1900 may provide preliminary diagnosis results of the incident or accident to the user according to the user's request, when it is necessary to diagnose the incident or accident due to the occurrence of the incident or accident.

In addition, the monitoring unit 1900 may provide optimal driving procedure information alternatives and expected information according to the alternatives in a corresponding driving step, when a situation outside the prepared procedure occurs.

The monitoring unit 1900 may provide input display information so that a user may set and store a procedure section requiring automatic execution, and may provide automatic execution of the procedure section set by the user and result data after execution.

In addition, the monitoring unit 1900 may provide a face to face communication function to support video communication between operators, who are users, and may provide control history and real-time control status information of other operators. there is.

In addition, the monitoring unit 1900 may generate a warning message when control authority (priority setting of control authority) is violated between operators who are users.

At this time, if the user is an artificial intelligence device, a warning message may be output by the monitoring unit 1100 when the user gets out of the process progress context by monitoring, and if an emergency issuance condition is satisfied during the emergency operation procedure, an emergency is automatically performed. (White, Blue, Red) An alarm can be issued. At this time, the corresponding emergency alert response is automatically executed, the result is provided to the operator, and additional action may be requested by the operator when action is not possible.

Also, based on at least one piece of information output from the monitoring unit 1900, the user may determine whether to execute plant automation by transmitting a control signal for dynamic control of facilities to the learning control unit.

In the above, the plant automation control device according to the embodiment of the present invention has been described for each software configuration.

Hereinafter, in FIG. 2, the plant automation control device will be described in more detail for each hardware configuration.

2 is a block diagram illustrating hardware configurations of a plant automation control device according to an embodiment of the present invention.

Referring to FIG. 2 , the plant automation control device 1000 includes a memory 100 for storing at least one command, a processor 200 for executing at least one command in the memory, a transceiver 300, and an input interface device. 400, an output interface device 500, and a storage device 600 may be further included.

According to the embodiment, each of the components 100, 200, 300, 400, 500, and 600 included in the plant automation control device 1000 are connected by a bus 700 to communicate with each other. there is.

Among the components 100, 200, 300, 400, 500, 600, and 700 of the plant automation control device 1000, the memory 100 and the storage device 600 are composed of at least one of a volatile storage medium and a non-volatile storage medium It can be. For example, the memory 100 and the storage device 600 may include at least one of a read only memory (ROM) and a random access memory (RAM).

The memory 100 may include at least one instruction to be executed by the processor 200 to be described later.

According to an embodiment, the at least one command includes a command for receiving status information on at least one facility in an energy plant, inputting the status information to a first learning model, and performing at least one operation corresponding to the status information. When performing virtual control of a driving procedure according to a command to generate procedure information, a command to input the generated at least one driving procedure information to a second learning model and perform virtual control, and the at least one state information, When it is confirmed that there is no abnormality in the facility corresponding to the operation procedure information, a command for dynamically controlling the facility according to a user's request may be included.

The processor 200 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed.

As described above, the processor 200 may execute software configurations by at least one program command stored in the memory 100 .

The input interface device 400 and the output interface device 500 may receive at least one control signal from a manager, and may output and visualize at least one piece of information related to the virtual training environment by the operation of the processor 200. there is.

In the above, the plant automation control device according to the embodiment of the present invention has been described.

Hereinafter, a plant automation control method executed by a processor operation in the plant automation control device will be described.

3 is a flowchart of a plant automation control method according to an embodiment of the present invention.

Referring to FIG. 3 , the processor 200 in the plant automation control device 4000 may execute the plant control unit 1100 to receive state information from at least one plant facility (S1000).

According to an embodiment, the plant control unit 1100 is a device that provides control information for an energy plant system and at least one facility, and may correspond to a conventional instrumentation and control system.

Thereafter, the processor 200 may execute the data storage unit 1300 to analyze a physical or mechanical relationship between the state information through data mining.

Also, the processor 200 may store and manage at least one piece of analyzed data. According to an embodiment, the processor 200 may store and manage at least one state information in a database-based logic tree (S2000).

The processor 200 may execute the first learning control unit 1510 to obtain state information on at least one plant facility from the data storage unit 1300 .

Then, the processor 200 may generate at least one driving state information by inputting the state information to the first learning model (S3000).

At this time, the first learning model is an artificial intelligence algorithm model pre-learned before execution of the first learning control unit 1510, at least one driving procedure information from the procedure correction unit 1700 and driving for each case according to the driving procedure information. It may be a pretrained model based on control history data. For example, the first learning model may be a machine learning model pre-learned by using previously selected driving procedure information as input data and using control history data of an operator previously performed in response to the input driving procedure information as label data. can

Thereafter, the processor 200 may execute the second learning controller 1550 to receive operation procedure information according to state information of energy plant facilities obtained through the first learning controller 1510 .

Thereafter, the processor 200 may perform a simulation of the received driving procedure information by using a second learning model. In other words, the processor 200 may perform virtual control of at least one plant facility according to the driving procedure information using the second learning model (S4000).

According to the embodiment, when it is determined that there is no abnormality in the simulation, the processor 200 may dynamically control or manually control at least one facility by checking whether an automatic control signal is input from the user (S5000).

According to an embodiment, when an automatic control signal is input, the processor 200 may transmit the automatic control signal to an energy plant facility. Accordingly, at least one energy plant facility may be dynamically controlled by the plant automation control device according to an embodiment of the present invention.

According to another embodiment, when an automatic control signal is not input, the processor 200 may manually control at least one energy plant facility based on operation procedure information output through a user's monitor.

In the above, the plant automation control apparatus and method according to the embodiment of the present invention have been described.

An apparatus and method for controlling plant automation according to an embodiment of the present invention receive state information on at least one facility in an energy plant, input the state information to a first learning model, and perform at least one operation corresponding to the state information. Generating procedure information, inputting the generated at least one driving procedure information to the second learning model to perform virtual control, and performing virtual control of the driving procedure according to at least one state information, corresponding to the driving procedure information When it is confirmed that there is no abnormality in the facility, the facility is dynamically controlled according to the user's request, and the energy plant composed of a plurality of facilities is integratedly controlled and monitored based on operation procedure information, and the operator's cognitive load is minimized during operation. A high utilization, high convenience, high reliability and low cost plant automation control device that prevents accidents and misjudgments that may occur, and further minimizes and optimizes the operator's duties to provide cost savings for operation and maintenance of energy plants. and methods can be provided.

The operation of the method according to the embodiments of the present invention can be implemented as a computer readable program or code on a computer readable recording medium. A computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. In addition, computer-readable recording media may be distributed to computer systems connected through a network to store and execute computer-readable programs or codes in a distributed manner.

In addition, the computer-readable recording medium may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, and flash memory. The program command may include high-level language codes that can be executed by a computer using an interpreter or the like as well as machine code generated by a compiler.

Although some aspects of the present invention have been described in the context of an apparatus, it may also represent a description according to a corresponding method, where a block or apparatus corresponds to a method step or feature of a method step. Similarly, aspects described in the context of a method may also be represented by a corresponding block or item or a corresponding feature of a device. Some or all of the method steps may be performed by (or using) a hardware device such as, for example, a microprocessor, programmable computer, or electronic circuitry. In some embodiments, one or more of the most important method steps may be performed by such an apparatus.

In embodiments, a programmable logic device (eg, a field programmable gate array) may be used to perform some or all of the functions of the methods described herein. In embodiments, a field programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. Generally, methods are preferably performed by some hardware device.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention described in the claims below. You will understand that you can.

1000: interceptor 2000: early warning radar
3000: Operation Control Unit 3100: Data Generation Unit
3300: data storage unit 3500: data transmission unit
4000: interception simulation training device 4100: target providing unit
4500: target output unit 100: memory
200: processor 300: transmitting and receiving device
400: input interface device 500: output interface device
600: storage device 700: bus
S: interception simulation training system

Claims (12)

A plant automation control method for dynamically controlling at least one facility in an energy plant,
receiving status information about the at least one facility;
generating at least one piece of driving procedure information corresponding to the state information by inputting the state information to a first learning model;
performing virtual control by inputting at least one piece of generated driving procedure information to a second learning model; and
When performing virtual control of the operating procedure according to the at least one state information, when it is confirmed that there is no abnormality in the facility corresponding to the operating procedure information, dynamically controlling the facility according to a user request, plant automation control method. According to claim 1,
The first learning model,
Pre-learned, plant automation control method based on user's control history data according to operation procedure information. According to claim 1,
The second learning model,
A plant automation control method learned using at least one equipment control history data performed without malfunction for each operation procedure according to operation procedure information. According to claim 1,
State information about the at least one facility,
Plant automation control method comprising one of environmental information of the energy plant and state information of at least one facility in the energy plant. According to claim 1,
After receiving status information on the at least one facility,
Analyzing the at least one state information by data mining and storing it in a database according to the degree of association, the plant automation control method. According to claim 1,
The driving procedure information,
Update information of at least one operation procedure information is updated according to a change in at least one information about the energy plant,
The at least one piece of information,
A plant automation control method comprising at least one information of change of property information of energy plant facilities and institutional change according to operation of energy plant facilities. A plant automation control device for dynamically controlling at least one facility in an energy plant,
memory; and
A processor executing at least one instruction stored in the memory,
The at least one command,
instructions for receiving status information on the at least one facility;
a command for generating at least one piece of driving procedure information corresponding to the state information by inputting the state information to a first learning model;
a command for inputting at least one piece of generated driving procedure information to a second learning model to perform virtual control; and
When performing virtual control of the operating procedure according to the at least one state information, when it is confirmed that there is no abnormality in the facility corresponding to the operating procedure information, including a command to dynamically control the facility according to the user's request, plant automation controller. According to claim 7,
The first learning model,
Plant automation control device pre-learned based on user control history data according to operating procedure information. According to claim 7,
The second learning model,
A plant automation control device learned using at least one facility control history data performed without malfunction for each operation procedure according to the operation procedure information. According to claim 7,
State information about the at least one facility,
A plant automation control device comprising one of environmental information of the energy plant and state information of at least one facility in the energy plant. According to claim 7,
The at least one command,
Further comprising a command for analyzing the at least one state information by data mining and storing it in a database according to a degree of association, the plant automation control device. According to claim 7,
The driving procedure information,
Update information of at least one operation procedure information is updated according to a change in at least one information about the energy plant,
The at least one piece of information,
A plant automation control device comprising at least one information of change of property information of energy plant facilities and institutional change according to operation of energy plant facilities.

Images