WO2022139198A1 - System and method for managing scheduling of power plant on basis of artificial neural network - Google Patents

Abstract

The present disclosure relates to an operation method of a system for managing the scheduling of a power plant on the basis of an artificial neural network. According to the present disclosure, the operation method of a system for managing the scheduling of a power plant comprises the steps of: acquiring plant schedule information about a plurality of nodes from a plant scheduling database; constructing, on the basis of the plant schedule information, a first schedule network reflecting plant scheduling conditions; identifying whether an abnormal situation has occurred in at least one of elements forming the first schedule network; constructing, on the basis of a trained artificial neural network, a second schedule network for replacing the first schedule network; and determining alternative plant scheduling on the basis of the second schedule network.

Description

System and method for managing scheduling of power plant based on artificial neural network

The present disclosure generally relates to a power plant schedule management system, and more specifically, diagnoses abnormal situations in a power plant based on an artificial neural network, configures an alternative schedule network of the power plant, and performs an alternative plant schedule plan. It is about a system to manage.

A plant designates all of the machinery, production equipment, or manufacturing equipment, such as production machinery, factory equipment, or the entire factory. Management technology for maintenance work performed in a plant or planned preventive maintenance is made in various forms, and in particular, a technology for planning and managing each process in a plant for power generation is used.

According to the prior art, the process was operated according to an information and communication technology (ICT)-based process management system. The ICT-based process management system indicates a system that synchronizes and computerizes the process management program based on ICT, and divides it into general management, risk management, and detailed management means. Most of the conventional process management system technology focused on managing each process itself. That is, the conventional process management system technology remains at the level of simply inquiring whether the process is delayed or the like in risk management. Accordingly, when an abnormal situation occurs in the schedule, the process management system cannot create a schedule network and a schedule plan that can replace the abnormal situation.

In addition, a process management system using a conventional artificial neural network could recognize an object based on deep learning or predict a process situation according to the object. However, even when an artificial neural network is used, the process management system focuses on managing the process schedule, and thus, when an abnormal situation occurs in the schedule, it is not possible to create a schedule network to respond to it.

The schedule management system of the power plant is the most fundamental system in various power plants and plant design and construction companies, and the process management system is used. However, since the schedule management system of the power plant also uses the conventional process management system, an alternative schedule cannot be determined when an abnormal situation occurs. Various abnormal situations may occur in the middle of the project being carried out and the process is in progress, and according to the prior art, the power plant and plant schedule plans are frequently changed due to these abnormal situations, thereby deteriorating the profitability of the project. Accordingly, there is a demand for technology development for efficiently coping with an abnormal situation occurring in a current power plant.

Based on the above discussion, the present disclosure provides a system and method for diagnosing abnormal conditions in a power plant.

The present disclosure also provides a system and method for creating a new replacement schedule network of a power plant when an abnormal situation occurs in the power plant.

The present disclosure also provides a system and method for generating an alternative plant scheduling plan for a power plant when an abnormal situation occurs in the power plant.

According to various embodiments of the present disclosure, a method of operating a system for managing a schedule of a power plant based on an artificial neural network includes: acquiring plant schedule information about a plurality of nodes from a plant schedule planning database; Based on the plant schedule information, configuring a first schedule network reflecting plant schedule planning conditions, identifying whether an abnormal situation has occurred in at least one of the elements constituting the first schedule network, the learned artificial intelligence based on the neural network, configuring a second schedule network to replace the first schedule network, and determining an alternate plant schedule plan based on the second schedule network.

According to another embodiment, the information about the plant schedule may include past plant schedule planning history information and current plant schedule information.

According to another embodiment, configuring the first schedule network may further include classifying plant schedule information about the plurality of nodes based on process configuration, resource configuration, restrictions, and detailed information. have.

According to another embodiment, the configuring of the second schedule network may include determining an issue element in which the abnormal situation occurs among elements of the first schedule network, based on a schedule planning structure. determining candidate replacement elements to replace the issue element, determining a replacement element from among the candidate replacement elements through the artificial neural network, and configuring the second schedule network to include the replacement element step, wherein the scheduling structure may be composed of an ontology layer, a process layer, a connection object layer, and a mapping layer.

According to another embodiment, the issue element includes at least one node among the plurality of nodes, and the determining of the issue element includes a loss in at least one of the nodes included in the first schedule network. case, determining a node in which the loss has occurred as an issue node, and when a node not included in the first schedule network is added to the first schedule network, determining the added node as an issue node have.

According to another embodiment, the issue element includes a connection state between the plurality of nodes, and the determining of the issue element includes a loss when a loss occurs in a connection state included in the first schedule network. Determining the generated connection state as the issue connection state, and when a connection state not included in the first schedule network is added to the first schedule network, determining the added connection state as the issue connection state can

According to another embodiment, the ontology layer indicates a plurality of processes, the process layer indicates at least one detailed process included in the plurality of processes, and the connection object layer manages the plurality of processes. at least one process person in charge, and the mapping layer is based on the ontology layer, the process layer, and the connection object layer of the scheduling structure, Layers constituting a connection relationship may be indicated.

According to another embodiment, the determining of the candidate replacement elements includes a process used by the issue element based on the arrangement of the issue element in the ontology layer, the process layer, the connection object layer, and the mapping layer; The detailed process and at least one of the person in charge may include determining identical elements as the candidate replacement elements.

According to another embodiment, the artificial neural network may be modeled based on at least one of a self organizing map (SOM) and a deep neural network (DNN).

*According to another embodiment, the method of operating the power plant schedule management system may further include evaluating an alternate schedule based on the alternate plant schedule.

According to an embodiment of the present disclosure, a system for managing a schedule plan of a power plant based on an artificial neural network includes a data linkage unit for acquiring plant schedule information on a plurality of nodes from a plant schedule planning database, the plant schedule Based on the information, a schedule network configuration unit constituting a first schedule network in which plant schedule planning conditions are reflected, an abnormal situation management unit that identifies whether an abnormal situation has occurred in at least one of the elements constituting the first schedule network; and an alternative schedule network configuration unit configured to configure a second schedule network to replace the first schedule network based on the learned artificial neural network, and to determine an alternate plant schedule plan based on the second schedule network.

Various respective aspects and features of the invention are defined in the appended claims. Combinations of features of the dependent claims may be combined with features of the independent claims as appropriate, not just expressly set forth in the claims.

In addition, one or more features selected in any one embodiment described in this disclosure may be combined with one or more features selected in any other embodiment described in this disclosure, and alternatives to these features a combination of at least partially alleviates one or more technical problems discussed in the present disclosure, or at least partially alleviates technical problems that can be discerned by a person skilled in the art from the present disclosure, and furthermore features of embodiments ( The combination is possible, provided that a specific combination or permutation so formed of the embodiment features is not understood by a person skilled in the art as incompatible.

In any described example implementation, two or more physically separate components may alternatively be integrated into a single component if their integration is possible, and the single component so formed If the same function is performed by , the integration is possible. Conversely, a single component of any embodiment described in the present disclosure may alternatively be implemented with two or more separate components that achieve the same function, where appropriate.

It is an object of certain embodiments of the present invention to solve, mitigate, or eliminate, at least in part, at least one of the problems and/or disadvantages associated with the prior art. Certain embodiments aim to provide at least one of the advantages described below.

The systems and methods according to various embodiments of the present disclosure diagnose an abnormal situation in a power plant and manage an alternate schedule network and an alternate schedule plan of the power plant, so that it is possible to quickly respond to an abnormal situation in the power plant.

In addition, the system and method according to various embodiments of the present disclosure manage an alternative schedule network and an alternate schedule plan of a power plant, thereby reducing costs caused by abnormal situations.

In addition, by managing the alternate schedule network and the alternate schedule plan of the system and the power generation plant according to various embodiments of the present disclosure, it is possible to efficiently cope with the process change issue.

In addition, systems and methods according to various embodiments of the present disclosure enable efficient management of dynamic schedules occurring in power plant construction management.

The system and method according to various embodiments of the present disclosure enable efficient response through an alternative schedule network when an abnormal situation occurs while a power plant schedule is performed according to a schedule plan and the entire schedule network collapses.

Effects obtainable in the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. will be.

1 illustrates a power plant system according to various embodiments of the present disclosure.

2 illustrates a configuration of a power plant schedule management system in a power plant system according to various embodiments of the present disclosure.

3 illustrates an example of project information included in a plurality of nodes in a power plant system according to various embodiments of the present disclosure.

4 is a schematic diagram illustrating a project classification method of a schedule network component in a power plant system according to various embodiments of the present disclosure.

5 illustrates an example of a schedule network in a power plant system according to various embodiments of the present disclosure.

6 is a schematic diagram illustrating an operation method of an abnormal situation management unit in a power plant system according to various embodiments of the present disclosure.

7 is a schematic diagram illustrating an operation method of an alternative schedule network component in a power plant system according to various embodiments of the present disclosure.

FIG. 8 is a schematic diagram illustrating a method in which a replacement schedule network component determines candidate replacement elements in a power plant system according to various embodiments of the present disclosure;

9 illustrates an example of a network configured by a power plant schedule management system in a power plant system according to various embodiments of the present disclosure.

10 is a flowchart illustrating an operation method in which a power plant schedule management system determines an alternative plant schedule plan in a power plant system according to various embodiments of the present disclosure;

11 is a flowchart illustrating a method for a power plant schedule management system to generate an alternative schedule network in a power plant system according to various embodiments of the present disclosure;

Terms used in the present disclosure are used only to describe specific embodiments, and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meanings as commonly understood by one of ordinary skill in the art described in the present disclosure. Among the terms used in the present disclosure, terms defined in a general dictionary may be interpreted with the same or similar meaning as the meaning in the context of the related art, and unless explicitly defined in the present disclosure, ideal or excessively formal meanings is not interpreted as In some cases, even terms defined in the present disclosure cannot be construed to exclude embodiments of the present disclosure.

In various embodiments of the present disclosure described below, a hardware access method will be described as an example. However, since various embodiments of the present disclosure include technology using both hardware and software, various embodiments of the present disclosure do not exclude a software-based approach.

Hereinafter, the present disclosure relates to a system and method for power plant schedule management. Specifically, the present disclosure describes a technique for diagnosing an abnormal situation in a power plant based on an artificial neural network and managing an alternative schedule network and an alternative schedule plan of the power plant.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present disclosure pertains can easily implement it. However, since the technical spirit of the present disclosure may be modified and implemented in various forms, it is not limited to the embodiments described herein. In the description of the embodiments disclosed in the present specification, when it is determined that a detailed description of a related known technology may obscure the gist of the present disclosure, a detailed description of the known technology will be omitted. The same or similar components are given the same reference numerals, and overlapping descriptions thereof will be omitted.

In the present specification, when an element is described as being "connected" with another element, it includes not only the case of being "directly connected" but also the case of being "indirectly connected" with another element interposed therebetween. When an element "includes" another element, it means that another element may be further included without excluding another element in addition to other elements unless otherwise stated.

Some embodiments may be described in terms of functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or by circuit configurations for a given function. The functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks of the present disclosure may be implemented as an algorithm running on one or more processors. A function performed by a functional block of the present disclosure may be performed by a plurality of functional blocks, or functions performed by a plurality of functional blocks in the present disclosure may be performed by one functional block. In addition, the present disclosure may employ prior art for electronic configuration, signal processing, and/or data processing, and the like.

In addition, in the present disclosure, in order to determine whether a specific condition is satisfied (satisfied) or satisfied (fulfilled), an expression of more than or less than is used, but this is only a description to express an example, and more or less description is excluded not to do Conditions described as 'more than' may be replaced with 'more than', conditions described as 'less than', and conditions described as 'more than and less than' may be replaced with 'more than and less than'.

Hereinafter used '… wealth', '… The term 'group' means a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

1 illustrates a power plant system 100 according to various embodiments of the present disclosure. Referring to FIG. 1 , a power plant system 100 includes a plant schedule planning database 101 , first to n-th nodes 105-1 to 105-n, and a power plant schedule management system. The plant schedule planning database 101 , the first to nth nodes 105 - 1 to 105 - n , and the power plant schedule planning management system may send and receive data through the communication network 103 .

The plant schedule planning database 101 performs a function of storing information necessary for plant schedule planning. The plant schedule planning database 101 may indicate a database provided by a company managing a power plant process. The plant schedule planning database 101 may transmit/receive data to and from the first to nth nodes 105 - 1 to 105 - n and the power plant schedule management system 107 through the communication network 103 . According to an embodiment of the present disclosure, the plant schedule planning database 101 may receive information necessary for configuring a plant schedule network from the first to n-th nodes 105 - 1 to 105 - n . The plant schedule planning database 101 may transmit information about the plant schedule to the power plant schedule planning management system 107 .

The communication network 103 may include at least one of the Internet, a local area network (LAN), a telecommunication network, and a wireless mobile communication network. Various technologies may be used to operate the communication network 103 . According to an embodiment of the present disclosure, a known network protocol such as TCP/IP, FTP, HTTP, etc. may be used.

The first to nth nodes 105 - 1 to 105 - n indicate nodes constituting the communication network through the communication network 103 . The first to n-th nodes 105 - 1 to 105 - n may configure a schedule network based on plant schedule management. According to an embodiment of the present disclosure, the first to n-th nodes 105 - 1 to 105 - n may instruct a process operated according to a power plant schedule plan. Correspondingly, each process may constitute one predetermined network.

The power plant schedule management system 107 indicates a system for comprehensively managing the power plant schedule. The power plant schedule management system 107 may configure a power plant schedule network using the first to n-th nodes 105 - 1 to 105 - n . According to an embodiment of the present disclosure, the power plant schedule management system 107 may generate a schedule network based on a plurality of nodes and a connection relationship between nodes and determine a plant schedule plan. In this case, when an abnormal situation occurs in the generated schedule network, the power plant schedule planning management system 107 may generate an alternate network to replace the schedule network, and determine an alternate plant schedule plan based on the alternate network. A specific configuration of the power plant schedule management system 107 is shown in FIG. 2 .

2 illustrates a configuration 200 of a power plant schedule management system in a power plant system according to various embodiments of the present disclosure. FIG. 2 illustrates the power plant scheduling management system 107 of FIG. 1 .

Referring to FIG. 2 , the power plant schedule management system 107 includes a data link unit 201 , a schedule network configuration unit 203 , an abnormal situation management unit 205 , an alternate schedule network configuration unit 207 , and an alternate schedule. and a network evaluation unit 209 .

The data link unit 201 performs a function of acquiring information about the power plant schedule from the power plant schedule plan database 101 . The data linkage unit 201 may be in charge of interfacing with the schedule plan database 101 of the existing power plant. The power plant schedule management system 107 may acquire data on the performance schedule of the power plant business and the past plant schedule planning history through the data link unit 201 . The data linkage unit 201 may obtain schedule information necessary to determine a schedule network and a plant schedule plan by linking with the plant schedule planning database 101 . According to an embodiment of the present disclosure, the data linkage unit 201 may obtain plant schedule information about a plurality of nodes from the power plant schedule planning database 101 . Here, the plant schedule information may include past plant schedule planning history information and current plant schedule information.

The data linkage unit 201 may perform a function of linking core projects constituting a power plant schedule and visualizing schedule information. Specifically, the data linkage unit 201 includes a power plant and plant project database linkage function, a template function for project linkage, a common project template import and/or export function, and a tool for major project editing (editing). ) linkage function, project detailed editing and modification functions can be performed.

The schedule network configuration unit 203 performs a function of configuring a schedule network for a plurality of nodes. The schedule network configuration unit 203 may generate a schedule network in which a plurality of nodes are connected and configured based on the plant schedule information obtained by the data link unit. According to an embodiment of the present disclosure, the schedule network configuration unit 203 may generate a schedule network by reflecting and mapping the conditions of the current plant schedule plan. In this case, the schedule network configuration unit 203 configures the currently performed project differently from the conventional schedule network based on business performance scheduling, process configuration, resource configuration, constraint configuration, It is possible to classify based on detailed information configuration and configure it as one network. A specific network configuration method of the schedule network configuration unit 203 will be described in detail with reference to FIGS. 4 to 5 .

The abnormal situation management unit 205 performs a function of identifying whether an abnormal situation has occurred in a predetermined network. According to an embodiment of the present disclosure, the abnormal situation management unit 205 may identify whether an abnormal situation has occurred in at least one of elements constituting a predetermined network. Here, the element may indicate at least one of a plurality of nodes constituting a predetermined network and a connection state between the plurality of nodes. When an abnormal situation occurs in an element of the predetermined network, the abnormal situation management unit 205 may obtain information indicating that an abnormal situation has occurred in the predetermined network from the outside. In this case, the abnormal situation management unit 205 may identify that an abnormal situation has occurred and identify whether to configure an alternative schedule network in response thereto. According to another embodiment of the present disclosure, the abnormal situation management unit 205 may analyze data transmitted and received by a plurality of nodes according to a network schedule to identify whether an abnormal situation has occurred.

The alternate schedule network configuration unit 207 performs a function of configuring an alternate schedule network and an alternate plant schedule plan to replace the schedule network. The replacement schedule network configuration unit 207 may determine an alternative element for replacing the issue element in which an abnormal situation occurs based on information about the plant schedule. According to an embodiment of the present disclosure, the replacement schedule network configuration unit 207 determines an alternate node or an alternate connection state by analyzing process, resource, and condition related data of a past power plant, and determines an alternate node or an alternate connection state. It can be used to configure an alternative schedule network. Here, the replacement schedule network configuration unit 207 may determine the replacement element using an artificial neural network. According to an embodiment of the present disclosure, the alternative schedule network configuration unit 207 may use deep learning and data mining techniques. The artificial neural network may be modeled based on at least one of a self-organizing map (SOM) and a deep neural network (DNN). Also, the alternative schedule network configuration unit 207 may configure a schedule planning structure based on a plurality of layers in order to use the artificial neural network. A specific alternative schedule network and a method for configuring an alternate schedule network and an alternate plant schedule of the alternate schedule network configuration unit 207 will be described in detail with reference to FIGS. 7 to 10 .

The alternate schedule network evaluation unit 209 performs a function of evaluating the created alternate schedule network. The alternative schedule network evaluation unit 209 may analyze and evaluate the alternate schedule network and the alternate plant schedule plan generated by the alternate schedule network configuration unit 207 . The alternative schedule network evaluation unit 209 may analyze a connection relationship between processes according to the alternative schedule network and search for an appropriate route. According to an embodiment of the present disclosure, the alternate schedule network evaluation unit 209 may perform detailed functions such as a visualization function of main processes according to the alternate schedule network and a network routing function.

3 illustrates an example 300 of project information included in a plurality of nodes in a power plant system according to various embodiments of the present disclosure.

Each of the plurality of nodes included in the power plant system may include project information for performing each process. According to an embodiment of the present disclosure, project information may include process information, resource information, and allocation information. Process information may include process ID, DB linkage/activation, schedule/reservation mode, process details, period, start date, completion date, predecessor, level, and other information. The resource information may include resource ID, process ID, resource name, resource type, resource layer, resource group, resource contact information, unit, air quantity, and other information. The assignment information may include process ID, resource ID, process progress rate, work hours, units, and other information.

Accordingly, one project information may be stored in a project DB (datebase), and may be classified and stored as at least one of a process DB, a resource DB, and an allocation DB. The project information stored in the plurality of nodes may be transferred to and stored in the plant schedule planning database 101 .

4 is a schematic diagram 400 of a project classification method of the schedule network configuration unit 203 in a power plant system according to various embodiments of the present disclosure.

Referring to FIG. 4 , the schedule network configuration unit 203 may generate a schedule network by reflecting and mapping conditions related to the current plant schedule plan. The schedule network configuration unit 203 may classify project information of a plurality of nodes in order to generate a schedule network from the acquired plant schedule information. According to an embodiment of the present disclosure, the schedule network configuration unit 203 configures the project necessary to configure the schedule network process configuration 401, resource configuration 403, limit configuration 405, detailed information configuration 407 Based on the classification, it can be configured as a single schedule network. The schedule network configuration result of the schedule network configuration unit 203 is shown in FIG. 5 .

5 illustrates an example 500 of a schedule network in a power plant system according to various embodiments of the present disclosure.

Referring to FIG. 5 , the schedule network configuration unit 203 may configure a schedule network based on plant information and generate a plant schedule plan. The schedule network configuration unit 203 may create a connection relationship with respect to a project performed by each of the plurality of nodes. The schedule network configuration unit 203 may create a connection relationship using a plurality of schedules, and may generate a schedule network for a plurality of nodes based on the connection relationship of the plurality of schedules. Also, the schedule network configuration unit 203 may determine a plant schedule plan based on the generated schedule network.

Referring to an example 500 of the schedule network, the schedule network may be configured based on a plurality of schedules related to a project. Here, FIG. 5 illustrates a first schedule 501 corresponding to one of a plurality of schedules. Referring to FIG. 5 , a first schedule 501 may include a process name, process start, process completion, process period, process ID, and resource information related to a process performed in the first process. The schedule network configuration unit 203 may configure a plurality of schedules including the same type of information as the first schedule 501 to be connected to each other, and configure a schedule network between a plurality of nodes to correspond thereto. The schedule network configuration unit 203 may visualize the connection relationship of the current plant schedule plan by determining the schedule network.

6 is a schematic diagram 600 illustrating an operation method of an abnormal situation management unit in a power plant system according to various embodiments of the present disclosure. 6 exemplifies the operation of the abnormal situation management unit 205 of FIG. 2 .

Referring to FIG. 6 , the abnormal situation management unit 205 identifies whether an abnormal situation has occurred in at least one of elements constituting a predetermined network. The abnormal situation management unit 205 may include an input unit for receiving an abnormal situation when an abnormal situation occurs in an element constituting the schedule network and a determination unit for identifying whether the current schedule network is valid or whether a new schedule network is required have. According to an embodiment of the present disclosure, whether a new schedule network is required may be determined as shown in <Table 1>.

type of anomaly	Details of the anomaly
loss of network nodes	Loss of existing nodes that make up the scheduling plan
loss of network connection	Due to procurement delays and problems, there is a loss of connectivity between nodes.
Addition of new network nodes	Due to the new inspection process, additional nodes
Addition of a new network connection state	Due to the change of the precedence process constraint, the connection state between the nodes is added.
Complex Connections and Node Appearance Cases	Combination of the above cases

Referring to <Table 1>, the abnormal situation indicates at least one of a situation in which a network node is lost, a situation in which a network connection state is lost, a situation in which a new network node is added, and a situation in which a new network connection state is added. . That is, when at least one of the network nodes constituting the existing predetermined network and the connection state between the nodes is lost, or when nodes not included in the predetermined network and the connection state between the nodes are added, an abnormal situation The management unit 205 may identify that an alternative schedule network is required.

The abnormal situation management unit 205 may perform a preparation procedure for configuring an alternative schedule network by removing or adding an issue element in which an abnormal situation has occurred. According to an embodiment of the present disclosure, the abnormal situation management unit 205 may perform project modification 601 to configure an alternative schedule network. Also, the abnormal situation management unit 205 may perform a configuration change 603 of a predetermined network by removing or adding a network issue node. According to an embodiment of the present disclosure, the abnormal situation management unit 205 may perform reanalysis and diagnosis 605 of the network regarding the alternative schedule network according to the project modification 601 and the configuration change 603 of the schedule network. have.

7 is a schematic diagram 700 of an operation method of an alternative schedule network component in a power plant system according to various embodiments of the present disclosure. FIG. 7 illustrates the operation of the alternative schedule network configuration unit 207 of FIG. 2 .

Referring to FIG. 7 , the alternative schedule network configuration unit 207 may perform a dynamic reconfiguration 709 procedure when an issue element occurs. The alternative schedule network configuration unit 207 may analyze process, resource, and condition-related data of a past power plant to determine an alternate node or an alternate connection state, and configure an alternate schedule network using the alternate node or alternate connection state. have. According to an embodiment of the present disclosure, the replacement schedule network configuration unit 207 performs a network analysis 701 on a network including issue elements and a deep neural network analysis 703 for determining an alternative element using an artificial neural network. It can be used to perform a dynamic reconfiguration 709 procedure for elements included in the replacement schedule network. Here, in order to use the artificial neural network, the alternative schedule network configuration unit 207 may configure a schedule planning structure based on a plurality of layers and continuously update the schedule planning structure. That is, in the dynamic reconfiguration 709 procedure, the alternative schedule network configuration unit 207 may determine the elements constituting the alternative schedule network through the approaches related to the probabilistic analysis 705 and the cluster analysis 707 .

The schedule planning structure indicates a database in which plant schedule-related data is configured through a plurality of layers. That is, the schedule planning structure may indicate a database for determining and mapping a similarity level based on at least one of past project comparison, item similarity, similar project participation, and resource similarity. The replacement schedule network configuration unit 207 may search for a plurality of candidate replacement elements similar to the issue element by using the schedule planning structure. According to an embodiment of the present disclosure, the replacement schedule network configuration unit 207 may have a similar level among the lost nodes through the schedule planning structure when one of the nodes constituting the schedule network is lost. Higher nodes may be determined as candidate replacement nodes. The configuration of the scheduling structure is described in detail in FIG. 8 .

After the plurality of candidate replacement elements are determined, the replacement schedule network configuration unit 207 may determine the replacement element based on the current status of the plurality of candidate replacement elements. According to an embodiment of the present disclosure, when one node among nodes constituting a predetermined network is lost, the replacement schedule network configuration unit 207 selects an alternate node based on current availability information of a plurality of candidate replacement nodes. can decide According to an embodiment of the present disclosure, the available status information may include whether to participate in other projects, and analysis information related to various process cycle times. In the process in which the replacement schedule network configuration unit 207 determines the replacement element, deep learning mapping may be performed, and accordingly, a mapped replacement schedule network may be generated.

After performing the dynamic reconfiguration (709) procedure for the alternative schedule network, the alternative schedule network configuration unit 207 may perform the alternative plant scheduling decision (711) procedure. The alternate schedule network configuration unit 207 may generate an alternate schedule network including the determined network elements, and determine an alternate plant schedule plan based on the generated alternate schedule network.

8 is a schematic diagram 800 of a method by which the replacement schedule network configuration unit 207 determines candidate replacement elements in a power plant system according to various embodiments of the present disclosure.

Referring to FIG. 8 , the replacement schedule network configuration unit 207 may determine a plurality of candidate replacement elements by using the schedule planning structure 810 . That is, when an issue element is input to the schedule planning structure 810 , the schedule planning structure 810 outputs a plurality of candidate replacement elements. Here, the schedule planning structure 810 indicates a database composed of a plurality of layers, which the replacement schedule network configuration unit 207 uses to determine a plurality of candidate replacement elements.

When an abnormal situation occurs in an element of the schedule network, the alternative schedule network configuration unit 207 may determine a similar element by using the similarity related to the issue element. To this end, the alternative schedule network configuration unit 207 may search for a schedule planning structure 810 . According to an embodiment of the present disclosure, in case of loss to a node of a schedule network, the replacement schedule network configuration unit 207 searches for the schedule planning structure 810 in order to check the similarity with the issue node.

Referring to FIG. 8 , the scheduling structure 810 shows a plurality of nodes and a connection state between the plurality of nodes, an ontology layer 801 , a scheduling layer 803 , and a connection object. It is configured in connection with the layer (objective layer) and the mapping layer (mapping layer). Here, each of the plurality of layers may be divided into a plurality of detailed layers based on plant schedule information.

The ontology layer 801 indicates each of the plurality of nodes. The ontology layer 801 may be responsible for the meaning of each of the plurality of nodes. According to an embodiment of the present disclosure, the power plant process A, process B, and the like may be configured as an ontology layer 801 .

The process layer 803 indicates a detailed process. The process layer 803 may indicate detailed process items included in a plurality of processes. According to an embodiment of the present disclosure, detailed process items A1, A2, B1, B2, etc. included in process A may be configured as a process layer 803 .

The connection object layer 805 indicates those in charge of the process. According to an embodiment of the present disclosure, the connection object layer 805 may indicate nodes of power plants and detailed plant companies and personnel responsible for respective processes.

The mapping layer 807 indicates a layer constituting a mapping relationship connecting the ontology layer 801 , the process layer 803 , and the connection object layer 805 . According to an embodiment of the present disclosure, the mapping layer 807 may configure a mapping relationship connecting certain resource manager nodes and the process layer.

When an abnormal situation occurs in an element of the schedule network, the alternate schedule network configuration unit 207 may determine a plurality of candidate alternate elements having a high similarity level in relation to the issue element by using the schedule planning structure. According to an embodiment of the present disclosure, when an abnormal situation occurs in a node, the alternate schedule network configuration unit 207 uses the schedule planning structure to share the same detailed process layer and the same detailed ontology layer as the issue node. Candidate replacement nodes may be determined.

Thereafter, the replacement schedule network configuration unit 207 may determine a replacement element from among a plurality of candidate similar elements by using an artificial neural network. According to an embodiment of the present disclosure, the replacement schedule network configuration unit 207 may perform connection deep learning on the replacement elements. Here, deep learning may be modeled based on at least one of SOM and DNN. As the replacement schedule network configuration unit 207 uses the artificial neural network, the adjacent relation of the issue element is located in the input layer, and the determined replacement element is located in the output layer. That is, the replacement schedule network configuration unit 207 may determine the replacement element having the highest adjacency relationship through DNN learning, and configure a new replacement schedule network based on the replacement element.

9 illustrates an example 900 of a network configured by the power plant schedule management system 107 in the power plant system according to various embodiments of the present disclosure. 9 illustrates a supply chain management (SCM) network.

Referring to the graph of FIG. 9 , the horizontal axis and the vertical axis indicate distances in relation to the arrangement of each node, and points arranged on the graph indicate each node. 9 illustrates a supplier, manufacturer, logistics, warehouse, marketing subsidiary, and retailer/wholesaler as respective nodes, but the respective nodes are not limited as in FIG. 9 . The first graph 910 exemplifies a network generated by the schedule network configuration unit 203 , and the second graph 960 exemplifies a network generated by the alternate schedule network configuration unit 207 .

Referring to FIG. 9 , the power plant schedule management system 107 may create a network using the schedule network configuration unit 203 . Thereafter, when an abnormal situation occurs in a network element, the power plant schedule management system 107 may generate an alternate network by using the alternate schedule network configuration unit 207 . Here, FIG. 9 exemplifies a case in which a connection state 961 is added to the network, and the alternative schedule network configuration unit 207 may add the connection state 961 to create an alternative network similar to the existing network. .

FIG. 10 is a flowchart 1000 of an operation method for determining an alternative plant schedule by the power plant schedule management system 107 in a power generation plant system according to various embodiments of the present disclosure.

Referring to FIG. 10 , in step 1001 , the power plant schedule management system 107 acquires plant schedule information on a plurality of nodes from the plant schedule planning database. The power plant schedule management system 107 may acquire data regarding the performance schedule of the power plant business and the past plant schedule planning history. The power plant schedule management system 107 may acquire schedule information necessary for determining a schedule network and a plant schedule plan in connection with a plant schedule planning database. According to an embodiment of the present disclosure, the information about the plant schedule may include past plant schedule planning history information and current plant schedule information.

In step 1003 , the power plant schedule management system 107 configures a first schedule network in which plant schedule planning conditions are reflected, based on the plant schedule information. The power plant schedule management system 107 may generate a schedule network in which a plurality of nodes are connected and configured based on the acquired plant schedule information. According to an embodiment of the present disclosure, the power plant schedule management system 107 may generate a schedule network by reflecting the conditions of the current plant schedule plan. According to an embodiment of the present disclosure, the power plant schedule management system 107 may classify plant schedule information about a plurality of nodes based on process configuration, resource configuration, restrictions, and detailed information.

In step 1005 , the power plant schedule management system 107 identifies whether an abnormality has occurred in at least one of the elements constituting the first schedule network. The power plant schedule management system 107 may identify whether an abnormality has occurred in at least one of the elements constituting the schedule network. Here, the element may indicate at least one of a plurality of nodes constituting a predetermined network and a connection state between the plurality of nodes. The power plant schedule management system 107 obtains information indicating that an abnormal situation has occurred in the schedule network from the outside, and can identify whether to configure an alternative schedule network to replace the first schedule network in response .

In step 1007 , the power plant scheduling management system 107 configures a second schedule network to replace the first schedule network based on the learned artificial neural network. The power plant schedule management system 107 may determine a replacement element for replacing an issue element in which an abnormal situation occurs based on information about the plant schedule. According to an embodiment of the present disclosure, the power plant scheduling management system 107 may configure a scheduling structure based on a plurality of layers in order to use the artificial neural network. The power plant scheduling management system 107 may determine candidate replacement factors using the scheduling structure, and may determine replacement factors using an artificial neural network. According to an embodiment of the present disclosure, the artificial neural network may be modeled based on at least one of SOM and DNN.

In step 1009 , the power plant scheduling management system 107 may determine an alternative plant scheduling plan based on the second schedule network. The power plant scheduling management system 107 may determine the plant replacement scheduling plan using the second schedule network including the replacement element. According to an embodiment of the present disclosure, the power plant schedule management system 107 may evaluate an alternate schedule based on the alternate plant schedule.

11 illustrates a flowchart 1100 of a method for generating an alternative schedule network by the power plant scheduling management system 107 in a power plant system according to various embodiments of the present disclosure.

Referring to FIG. 11 , in step 1101 , the power plant schedule management system 107 determines an issue element in which an abnormal situation occurs among elements of the first schedule network. According to an embodiment of the present disclosure, the issue element may indicate at least one node among a plurality of nodes. Accordingly, when a loss occurs in at least one of the nodes included in the first schedule network, the power plant schedule management system 107 determines the node in which the loss occurs as an issue node, and is not included in the first schedule network. When a node is added to the first schedule network, the added node may be determined as an issue node.

According to another embodiment of the present disclosure, the issue element may indicate a connection state between a plurality of nodes. Accordingly, when a loss occurs in the connection state included in the first schedule network, the power plant schedule management system 107 determines the connection state in which the loss occurs as the issue connection state, and is not included in the first schedule network. When the connection state is added to the first schedule network, the added connection state may be determined as an issue connection state.

In step 1103 , the power plant scheduling management system 107 determines candidate replacement elements for replacing the issue element based on the scheduling structure. According to an embodiment of the present disclosure, the scheduling structure may include an ontology layer, a process layer, a connection object layer, and a mapping layer. According to an embodiment of the present disclosure, the ontology layer indicates a plurality of processes, the process layer indicates at least one detailed process included in the plurality of processes, and the connection object layer is at least one for managing the plurality of processes. of the process person in charge, and the mapping layer may indicate a layer constituting a connection relationship between at least one detailed process and at least one process person based on the ontology layer, process layer, and connection object layer of the scheduling structure. have.

According to an embodiment of the present disclosure, the power plant schedule management system 107 is based on the arrangement of the issue elements in the ontology layer, the process layer, the connection object layer, and the mapping layer, the process, detailed process, and at least one of the person in charge may determine the same elements as candidate replacement elements.

In step 1105 , the power plant scheduling management system 107 determines a replacement element from among the candidate replacement elements through the artificial neural network. According to an embodiment of the present disclosure, the power plant schedule management system 107 may use deep learning and data mining techniques. According to an embodiment of the present disclosure, when one node among nodes constituting a schedule network is lost, the power plant schedule management system 107 may be configured to perform a replacement node based on current availability information of a plurality of candidate replacement nodes. can be decided According to an embodiment of the present disclosure, the available status information may include whether to participate in other projects, and analysis information related to various process cycle times.

In step 1107 , the power plant scheduling management system 107 may configure the second scheduling network to include the replacement element. According to an embodiment of the present disclosure, the power plant schedule management system 107 may configure a replacement schedule network including the replacement factor for the reason why the replacement factor is determined.

The occurrence of process delays and abnormal processes in the power plant deteriorates the economic feasibility and profitability of not only the overall process execution as a result of design changes, but also the establishment of follow-up measures and the operation part. In particular, the abnormal situation may cause more frequent loss of nodes and connection states constituting the schedule than the general delay issue situation, and may cause a risk of worsening profitability and impossibility of continuing the project.

Methods according to the embodiments described in the claims or specifications of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. One or more programs stored in the computer-readable storage medium are configured to be executable by one or more processors in an electronic device (device). One or more programs include instructions for causing an electronic device to execute methods according to embodiments described in a claim or specification of the present disclosure.

Such programs (software modules, software) include random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable ROM (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other It may be stored in an optical storage device or a magnetic cassette. Alternatively, it may be stored in a memory composed of a combination of some or all thereof. In addition, each configuration memory may be included in plurality.

In addition, the program is transmitted through a communication network consisting of a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that can be accessed. Such a storage device may be connected to a device implementing an embodiment of the present disclosure through an external port. In addition, a separate storage device on the communication network may be connected to the device implementing the embodiment of the present disclosure.

In the specific embodiments of the present disclosure described above, elements included in the disclosure are expressed in the singular or plural according to the specific embodiments presented. However, the singular or plural expression is appropriately selected for the context presented for convenience of description, and the present disclosure is not limited to the singular or plural component, and even if the component is expressed in plural, it is composed of the singular or singular. Even an expressed component may be composed of a plurality of components.

Meanwhile, although specific embodiments have been described in the detailed description of the present disclosure, various modifications are possible without departing from the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the described embodiments and should be defined by the claims described below as well as the claims and equivalents.

Claims (11)

1. In the operating method of a system for managing a schedule of a power plant based on an artificial neural network,

   obtaining, from the plant schedule planning database, plant schedule information about a plurality of nodes;

   configuring a first schedule network to which plant schedule planning conditions are reflected, based on the plant schedule information;

   identifying whether an abnormal situation has occurred in at least one of the elements constituting the first schedule network;

   configuring a second schedule network to replace the first schedule network based on the learned artificial neural network; and

   and determining an alternative plant schedule plan based on the second schedule network.
2. The method according to claim 1,

   The information on the plant schedule is an operating method of a power plant schedule management system including past plant schedule planning history information and current plant schedule information.
3. 3. The method according to claim 2,

   The step of configuring the first schedule network comprises:

   The method of operating a power plant schedule management system further comprising the step of classifying plant schedule information about the plurality of nodes based on process configuration, resource configuration, restrictions, and detailed information.
4. The method according to claim 1,

   The step of configuring the second schedule network comprises:

   determining an issue element in which the abnormal situation occurs among elements of the first schedule network;

   determining candidate replacement elements for replacing the issue element based on a scheduling structure;

   determining a replacement element from among the candidate replacement elements through the artificial neural network; and

   configuring the second schedule network to include the replacement element;

   The scheduling structure is an operating method of a power plant schedule management system consisting of an ontology layer, a process layer, a connection object layer, and a mapping layer.
5. 5. The method according to claim 4,

   the issue element includes at least one node among the plurality of nodes;

   The step of determining the issue factor,

   when loss occurs in at least one of the nodes included in the first schedule network, determining the node in which the loss has occurred as an issue node; and

   and determining the added node as an issue node when a node not included in the first schedule network is added to the first schedule network.
6. 5. The method according to claim 4,

   The issue element includes a connection state between the plurality of nodes,

   The step of determining the issue factor,

   determining, when a loss occurs in a connection state included in the first schedule network, a connection state in which the loss occurs as an issue connection state; and

   and determining the added connection state as an issue connection state when a connection state not included in the first schedule network is added to the first schedule network.
7. 5. The method according to claim 4,

   The ontology layer indicates a plurality of processes,

   The process layer indicates at least one detailed process included in the plurality of processes,

   The connection object layer indicates at least one process person in charge of managing the plurality of processes,

   The mapping layer is based on the ontology layer, the process layer, and the connection object layer of the scheduling structure, indicating a layer constituting a connection relationship between the at least one detailed process and the at least one process manager. How a plant scheduling management system works.
8. 8. The method of claim 7,

   The step of determining the candidate replacement factors comprises:

   Based on the arrangement of the issue element in the ontology layer, the process layer, the connection object layer, and the mapping layer, elements having the same at least one of a process used by the issue element, a detailed process, and a person in charge are selected as the candidate replacement element A method of operating a power plant scheduling management system comprising the step of determining
9. 5. The method according to claim 4,

   The artificial neural network is

   A method of operating a power plant scheduling management system modeled based on at least one of a self organizing map (SOM) and a deep neural network (DNN).
10. The method according to claim 1,

    The method of operating a power plant schedule management system further comprising the step of evaluating an alternate schedule based on the alternate plant schedule plan.
11. A system for managing a schedule of a power plant based on an artificial neural network, the system comprising:

    a data linkage unit for acquiring plant schedule information on a plurality of nodes from the plant schedule planning database;

    a schedule network configuration unit configured to configure a first schedule network to which plant schedule planning conditions are reflected, based on the plant schedule information;

    an abnormal situation management unit for identifying whether an abnormal situation has occurred in at least one of the elements constituting the first schedule network;

    A power plant schedule comprising: a second schedule network configured to replace the first schedule network based on the learned artificial neural network; and an alternate schedule network configuration unit configured to determine an alternate plant schedule plan based on the second schedule network plan management system.

Images