Equipment maintenance decision-making method and device for thermal power plant, medium and equipment

Abstract

The invention relates to an equipment maintenance decision-making method and device for a thermal power plant, a medium and equipment. The decision-making quality and the working efficiency can be improved. The method comprises the following steps: acquiring a multi-source data set of target equipment in the thermal power plant, wherein the multi-source data set comprises component data, historical maintenance data and equipment sensor real-time data of the target equipment; constructing a target equipment knowledge graph according to the multi-source data set; in response to an input instruction of a user for the target equipment, determining user intention information corresponding to the input instruction, and obtaining a target Mermaid graph according to the user intention information and the target equipment knowledge graph; and determining a maintenance strategy of the target equipment according to the target Mermaid graph.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to an equipment maintenance decision method, device, medium and equipment for a thermal power plant. Background Art

[0002] In a thermal power plant, when related equipment fails, technicians need to quickly diagnose the cause of the failure and develop a corresponding maintenance plan. Equipment maintenance decisions involve complex fault diagnosis, data analysis, performance optimization, and other aspects, all of which rely on accurate information acquisition and effective communication.

[0003] In related technologies, although artificial intelligence technology has been used to support equipment maintenance decisions, it mainly relies on text and language interaction, which leads to the lack of clear thinking paths for technicians in the decision-making process and makes it difficult to meet the needs of efficient and accurate communication. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method, device, medium and equipment for equipment maintenance decision-making in a thermal power plant to improve decision-making quality and work efficiency.

[0005] In order to achieve the above objectives, in a first aspect, the present disclosure provides an equipment maintenance decision method for a thermal power plant, the method comprising: Acquire a multi-source data set of a target device in a thermal power plant, wherein the multi-source data set includes component data, historical maintenance data, and real-time data of device sensors of the target device; Construct a target device knowledge graph based on the multi-source data set; In response to an input instruction from a user to the target device, determining user intent information corresponding to the input instruction, and obtaining a target Mermaid graph according to the user intent information and the target device knowledge graph; A maintenance strategy for the target device is determined according to the target Mermaid graph.

[0006] Optionally, constructing a target device knowledge graph according to the multi-source data set includes: Performing text preprocessing on the multi-source data set to obtain knowledge graph entity data, wherein the knowledge graph entity data includes a plurality of entities related to the target device; Determine triple information in the multi-source data set according to the knowledge graph entity data; The target device knowledge graph is constructed according to the triple information.

[0007] Optionally, the multi-source data set includes structured data, semi-structured data and unstructured data; The text preprocessing of the multi-source data set to obtain knowledge graph entity data includes: Performing knowledge extraction on the semi-structured data and the unstructured data to obtain structured knowledge extraction results; Fusion of the knowledge extraction result and the structured data to obtain knowledge graph text data; The knowledge graph text data is segmented based on the point mutual information algorithm to obtain knowledge graph entity data.

[0008] Optionally, obtaining a target Mermaid graph according to the user intent information and the target device knowledge graph includes: Based on the user intention information, a search operation is performed on the target device knowledge graph to obtain target knowledge information related to the user intention information; Performing knowledge reasoning on the target device knowledge graph according to the target knowledge information to obtain a knowledge reasoning result; According to the knowledge reasoning result, the corresponding target Mermaid graph is obtained.

[0009] Optionally, determining the maintenance strategy of the target device according to the target Mermaid graph includes: In response to a user selecting any node in the target Mermaid graph, determining the current display content of the target Mermaid graph according to the node, the current display content including the equipment maintenance decision path and maintenance suggestion information corresponding to the node; A maintenance strategy for the target device is determined according to the current display content.

[0010] Optionally, the type of the target Mermaid graph includes at least one of a flow chart, a timing diagram, and an entity relationship diagram.

[0011] Optionally, the method further comprises: When it is determined that the user has executed and completed the maintenance strategy, the target device knowledge graph is updated based on the currently acquired real-time data of the device sensors and the device maintenance data.

[0012] In a second aspect, the present disclosure provides an equipment maintenance decision-making device for a thermal power plant, the device comprising: An acquisition module, used to acquire a multi-source data set of a target device in a thermal power plant, wherein the multi-source data set includes component data, historical maintenance data, and real-time data of device sensors of the target device; A construction module, used to construct a target device knowledge graph based on the multi-source data set; A determination module, configured to determine, in response to an input instruction from a user to the target device, user intention information corresponding to the input instruction, and obtain a target Mermaid graph according to the user intention information and the target device knowledge graph; A decision module is used to determine a maintenance strategy for the target device according to the target Mermaid graph.

[0013] In a third aspect, the present disclosure further provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0014] In a fourth aspect, the present disclosure further provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0015] Through the above technical solution, a multi-source data set of the target equipment in the thermal power plant is obtained, and the multi-source data set includes the component data, historical maintenance data and real-time data of the equipment sensor of the target equipment; a knowledge graph of the target equipment is constructed according to the multi-source data set; in response to the user's input instruction for the target equipment, the user intention information corresponding to the input instruction is determined, and the target Mermaid graph is obtained according to the user intention information and the target equipment knowledge graph; according to the target Mermaid graph, the maintenance strategy of the target equipment is determined. Among them, by constructing a knowledge graph through a multi-source data set and generating an interactive Mermaid graph based on the user intention information and the knowledge graph, the decision results and related knowledge systems can be effectively graphically presented to ensure the accurate transmission of information, thereby improving the decision quality and work efficiency.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The figure is a flow chart showing a method for equipment maintenance decision-making in a thermal power plant according to an exemplary embodiment of the present disclosure.

[0018] Figure 2 The present invention is a block diagram of an equipment maintenance decision-making device for a thermal power plant according to an exemplary embodiment of the present invention.

[0019] Figure 3It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0021] As mentioned in the background technology, although artificial intelligence technology has been used in related technologies to support equipment maintenance decisions, it mainly relies on text and language interaction, resulting in a lack of clear thinking paths in the decision-making process of technicians, making it difficult to meet the needs of efficient and accurate communication.

[0022] In view of this, the embodiments of the present disclosure provide a method, apparatus, medium and equipment for equipment maintenance decision-making in a thermal power plant, which can improve decision-making quality and work efficiency.

[0023] Figure 1 A method for equipment maintenance decision-making in a thermal power plant is shown according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the method may include the following steps: Step S101, obtaining a multi-source data set of a target device in a thermal power plant, the multi-source data set including component data, historical maintenance data and real-time data of device sensors of the target device; Step S102, constructing a target device knowledge graph based on multi-source data sets; Step S103, in response to the user's input instruction for the target device, determining the user's intention information corresponding to the input instruction, and obtaining the target Mermaid graph according to the user's intention information and the target device knowledge graph; Step S104: determining a maintenance strategy for the target device according to the target Mermaid graph.

[0024] It should be understood that the knowledge graph is a structured knowledge representation method that can be used to describe various information related to the target device and its relationships. It can be understood as a mesh structure in which nodes represent entities such as device components, states, parameters, etc., and edges represent various relationships between entities, which helps the system understand and analyze the overall status of the device.

[0025] It should be understood that Mermaid is a graphical representation tool that allows users to describe charts in text format, and then converts the text into visual charts through a rendering engine to facilitate description and presentation in documents. In the disclosed embodiment, a complex equipment maintenance decision process can be converted into an intuitive visual graphic that can clearly and intuitively display the relevant technical process, operation steps or fault diagnosis process, helping technicians better understand the decision path and basis, and avoiding misunderstandings that may occur in traditional text communication.

[0026] For example, the target device knowledge graph can be stored in a relational graph database (such as Neo4j, Amazon Neptune, etc.), which can support dynamic updates and reasoning.

[0027] For example, when the target device is a boiler, the multi-source data set may include historical maintenance records of the boiler, real-time sensor data, expert experience and other multi-source data, thereby constructing a knowledge graph of the boiler. The corresponding knowledge graph may contain component information of the boiler, historical failure cases, maintenance cycles, common failure modes, etc.

[0028] For example, when the target device is a boiler, the technician can describe the abnormal phenomenon of the boiler through natural language as an input instruction, such as "the boiler pressure drops and the temperature rises abnormally", and the user intention information corresponding to the input instruction can be determined as "fault diagnosis" through natural language processing (NLP) technology.

[0029] For example, the type of the target Mermaid graph may include at least one of a flow chart, a sequence diagram, and an entity relationship diagram. For example, a sequence diagram may be used to display the failure mode of a power generation device to help technicians analyze the time sequence and influencing factors of the failure. For example, the target equipment knowledge graph may include but is not limited to information such as the type of power generation equipment, maintenance history, failure mode, and predictive maintenance recommendations.

[0030] Through the above method, a multi-source data set of the target equipment in the thermal power plant is obtained, and the multi-source data set includes the component data, historical maintenance data and real-time data of the equipment sensor of the target equipment; a knowledge graph of the target equipment is constructed according to the multi-source data set; in response to the user's input instruction for the target equipment, the user intention information corresponding to the input instruction is determined, and the target Mermaid graph is obtained according to the user intention information and the target equipment knowledge graph; according to the target Mermaid graph, the maintenance strategy of the target equipment is determined. Among them, by constructing a knowledge graph through a multi-source data set and generating an interactive Mermaid graph based on the user intention information and the knowledge graph, the decision results and related knowledge systems can be effectively graphically presented to ensure the accurate transmission of information, thereby improving the decision quality and work efficiency.

[0031] In a possible implementation, building a target device knowledge graph based on multi-source data sets may include: Perform text preprocessing on multi-source data sets to obtain knowledge graph entity data, which includes multiple entities related to the target device; Determine triple information in multi-source datasets based on knowledge graph entity data; Build the target device knowledge graph based on the triple information.

[0032] It should be understood that by preprocessing the text of multi-source data sets, raw data in different formats can be converted into a unified standard format, and key information related to the target device can be extracted to eliminate noise and redundancy in the data, thereby providing basic data for subsequent knowledge graph construction.

[0033] It should be understood that by analyzing the relationship between entities, a triple structure of "subject-relationship-object" can be formed, for example, "boiler-contains-safety valve", "pressure drop-leads to-temperature abnormality", etc. The triple information can reflect the association between equipment components, the causal relationship of failure modes, etc.

[0034] In a possible implementation, the multi-source data set includes structured data, semi-structured data, and unstructured data; Perform text preprocessing on multi-source datasets to obtain knowledge graph entity data, which can include: Extract knowledge from semi-structured data and unstructured data to obtain structured knowledge extraction results; Integrate knowledge extraction results with structured data to obtain knowledge graph text data; The knowledge graph text data is segmented based on the point mutual information algorithm to obtain the knowledge graph entity data.

[0035] It should be understood that, regarding the knowledge extraction process, for semi-structured data, specific formats can be parsed to extract key information; for unstructured data, natural language processing technology can be used to identify and extract important entities and relationships.

[0036] It should be understood that integrating the knowledge extraction results with the original structured data can unify the data format, eliminate redundancy and inconsistency, and form a unified knowledge graph text data.

[0037] It should be understood that the use of the point mutual information (PMI) algorithm for word segmentation can accurately identify the professional terms and complex equipment names of thermal power plants. By calculating the degree of correlation between words, the algorithm can effectively identify fixed character combinations (such as "feedwater pump", "steam turbine unit", etc.), avoid incorrect segmentation of professional terms, thereby improving the accuracy of entity recognition and providing more reliable entity data support for the subsequent construction of knowledge graphs.

[0038] For example, among the data types of multi-source data sets, structured data can be numerical data of equipment sensors, standardized parameter records, etc.; semi-structured data can be equipment manuals in XML format, maintenance records in JSON format, etc.; unstructured data can be natural language texts such as written records of maintenance personnel and fault diagnosis reports.

[0039] Through the above method, different types of data can be effectively converted into unified and structured knowledge graph entity data, ensuring that the data foundation for subsequent knowledge graph construction is accurate and reliable.

[0040] In a possible implementation, obtaining a target Mermaid graph according to user intent information and a target device knowledge graph may include: Based on the user intent information, a search operation is performed on the target device knowledge graph to obtain target knowledge information related to the user intent information; Perform knowledge reasoning on the target device knowledge graph according to the target knowledge information to obtain the knowledge reasoning result; According to the knowledge reasoning results, the corresponding target Mermaid graph is obtained.

[0041] It should be understood that when a user inputs a question or demand, the input content can first be semantically parsed and intent recognized to extract keywords and core needs; then the context and purpose of the query can be analyzed through the Dialog Management System combined with natural language processing (NLP) technology to generate standardized query instructions; finally, the query instructions are converted into graph query statements, and a targeted search is performed in the knowledge graph to obtain and organize relevant knowledge information, thereby ensuring that query results that match the user's intent are returned.

[0042] It should be understood that it is possible to conduct a targeted search in the target device knowledge graph based on the user's intent, locate nodes and relationships related to the query, and extract knowledge points that meet the query conditions (such as device status, fault causes, etc.). This achieves an accurate match between user needs and device knowledge stored in the knowledge graph, ensuring the accuracy of subsequent reasoning and visualization.

[0043] It should be understood that in the process of converting the results of knowledge reasoning into Mermaid graphs, the structured data obtained by reasoning can be parsed first to identify the node and relationship information and logical hierarchy therein; then this information can be converted into corresponding graphic elements and connection relationships according to the Mermaid syntax specifications, and appropriate layout parameters can be set; finally, the Mermaid graphic code is generated and rendered to display the relationship between knowledge in an intuitive way, making it easier for users to understand complex reasoning results.

[0044] For example, when the content of the input instruction is "boiler pressure drops, temperature rises abnormally", the user's intention can be identified as "fault diagnosis" by analyzing the technician's input instruction, and fault cases and maintenance suggestions related to boiler pressure drop and abnormal temperature can be retrieved from the knowledge graph. Based on the reasoning results, a Mermaid time series diagram can be generated to show the change process of the boiler from normal state to abnormal state, which can include time points, pressure and temperature change curves to help technicians analyze the time series and influencing factors of the fault. The abnormal points can be highlighted in the graph and linked to possible fault causes and historical cases. Through the Mermaid graph, technicians can intuitively understand the fault status and maintenance steps of the boiler, improving the efficiency and accuracy of fault handling.

[0045] Through the above method, the Mermaid graphical display method based on user intent information and target device knowledge graph is used to present complex equipment and technical information in a graphical way, which can help technicians understand complex technical problems and equipment conditions more intuitively, thereby reducing understanding time and improving decision-making quality and efficiency.

[0046] In a possible implementation, determining a maintenance strategy for a target device according to a target Mermaid graph may include: In response to a user selecting any node in the target Mermaid graph, determining the current display content of the target Mermaid graph according to the node, the current display content including the equipment maintenance decision path and maintenance suggestion information corresponding to the node; Determine the maintenance strategy for the target device based on the current display content.

[0047] It should be understood that the user can select the node of interest in the Mermaid graphical interface. In response to the user's selection operation, the Mermaid graphic can dynamically update the current display content according to the attributes and associated information of the selected node. Among them, the current display content can display the equipment maintenance decision path related to the selected node, as well as the corresponding maintenance suggestion information. Based on the currently displayed decision path and suggestions, a targeted equipment maintenance plan can be formulated to ensure the executability of the maintenance strategy.

[0048] For example, when a Mermaid timing diagram is generated to show the change process of a boiler from a normal state to an abnormal state, and the abnormal point is highlighted, the user can click on the abnormal point in the diagram to trigger the update of the diagram and display the relevant fault diagnosis flowchart, which includes possible fault causes and recommended inspection steps. Based on this graphical information, technicians can quickly understand the possible causes of the fault.

[0049] For example, after the technician confirms the current display content of the graphic, the knowledge graph can be automatically triggered to perform corresponding knowledge reasoning, obtain targeted maintenance suggestions, such as "check the boiler safety valve" or "adjust combustion parameters", and generate a Mermaid flowchart of the maintenance process to guide the technician to follow the best practices. In addition, risk prediction diagrams can be generated by analyzing historical equipment data to assist technicians in making timely adjustments.

[0050] Through the above methods, this graphical interactive method reduces communication errors and ensures the accurate transmission of information, so that accurate and efficient decision support can be given for various special situations in the power system.

[0051] In a possible implementation, the method may further include: When it is determined that the user has executed and completed the maintenance strategy, the knowledge graph of the target device is updated based on the real-time data of the device sensors and the device maintenance data currently obtained.

[0052] It should be understood that the real-time data from equipment sensors can reflect the equipment status after maintenance, and the equipment maintenance data can record specific maintenance operations and results, thereby enabling in-depth mining of the equipment status and maintenance history, and providing real-time data-based recommendations.

[0053] It should be understood that after a technician performs a maintenance operation, the knowledge graph can be dynamically updated based on new sensor data and maintenance records, and the corresponding Mermaid graph can be regenerated to reflect the latest equipment status and maintenance history.

[0054] For example, the knowledge update content may include: updating device status information, supplementing maintenance records, adjusting the association relationship of related knowledge nodes, etc.

[0055] Through the above method, the timeliness and accuracy of the knowledge graph can be maintained through dynamic updating of the knowledge graph, enhancing the decision support capability.

[0056] In summary, the equipment maintenance decision-making method for thermal power plants has the following advantages: 1) Improve work efficiency: Through graphical display, technicians can understand complex technical problems and equipment conditions more intuitively, reduce understanding time, and improve decision-making efficiency.

[0057] 2) Reduce communication errors: Through graphical feedback, ensure that technicians can clearly and intuitively understand the reasoning process, avoiding misunderstandings that may occur in traditional text communication.

[0058] 3) Enhanced decision support: By combining the reasoning capabilities of knowledge graphs and Mermaid graphs, powerful decision support is provided, especially when choosing between complex problems and multiple solutions, and the advantages, disadvantages and potential risks of each solution can be clearly displayed.

[0059] Figure 2 According to an exemplary embodiment of the present disclosure, an equipment maintenance decision-making device 200 for a thermal power plant is shown. Figure 2 As shown, the equipment maintenance decision-making device 200 may include: An acquisition module 201 is used to acquire a multi-source data set of a target device in a thermal power plant, wherein the multi-source data set includes component data, historical maintenance data, and real-time data of device sensors of the target device; A construction module 202 is used to construct a target device knowledge graph based on the multi-source data set; A determination module 203 is used to determine user intention information corresponding to the input instruction of the target device in response to the user's input instruction, and obtain a target Mermaid graph according to the user intention information and the target device knowledge graph; The decision module 204 is used to determine the maintenance strategy of the target device according to the target Mermaid graph.

[0060] Optionally, the construction module 202 includes: A preprocessing submodule is used to perform text preprocessing on multi-source data sets to obtain knowledge graph entity data, which contains multiple entities related to the target device; A determination submodule is used to determine triple information in a multi-source data set based on knowledge graph entity data; The construction submodule is used to build the target device knowledge graph based on the triple information.

[0061] Optionally, the multi-source data set includes structured data, semi-structured data, and unstructured data; The preprocessing submodule is used to: Extract knowledge from semi-structured data and unstructured data to obtain structured knowledge extraction results; Integrate knowledge extraction results with structured data to obtain knowledge graph text data; The knowledge graph text data is segmented based on the point mutual information algorithm to obtain the knowledge graph entity data.

[0062] Optionally, the determination module 203 is used to: Based on the user intent information, a search operation is performed on the target device knowledge graph to obtain target knowledge information related to the user intent information; Perform knowledge reasoning on the target device knowledge graph according to the target knowledge information to obtain the knowledge reasoning result; According to the knowledge reasoning results, the corresponding target Mermaid graph is obtained.

[0063] Optionally, the decision module 204 is used to: In response to a user selecting any node in the target Mermaid graph, determining the current display content of the target Mermaid graph according to the node, the current display content including the equipment maintenance decision path and maintenance suggestion information corresponding to the node; Determine the maintenance strategy for the target device based on the current display content.

[0064] Optionally, the type of the target Mermaid graph includes at least one of a flow chart, a timing diagram, and an entity relationship diagram.

[0065] Optionally, the equipment maintenance decision-making device 200 further includes an updating module, which is used to: When it is determined that the user has executed and completed the maintenance strategy, the target device knowledge graph is updated based on the currently acquired real-time data of the device sensors and the device maintenance data.

[0066] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0067] Figure 3 FIG. 1 is a block diagram of an electronic device 300 according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0068] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned equipment maintenance decision method for a thermal power plant. The memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0069] In an exemplary embodiment, the electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned equipment maintenance decision method for thermal power plants.

[0070] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned equipment maintenance decision method for a thermal power plant are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned equipment maintenance decision method for a thermal power plant.

[0071] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0072] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0073] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for equipment maintenance decision-making in a thermal power plant, characterized in that: The method comprises: Acquire a multi-source data set of a target device in a thermal power plant, wherein the multi-source data set includes component data, historical maintenance data, and real-time data of device sensors of the target device; Construct a target device knowledge graph based on the multi-source data set; In response to an input instruction from a user to the target device, determining user intent information corresponding to the input instruction, and obtaining a target Mermaid graph according to the user intent information and the target device knowledge graph; A maintenance strategy for the target device is determined according to the target Mermaid graph.

2. The method according to claim 1, characterized in that The step of constructing a target device knowledge graph according to the multi-source data set includes: Performing text preprocessing on the multi-source data set to obtain knowledge graph entity data, wherein the knowledge graph entity data includes a plurality of entities related to the target device; Determine triple information in the multi-source data set according to the knowledge graph entity data; The target device knowledge graph is constructed according to the triple information.

3. The method according to claim 2, characterized in that The multi-source data set includes structured data, semi-structured data and unstructured data; The text preprocessing of the multi-source data set to obtain knowledge graph entity data includes: Performing knowledge extraction on the semi-structured data and the unstructured data to obtain structured knowledge extraction results; Fusion of the knowledge extraction result and the structured data to obtain knowledge graph text data; The knowledge graph text data is segmented based on the point mutual information algorithm to obtain knowledge graph entity data.

4. The method according to claim 1, characterized in that: The step of obtaining a target Mermaid graph according to the user intent information and the target device knowledge graph includes: Based on the user intention information, a search operation is performed on the target device knowledge graph to obtain target knowledge information related to the user intention information; Performing knowledge reasoning on the target device knowledge graph according to the target knowledge information to obtain a knowledge reasoning result; According to the knowledge reasoning result, the corresponding target Mermaid graph is obtained.

5. The method according to claim 1, characterized in that The step of determining the maintenance strategy of the target device according to the target Mermaid graph includes: In response to a user selecting any node in the target Mermaid graph, determining the current display content of the target Mermaid graph according to the node, the current display content including the equipment maintenance decision path and maintenance suggestion information corresponding to the node; A maintenance strategy for the target device is determined according to the current display content.

6. The method according to claim 1, characterized in that The type of the target Mermaid graph includes at least one of a flow chart, a sequence diagram, and an entity relationship diagram.

7. The method according to claim 1, characterized in that The method further comprises: When it is determined that the user has executed and completed the maintenance strategy, the target device knowledge graph is updated based on the currently acquired real-time data of the device sensors and the device maintenance data.

8. An equipment maintenance decision-making device for a thermal power plant, characterized in that: The device comprises: An acquisition module, used to acquire a multi-source data set of a target device in a thermal power plant, wherein the multi-source data set includes component data, historical maintenance data, and real-time data of device sensors of the target device; A construction module, used to construct a target device knowledge graph based on the multi-source data set; A determination module, configured to determine, in response to an input instruction from a user to the target device, user intention information corresponding to the input instruction, and obtain a target Mermaid graph based on the user intention information and the target device knowledge graph; A decision module is used to determine a maintenance strategy for the target device according to the target Mermaid graph.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images