Hydropower station on-duty emergency processing method, system and equipment based on knowledge graph, and medium

Abstract

The invention discloses a hydropower station on-duty emergency processing method, system, equipment and medium based on a knowledge graph, and belongs to the technical field of hydropower station emergency processing, and the method comprises the steps: collecting the operation parameter data and historical fault information of a hydropower station, and carrying out the digital processing; based on a natural language processing and artificial intelligence training technology, constructing a knowledge graph including fault types, cause analysis and emergency disposal measures; establishing an intelligent fault diagnosis algorithm based on a knowledge graph, and carrying out fault identification and positioning on the operation data of the hydropower station; performing classification and priority ranking on the faults according to the identified fault result, and matching a corresponding processing flow; and according to the fault classification information, an emergency plan is started, a control instruction is executed to complete emergency processing operation, and recording is carried out. According to the invention, real-time sensing of the operation state of the hydropower station, accurate fault identification and priority classification are realized, and the response speed and processing accuracy of the hydropower station to emergencies are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency treatment of hydropower stations, and in particular to a knowledge graph-based on-duty emergency treatment method, system, equipment and medium for hydropower stations. Background Art

[0002] Currently, when an emergency occurs, the upper computer monitoring system of a hydropower plant cannot sort the signal reporting by urgency and importance, and relies on operators to manually screen key fault information. Due to differences in personal experience, there are large differences in the level of emergency handling, which is very likely to affect the response speed to major accidents, causing accidents to escalate, and damaging equipment and even personnel safety.

[0003] To improve the efficiency and accuracy of emergency response, this invention aims to summarize historical experience to form a knowledge graph for identifying and handling various types of accidents, achieve rapid and comprehensive confirmation of fault information, and instantly present standardized handling process guidance information, ensuring that on-duty personnel can quickly locate faults, follow standard procedures for handling, and effectively curb the expansion of accidents. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to solve the problem that there are large differences in the level of handling of emergency accidents, which is very likely to affect the response speed to major accidents, cause accidents to escalate, and damage equipment and even personnel safety.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a knowledge graph-based on-duty emergency response method for a hydropower station, which includes the following steps: collecting the operating parameter data and historical fault information of the hydropower station and performing digital processing; constructing a knowledge graph containing fault types, cause analysis and emergency response measures based on natural language processing and artificial intelligence training technology; establishing a fault diagnosis model algorithm based on the knowledge graph to identify and locate faults in the hydropower station operation data; classifying and prioritizing the faults according to the identified fault results, and matching the corresponding processing procedures; activating the emergency plan based on the fault classification information, executing the control instructions to complete the emergency response operations, and recording them.

[0007] As a preferred solution of the knowledge graph-based hydropower station on-duty emergency handling method described in the present invention, the construction of a knowledge graph containing fault types, cause analysis and emergency response measures includes: performing text analysis on operating parameter data and historical fault information, extracting entity and relationship information to form structured data; learning the structured data based on a pre-trained artificial intelligence model, and mining potential correlations between faults; deploying a graph database system in the server, and constructing a knowledge graph based on the learning results.

[0008] As a preferred solution of the knowledge graph-based hydropower station on-duty emergency response method described in the present invention, the establishment of a fault diagnosis model algorithm based on the knowledge graph includes taking structured operating parameter data and knowledge graph content as training inputs; and using a deep learning framework in the server to construct and train a fault diagnosis model to realize the identification and location of the fault type.

[0009] As a preferred solution of the knowledge graph-based on-duty emergency response method of a hydropower station described in the present invention, the method includes collecting the operating parameter data and historical fault information of the hydropower station and performing digital processing, including collecting temperature, pressure and flow operating parameters through sensors installed at key equipment locations of the hydropower station; transmitting the operating parameters to the edge computing device through a data transmission network constructed by industrial Ethernet and optical fiber; the edge computing device performs data preprocessing and feature extraction on the operating parameter data, and sends the processing results to the server.

[0010] As a preferred solution of the knowledge graph-based on-duty emergency handling method of a hydropower station described in the present invention, the fault classification and priority sorting include taking the fault type output by the fault diagnosis model as input, classifying the fault level based on the set rules; and prioritizing the fault classification results according to the impact range and severity indicators.

[0011] As a preferred solution of the knowledge graph-based hydropower station on-duty emergency handling method described in the present invention, the initiation of the emergency plan includes the server calling a matching emergency handling process in the emergency response plan library according to the fault type and priority; executing the automation control script associated with the emergency handling process to control the automation equipment to perform emergency operations; and sending a text message through the on-call system to notify the on-duty personnel to respond on site.

[0012] As a preferred solution of the knowledge graph-based hydropower station on-duty emergency handling method described in the present invention, the recording includes recording the entire process of fault identification results, fault classification information, executed emergency response procedures and operating parameter data; the entire process record is written into the server as a new knowledge sample, which serves as training data for subsequent knowledge graph construction and fault diagnosis model optimization.

[0013] Another object of the present invention is to provide a hydropower station duty emergency response system based on knowledge graph.

[0014] In order to solve the above technical problems, the present invention provides the following technical solutions: a hydropower station duty emergency response system based on knowledge graph, comprising: a data acquisition module, a knowledge graph construction module, a fault diagnosis module, a fault processing module and an emergency plan execution module; the data acquisition module is used to collect the operating parameter data and historical fault information of the hydropower station and perform digital processing; the knowledge graph construction module is used to construct a knowledge graph containing fault types, cause analysis and emergency response measures based on natural language processing and artificial intelligence training technology; the fault diagnosis module is used to establish a fault diagnosis model algorithm based on the knowledge graph to identify and locate faults in the hydropower station operation data; the fault processing module is used to classify and prioritize faults according to the identified fault results, and match the corresponding processing flow; the emergency plan execution module is used to start the emergency plan based on the fault classification information, execute control instructions to complete the emergency processing operation, and record it.

[0015] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of the hydropower station on-duty emergency handling method based on a knowledge graph.

[0016] The present invention provides a 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 knowledge graph-based hydropower station on-duty emergency handling method are implemented.

[0017] Beneficial effects of the present invention: The present invention can perform real-time analysis on the data collected by the hydropower station monitoring system, automatically classify and sort fault information according to the rules of the knowledge graph, ensure that urgent and important fault information is detected and can be processed with priority.

[0018] Build a comprehensive knowledge graph for hydropower fault diagnosis and emergency response, covering various possible fault types, cause analysis, response processes, and historical cases. This knowledge graph will serve as the system's core database, providing decision support for on-duty personnel.

[0019] Based on real-time monitoring data and knowledge graph content, it provides on-duty personnel with fault diagnosis, cause analysis, and emergency response recommendations. This real-time data monitoring and alarm platform is suitable for on-site on-duty operations. It integrates human-machine interface, data acquisition, preprocessing, feature extraction, and recognition functions, providing accurate data support for intelligent alarm systems and decision support systems.

[0020] Emergency response processes and plans, including accident reporting, resource allocation, accident handling and post-event evaluation, ensure that the hydropower station can handle emergencies quickly and orderly in the event of an accident. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 An overall flow chart of a knowledge graph-based method for handling emergency situations at a hydropower station is provided as an embodiment of the present invention.

[0023] Figure 2 A system solution module diagram of a hydropower station duty emergency response system based on a knowledge graph provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0025] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a knowledge graph-based on-duty emergency handling method for a hydropower station, comprising: collecting operating parameter data and historical fault information of the hydropower station and performing digital processing; constructing a knowledge graph containing fault types, cause analysis, and emergency response measures based on natural language processing and artificial intelligence training technology; establishing a fault diagnosis model algorithm based on the knowledge graph to identify and locate faults in the hydropower station operating data; classifying and prioritizing the faults based on the identified fault results, and matching the corresponding processing procedures; activating the emergency plan based on the fault classification information, executing control instructions to complete the emergency handling operations, and recording them.

[0026] S1. Collect the operating parameter data and historical fault information of the hydropower station and perform digital processing.

[0027] Operating parameters such as temperature, pressure and flow are collected through sensors installed at key equipment locations in the hydropower station.

[0028] The operating parameters are transmitted to the edge computing device via a data transmission network built through industrial Ethernet and optical fiber.

[0029] The edge computing device performs data preprocessing and feature extraction on the operating parameter data, and sends the processing results to the server.

[0030] S2. Based on natural language processing and artificial intelligence training technology, a knowledge graph is constructed that includes fault types, cause analysis, and emergency response measures.

[0031] Perform text analysis on operating parameter data and historical fault information, extract entity and relationship information to form structured data.

[0032] Learn structured data based on pre-trained artificial intelligence models to explore potential correlations between faults.

[0033] Deploy a graph database system in the server and build a knowledge graph based on the learning results.

[0034] S3. Establish a fault diagnosis model algorithm based on knowledge graph to identify and locate faults in hydropower station operation data.

[0035] Structured operating parameter data and knowledge graph content are used as training input.

[0036] A deep learning framework is used in the server to build and train a fault diagnosis model to identify and locate fault types.

[0037] S4. Classify and prioritize the faults based on the identified fault results, and match them with corresponding processing procedures.

[0038] The fault type output by the fault diagnosis model is used as input to classify the fault level based on the set rules.

[0039] Prioritize the fault classification results based on the impact scope and severity indicators.

[0040] S5. Based on the fault classification information, start the emergency plan, execute the control instructions to complete the emergency handling operations, and record them.

[0041] The server calls the matching emergency handling process in the emergency response plan library based on the fault type and priority.

[0042] Execute the automation control scripts associated with the emergency response process to control the automation equipment to perform emergency operations.

[0043] Send SMS via the On Call system to notify the on-call personnel for on-site response.

[0044] The fault identification results, fault classification information, emergency response procedures executed, and operating parameter data are recorded throughout the entire process.

[0045] The entire process record is written into the server as a new knowledge sample, which serves as training data for subsequent knowledge graph construction and fault diagnosis model optimization.

[0046] Specifically, knowledge graph construction and application include hardware, software and data, usage methods and logical diagrams.

[0047] The hardware uses high-performance servers (with multi-core CPUs, large-capacity memory and high-speed storage, such as Dell PowerEdge R740 servers, which are used to run AI large model training, knowledge graph construction and storage-related tasks. The powerful computing power can accelerate model training and data processing).

[0048] Software and data, text data compiled from historical experience, advanced algorithms (such as text extraction and classification algorithms in natural language processing, Python-based NLTK, SpaCy and other libraries), AI large model learning technology (such as BERT, a pre-trained model based on the Transformer architecture), Internet and accident handling related literature, and knowledge graph construction tools (such as the Neo4j graph database).

[0049] The usage method is to convert the experience of operators and experts into digital text and store it on the server; use the text extraction and classification algorithm based on the Python library to extract key information from the Internet and accident handling related literature; use the server's computing resources to input the extracted information into the AI ​​large model based on the Transformer architecture for learning and training to explore potential relationships; use the Neo4j graph database to build a knowledge graph on the server to store and manage structured information such as equipment parameters, fault cases, operation and maintenance experience, etc.

[0050] Logic diagram:

[0051] st=>start: start.

[0052] collect=>inputoutput: Collect experience and literature and store them on high-performance servers.

[0053] extract=>operation: Use NLTK and SpaCy libraries to extract classified text.

[0054] train=>operation: server-based training using the BERT model.

[0055] build=>operation: Use Neo4j to build a knowledge graph on the server.

[0056] e=>end:end.

[0057] st->collect->extract->train->build->e.

[0058] Fault diagnosis model algorithm:

[0059] The hardware uses GPU accelerator cards (such as NVIDIA Tesla V100, integrated in the server to accelerate the machine learning model training and inference process, significantly improving computing efficiency) and storage devices (used to store operating experience data and trained models, such as enterprise-level solid-state drives).

[0060] Software and data, building a good knowledge graph, operating experience data, intelligent retrieval technology (such as inverted index, semantic retrieval technology, which can be implemented based on Lucene, etc.), and machine learning algorithm framework (such as TensorFlow, PyTorch).

[0061] The method involves organizing operational experience data into the format required by the machine learning framework and storing it in a storage device. Using intelligent retrieval technology based on Lucene, relevant information can be quickly located within the server's knowledge graph. Using a GPU accelerator, based on the TensorFlow or PyTorch machine learning algorithm framework, the knowledge graph and operational experience data are combined to train an intelligent fault diagnosis model on the server. When a fault occurs, the fault-related data is fed into the trained model on the server, which then outputs a diagnostic result.

[0062] Logic diagram:

[0063] st=>start: start.

[0064] prepare_data=>inputoutput: organize the operating experience data and store it in the storage device.

[0065] retrieve=>operation: Use Lucene to retrieve the knowledge graph.

[0066] train_model=>operation: Use GPU to train the model using TF or PT framework.

[0067] diagnose=>operation: input fault data, server model diagnosis.

[0068] e=>end:end.

[0069] st->prepare_data->retrieve->train_model->diagnose->e.

[0070] For real-time monitoring and early warning, the hardware uses sensors (such as temperature sensors, pressure sensors, flow sensors, etc., installed in key parts of hydropower station equipment to collect equipment operating parameters in real time), data transmission networks (industrial Ethernet switches, optical fibers, etc., to transmit sensor data to the data processing center at high speed and stability), edge computing devices (such as Advantech's WISE-5000 series, which perform preliminary data processing and analysis at the source of the data to reduce the computing pressure on the core server), servers (used to run real-time data analysis and processing programs and fault diagnosis model algorithms), and SMS gateway devices (used to connect to SMS operators and send early warning SMS messages).

[0071] Software and data, real-time data analysis and processing technology (such as data preprocessing, eigenvalue extraction, pattern recognition technology, based on MATLAB, Python, etc.), fault diagnosis model algorithms, early warning notification tools (such as SMS sending programs developed based on SMS gateway device interfaces).

[0072] Instructions for use: Various sensors collect key parameters of the hydropower station in real time, and transmit the data to the edge computing device through a data transmission network composed of industrial Ethernet switches and optical fibers; the edge computing device uses real-time data analysis and processing technology based on MATLAB or Python to perform preliminary preprocessing, feature value extraction and other operations on the data, and then transmits the processed data to the server; the server uses the fault diagnosis model algorithm to further analyze the data to determine whether there is a fault risk; if there is a risk, an early warning SMS is sent through the SMS sending program developed based on the SMS gateway device interface.

[0073] Logic diagram:

[0074] st=>start: start.

[0075] collect_data=>inputoutput: sensor collects data.

[0076] transmit=>operation: Transmitted to edge devices via Ethernet or optical fiber.

[0077] preprocess=>operation: Edge devices use MATLAB / Python for preprocessing.

[0078] extract_feature=>operation: extract feature values.

[0079] recognize_pattern=>operation: pattern recognition.

[0080] diagnose_risk=>operation: Server intelligent algorithm diagnoses risk.

[0081] send_warning=>operation: Send an early warning via the SMS gateway.

[0082] e=>end:end.

[0083] st->collect_data->transmit->preprocess->extract_feature->recognize_pattern->.

[0084] diagnose_risk.

[0085] diagnose_risk(yes)->send_warning->e.

[0086] diagnose_risk(no)->e.

[0087] For emergency response plans, the hardware uses servers (running intelligent algorithms, automated processing scripts, and decision support knowledge bases) and automated execution equipment (such as programmable logic controllers (PLCs), which connect to hydropower station equipment to perform automated operations).

[0088] Software and data, intelligent algorithms (used for fault classification and prioritization, based on heuristic algorithms, machine learning classification algorithms, etc.), automated processing scripts (such as scripts written in Python for controlling PLCs), decision support knowledge bases, and expert system tools (optional, used to integrate expert knowledge, such as the Drools rule engine).

[0089] Usage method: Use the server to run intelligent algorithms based on heuristic or machine learning classification algorithms to classify and prioritize faults; based on the fault type and priority, the server triggers automated processing scripts written in Python to control PLC and other automated execution devices to perform corresponding operations on hydropower station equipment; extract processing suggestions and solutions from the decision support knowledge base on the server, integrate expert knowledge through expert system tools such as Drools rule engine, and provide decision support for operation and maintenance personnel.

[0090] Logic diagram:

[0091] st=>start: start.

[0092] receive_fault=>inputoutput: The server receives fault information.

[0093] classify_priority=>operation: classify and sort using heuristic / machine learning algorithms.

[0094] trigger_process=>operation: triggers the Python script to control the PLC.

[0095] retrieve_solution=>operation: retrieve the solution from the knowledge base.

[0096] provide_support=>operation: Provide decision support using Drools.

[0097] e=>end:end.

[0098] st->receive_fault->classify_priority->trigger_process.

[0099] classify_priority->retrieve_solution->provide_support->e.

[0100] trigger_process->e.

[0101] To execute control instructions and complete emergency handling operations, the hardware uses a server (running the intelligent operation and maintenance system, emergency response plan library, and fault diagnosis model algorithm) and on-call system hardware equipment (server or dedicated communication equipment for sending SMS notifications).

[0102] Software and data, intelligent operation and maintenance system, emergency response plan library, on-call system interface, knowledge graph, and fault diagnosis model algorithm.

[0103] Instructions for use: The server uses a fault diagnosis model algorithm combined with a knowledge graph to quickly locate faults; matches the corresponding emergency response plan from the server's emergency response plan library based on the fault type and severity; uses the On Call system interface and On Call system hardware to send text messages to notify relevant personnel; and guides on-site personnel to handle emergencies according to the emergency plan.

[0104] Logic diagram:

[0105] st=>start: start.

[0106] diagnose_fault=>operation: The server uses algorithms combined with graphs to diagnose faults.

[0107] match_plan=>operation: Matches the emergency response plan library plan.

[0108] send_notify=>operation: Send notification via the On call system interface.

[0109] guide_response=>operation: Guide emergency response according to the plan.

[0110] e=>end:end.

[0111] st->diagnose_fault->match_plan->send_notify->guide_response->e.

[0112] Embodiment 2 is the second embodiment of the present invention, which differs from the first two embodiments in that:

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0114] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0115] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0116] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0117] Example 3, reference Figure 2 , which is the third embodiment of the present invention, provides a hydropower station duty emergency processing system based on knowledge graph, including a data acquisition module, a knowledge graph construction module, a fault diagnosis module, a fault processing module and an emergency plan execution module.

[0118] The data acquisition module is used to collect the operating parameter data and historical fault information of the hydropower station and perform digital processing.

[0119] The knowledge graph construction module is used to build a knowledge graph that includes fault types, cause analysis and emergency response measures based on natural language processing and artificial intelligence training technology.

[0120] The fault diagnosis module is used to establish a fault diagnosis model algorithm based on knowledge graph to identify and locate faults in hydropower station operation data.

[0121] The fault handling module is used to classify and prioritize faults based on the identified fault results and match the corresponding processing flow.

[0122] The emergency plan execution module is used to start the emergency plan according to the fault classification information, execute the control instructions to complete the emergency handling operations, and record them.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A knowledge graph-based method for handling emergency situations at a hydropower station, characterized by: include, Collect the operating parameter data and historical fault information of the hydropower station and perform digital processing; Based on natural language processing and artificial intelligence training technology, a knowledge graph is constructed that includes fault types, cause analysis, and emergency response measures; Establish a fault diagnosis model algorithm based on knowledge graph to identify and locate faults in hydropower station operation data; Based on the identified fault results, classify and prioritize the faults and match them with the corresponding processing procedures; Based on the fault classification information, the emergency plan is activated, and the control instructions are executed to complete the emergency handling operations and record them.

2. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 1, characterized in that: The construction of the knowledge graph including fault types, cause analysis and emergency response measures includes: Perform text analysis on operating parameter data and historical fault information, extract entity and relationship information to form structured data; Use pre-trained AI models to learn from structured data and discover potential correlations between faults. Deploy a graph database system in the server and build a knowledge graph based on the learning results.

3. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 2, characterized in that: The fault diagnosis model algorithm based on the knowledge graph is established, including: Use structured operating parameter data and knowledge graph content as training input; A deep learning framework is used in the server to build and train a fault diagnosis model to identify and locate fault types.

4. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 3, characterized in that: The operation parameter data and historical fault information of the hydropower station are collected and digitally processed, including: Temperature, pressure and flow operating parameters are collected through sensors installed at key equipment locations in the hydropower station; The operating parameters are transmitted to the edge computing device via a data transmission network built through industrial Ethernet and optical fiber; The edge computing device performs data preprocessing and feature extraction on the operating parameter data, and sends the processing results to the server.

5. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 4, characterized in that: The fault classification and priority sorting include: The fault type output by the fault diagnosis model is used as input to classify the fault level based on the set rules; Prioritize the fault classification results based on the impact scope and severity indicators.

6. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 4, characterized in that: The initiation of the emergency plan includes the server calling a matching emergency handling process in the emergency response plan library according to the fault type and priority; Execute the automation control scripts associated with the emergency response process to control the automation equipment to perform emergency operations; Send SMS via the On Call system to notify the on-call personnel for on-site response.

7. The knowledge graph-based method for handling emergency situations at a hydropower station as claimed in claim 4, characterized in that: The recording includes recording the entire process of fault identification results, fault classification information, executed emergency response procedures, and operating parameter data; The entire process record is written into the server as a new knowledge sample, which serves as training data for subsequent knowledge graph construction and fault diagnosis model optimization.

8. A hydropower station duty emergency handling system based on knowledge graph, applying a hydropower station duty emergency handling method based on knowledge graph according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, knowledge graph construction module, fault diagnosis module, fault handling module and emergency plan execution module; The data acquisition module is used to collect the operating parameter data and historical fault information of the hydropower station and perform digital processing; The knowledge graph construction module is used to construct a knowledge graph including fault types, cause analysis and emergency response measures based on natural language processing and artificial intelligence training technology; The fault diagnosis module is used to establish a fault diagnosis model algorithm based on the knowledge graph to identify and locate faults in the hydropower station operation data; The fault processing module is used to classify and prioritize faults according to the identified fault results and match them with corresponding processing procedures; The emergency plan execution module is used to start the emergency plan according to the fault classification information, execute the control instructions to complete the emergency processing operation, and record it.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a hydropower station on-duty emergency handling method based on a knowledge graph as described in any one of claims 1 to 7 are implemented.

10. A 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 a knowledge graph-based hydropower station on-duty emergency handling method according to any one of claims 1 to 7 are implemented.

Images