Intelligent diagnosis method and system for shutdown and reactor shutdown reasons of nuclear power unit, medium and equipment

Abstract

The invention relates to a nuclear power unit shutdown reason intelligent diagnosis method and system, a medium and equipment. The method comprises the following steps: acquiring real-time alarm information; performing semantic recognition, reasoning and positioning on the real-time alarm information by using an AI technology, and determining a matched fault tree node list; performing reason analysis and summarization according to the logic structure of the fault tree and the matched fault tree node list to obtain an initial fault reason; performing reason elimination on the initial fault reason in combination with the real-time measurement point information and a preset corresponding relation to obtain a target fault reason; and sorting the target fault reasons according to the quantitative analysis result of the fault tree, and outputting processing suggestions. According to the method, the AI technology is utilized to realize rapid and accurate positioning of the fault tree nodes, the troubleshooting efficiency is remarkably improved, meanwhile, fault reasons can be comprehensively and accurately troubleshot through fault tree logic analysis in combination with real-time point measurement information and historical experience feedback data, the troubleshooting accuracy is improved, and the risk of misjudgment and missed judgment is reduced.

Description

Technical Field

[0001] This invention relates to the technical field of nuclear power unit fault diagnosis, and more specifically, to an intelligent diagnostic method, system, medium, and equipment for the causes of nuclear power unit shutdowns and outages. Background Technology

[0002] Ensuring the safe and stable operation of nuclear power units is of paramount importance. When alarms or anomalies occur in the nuclear power unit or equipment, quickly and accurately locating the cause of the fault and taking effective measures are crucial to ensuring the safe operation of the nuclear power unit. Traditional troubleshooting methods typically rely on manual experience and analysis, which is inefficient and prone to misdiagnosis and omission. As the scale and complexity of nuclear power units continue to increase, traditional methods are no longer sufficient to meet practical needs.

[0003] Some existing fault diagnosis technologies focus on diagnosing faults in the equipment hardware itself, such as using sensors to acquire data for fault diagnosis; or they focus on the application of a single intelligent technology in a specific aspect, such as using image recognition technology to detect cracks in in-core components. These fault diagnosis technologies cannot accurately locate faults, and the troubleshooting process is time-consuming and inefficient. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide an intelligent diagnostic method, system, medium, and equipment for the causes of nuclear power unit shutdowns and outages, addressing the problems existing in the prior art.

[0005] The technical solution adopted by this invention to solve its technical problem is: to construct an intelligent diagnostic method for the causes of nuclear power unit shutdown, including the following steps:

[0006] Obtain real-time alarm information;

[0007] AI technology is used to perform semantic recognition, reasoning, and localization on the real-time alarm information to determine a list of matching fault tree nodes;

[0008] Based on the logical structure of the fault tree and the matching fault tree node list, cause analysis and summary are performed to obtain the initial fault cause;

[0009] By combining real-time measurement point information and preset correspondence, the initial fault cause is eliminated to obtain the target fault cause;

[0010] Based on the quantitative analysis results of the fault tree, the causes of the target fault are ranked, and processing suggestions are output.

[0011] In the intelligent diagnostic method for the causes of nuclear power unit shutdown and reactor stoppage described in this invention, the real-time alarm information includes: real-time alarm coding information or abnormal information;

[0012] The step of using AI technology to perform semantic recognition, reasoning, and localization on the real-time alarm information to determine the list of matching fault tree nodes includes:

[0013] By using AI technology combined with alarm-related information in the alarm card and basic nuclear power knowledge, the real-time alarm coding information or abnormal description information is identified and inferred to obtain key information;

[0014] The key information is compared with the fault tree node information to obtain the list of matching fault tree nodes.

[0015] In the intelligent diagnostic method for nuclear power unit shutdown causes described in this invention, the step of analyzing and summarizing the causes based on the logical structure of the fault tree and the matching fault tree node list to obtain the initial fault causes includes:

[0016] The located node is obtained based on the matched fault tree node list;

[0017] Based on the logical structure of the fault tree, the fault tree model is traversed downwards from the located node to obtain the initial fault cause.

[0018] In the intelligent diagnostic method for the causes of nuclear power unit shutdown and reactor stoppage described in this invention, the method further includes:

[0019] The process of analyzing and summarizing the causes of failures is visualized using a tree structure.

[0020] In the intelligent diagnostic method for the causes of nuclear power unit shutdown and reactor stoppage described in this invention, the preset correspondence includes: the correspondence between equipment code, equipment category, equipment type fault mode, fault symptom, characteristic parameter, and measurement point;

[0021] Based on the preset correspondence and real-time measurement point information, eliminate the fault causes in the initial fault causes that do not match the real-time measurement point information, and obtain the target fault cause.

[0022] In the intelligent diagnostic method for the causes of nuclear power unit shutdown and reactor stoppage described in this invention, the method further includes:

[0023] The troubleshooting process is visualized.

[0024] In the intelligent diagnostic method for nuclear power unit shutdown causes described in this invention, the step of ranking the target fault causes based on the quantitative analysis results of the fault tree and outputting processing suggestions includes:

[0025] Based on the quantitative analysis results of the fault tree, all target fault causes are sorted from high to low probability to obtain a fault cause ranking list.

[0026] The processing suggestions are generated and output based on historical experience feedback data and / or AI technology.

[0027] This invention also provides an intelligent diagnostic system for the causes of nuclear power unit shutdowns and outages, comprising:

[0028] The information acquisition module is used to acquire real-time alarm information;

[0029] The AI ​​semantic recognition and reasoning module is used to perform semantic recognition, reasoning and location on the real-time alarm information using AI technology, and to determine the list of matching fault tree nodes.

[0030] The fault tree analysis module is used to perform cause analysis and summary based on the logical structure of the fault tree and the matching fault tree node list to obtain the initial fault cause.

[0031] The cause elimination module is used to combine real-time measurement point information and preset correspondence to eliminate the cause of the initial fault and obtain the target fault cause;

[0032] The cause ranking and suggestion module is used to rank the causes of the target fault based on the quantitative analysis results of the fault tree and output processing suggestions.

[0033] The visualization and interaction module is used to visually display the troubleshooting process and results.

[0034] The present invention also provides a storage medium storing a computer program adapted for loading by a processor to execute the steps of the intelligent diagnostic method for the causes of nuclear power unit shutdown as described above.

[0035] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the intelligent diagnosis method for the causes of nuclear power unit shutdown as described above by calling the computer program stored in the memory.

[0036] The intelligent diagnostic method, system, medium, and equipment for nuclear power unit shutdown causes of this invention have the following beneficial effects: They include: acquiring real-time alarm information; using AI technology to perform semantic recognition, reasoning, and localization of the real-time alarm information to determine a matching fault tree node list; performing cause analysis and summarization based on the logical structure of the fault tree and the matching fault tree node list to obtain the initial fault cause; combining real-time measurement point information and preset correspondences to eliminate the initial fault cause and obtain the target fault cause; and ranking the target fault causes based on the quantitative analysis results of the fault tree and outputting processing suggestions. This invention utilizes AI technology to achieve rapid and accurate location of fault tree nodes, significantly improving fault troubleshooting efficiency. Simultaneously, through fault tree logical analysis combined with real-time measurement point information and historical experience feedback data, it can comprehensively and accurately investigate fault causes, improving the accuracy of fault troubleshooting and reducing the risk of misjudgment and omission. Attached Figure Description

[0037] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0038] Figure 1 This is a flowchart illustrating the intelligent diagnostic method for nuclear power unit shutdown and reactor stoppage causes provided in an embodiment of the present invention;

[0039] Figure 2 This is an example diagram of the alarm card provided in an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of the alarm and fault tree matching of the jacquard unit according to an embodiment of the present invention;

[0041] Figure 4 This is an example diagram of the preset correspondence provided in the embodiments of the present invention;

[0042] Figure 5 This is an example diagram of the failure mode-root cause provided in the embodiments of the present invention;

[0043] Figure 6 This is a logic block diagram of the intelligent diagnostic system for nuclear power unit shutdown and reactor stoppage provided in an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] This invention deeply integrates AI semantic recognition and reasoning capabilities into the nuclear power unit fault investigation process. Closely combined with the shutdown fault tree model, it can not only quickly locate fault tree nodes, but also achieve cause summarization, elimination and sorting through multi-source data fusion (including fault tree knowledge data, alarm card information, real-time measurement point information and experience feedback data).

[0046] This invention provides an intelligent diagnostic method for the causes of nuclear power unit shutdowns and outages. It is an intelligent troubleshooting method for nuclear power unit shutdowns and outages based on fault tree and multi-source data fusion. When an alarm or defect occurs in a nuclear power unit, this method can use AI technology to quickly locate a certain node in the fault tree, provide possible causes based on the fault tree structure, and combine real-time measurement point information and experience feedback to eliminate certain causes. Finally, it provides a ranking of all possible causes and handling opinions.

[0047] refer to Figure 1 , Figure 1 This invention illustrates a preferred embodiment of the intelligent diagnostic method for nuclear power unit shutdown causes provided by the present invention.

[0048] like Figure 1 As shown, the intelligent diagnostic method for the causes of nuclear power unit shutdown includes the following steps:

[0049] Step S101: Obtain real-time alarm information.

[0050] Optionally, in this embodiment of the invention, the real-time alarm information includes: real-time alarm coding information or abnormal information. The real-time alarm coding information includes an alarm number, such as 3APA140KA. The abnormal information includes a unit-level fault notification form. The real-time alarm information and abnormal information can be directly obtained by the system from the equipment management platform; that is, when an alarm or defect occurs in the nuclear power unit, the system directly obtains the real-time alarm information of the nuclear power unit from the equipment management platform.

[0051] Step S102: Use AI technology to perform semantic recognition, reasoning, and localization on real-time alarm information to determine the list of matching fault tree nodes.

[0052] Optionally, in this embodiment of the invention, using AI technology to perform semantic recognition, reasoning, and location of real-time alarm information to determine a matching fault tree node list includes: using AI technology in combination with alarm-related information in the alarm card and basic nuclear power knowledge to identify and reason about real-time alarm coding information or abnormal description information to obtain key information; comparing the key information with fault tree node information to obtain a matching fault tree node list.

[0053] Specifically, after obtaining real-time alarm information, AI technology is used to search the alarm card knowledge base to retrieve detailed alarm information corresponding to the alarm code (including but not limited to alarm number, alarm name, involved sensors, alarm threshold, alarm logic, brief alarm reason, and consequences after the alarm occurred). For an example of an alarm card, see [link to alarm card example]. Figure 2 Simultaneously, combining fundamental nuclear power knowledge (such as the functions, equipment configuration, and operational configuration of nuclear power systems), word segmentation and part-of-speech tagging are performed to extract key information such as alarm number, alarm name, alarm logic, involved sensors, alarm threshold, brief alarm reason, and consequences after the alarm occurs. Then, this key information is semantically or logically matched with the codes and descriptions of fault tree nodes. Specifically, the key information is compared with fault tree node information (where fault tree node information is a fault tree pattern for a specific device, including code and description; for example, code CRF001RR.ST, description of circulating water pump gearbox failure and shutdown). Through AI's semantic recognition and logical reasoning capabilities, a list of matching fault tree nodes is determined. Specifically, as shown below... Figure 3 As shown.

[0054] Step S103: Analyze and summarize the causes based on the logical structure of the fault tree and the list of matching fault tree nodes to obtain the initial causes of the fault.

[0055] Optionally, in this embodiment of the invention, the cause analysis and summary based on the logical structure of the fault tree and the matching fault tree node list to obtain the initial fault cause includes: obtaining the located node based on the matching fault tree node list; and traversing the fault tree model from the located node downwards according to the logical structure of the fault tree to obtain the initial fault cause.

[0056] Specifically, by parsing the logical relationships of the fault tree (such as AND gates, OR gates, etc.), the logical structure of the fault tree is obtained. Based on the logical structure of the fault tree, the fault tree model is traversed from the located node downwards to summarize the possible causes and combinations of different aspects, thereby obtaining the initial fault cause.

[0057] Furthermore, in this embodiment of the invention, during the process of fault cause analysis and summarization, a tree structure is used for visual display of the fault cause analysis and summarization process. By using a tree structure for visualization, the hierarchical relationship and logical connection between various possible causes can be clearly presented.

[0058] Step S104: Combine real-time measurement point information and preset correspondence to eliminate the cause of the initial fault and obtain the cause of the target fault.

[0059] In this embodiment of the invention, the initial fault cause is eliminated by combining real-time measurement point information and preset correspondence to obtain the target fault cause. This includes: eliminating fault causes in the initial fault cause that do not match the real-time measurement point information according to the preset correspondence and real-time measurement point information, obtaining the target fault cause, and visually displaying the fault cause elimination process.

[0060] Optionally, in this embodiment of the invention, the preset correspondence includes: the correspondence between equipment code, equipment category, equipment type fault mode, fault symptom, characteristic parameter, and measurement point. Figure 4 An example of this correspondence is given. This preset relationship can be pre-stored in the device management platform and can be directly read or called by the system. For example, such as... Figure 3 As shown, the CRF001RR gearbox belongs to the RRGA01 equipment category and has a failure shutdown fault mode. After the failure shutdown occurs, there are three corresponding fault symptoms. Taking the third fault symptom in the figure (gearbox auxiliary comprehensive monitoring) as an example, this symptom corresponds to two monitoring parameters. Each monitoring parameter corresponds to a corresponding online or offline measuring point, which can be obtained from the equipment management platform.

[0061] After determining all possible causes and combinations of faults in step S103, and combining this with the existing correspondence between equipment code, equipment category, equipment fault mode, fault symptom, characteristic parameter, and measurement point in the equipment management platform, causes inconsistent with real-time measurement point information are automatically eliminated (for example, the fault tree location shows that one of the possible causes of the current unit alarm is gearbox malfunction, but the corresponding measurement point for gearbox malfunction is within the normal range, so fault branches and combinations related to gearbox malfunction can be eliminated), and the cause elimination process is visualized. Simultaneously, this invention also provides an interactive operation interface to support operators in manually eliminating some causes. For example, information obtained offline by the operator.

[0062] Step S105: Sort the causes of the target faults according to the quantitative analysis results of the fault tree and output processing suggestions.

[0063] Optionally, in this embodiment of the invention, sorting the target fault causes according to the fault tree quantitative analysis results and outputting processing suggestions includes: sorting all target fault causes according to their probability from high to low based on the fault tree quantitative analysis results to obtain a fault cause sorting list; generating and outputting processing suggestions based on historical experience feedback data and / or AI technology.

[0064] Specifically, after eliminating some fault causes by comparing real-time measurement point information, the remaining fault causes and combinations (i.e., target fault causes) are ranked by probability, and a final handling suggestion is given. The ranking of the remaining fault causes and combinations can be based on the quantitative analysis results of the fault tree, sorting them from highest to lowest probability. The handling suggestions can be derived by retrieving historical experience feedback data from the experience feedback knowledge base and combining it with AI technology to recommend appropriate handling methods. For example, if the same or similar faults have occurred historically, the historical handling methods are directly recommended; if the same or similar faults have not occurred historically, the fault mode-fault mode root cause analysis data from the equipment management platform (such as...) is used. Figure 5 As shown in the figure, AI is used to recommend appropriate processing methods.

[0065] refer to Figure 6 This invention also provides an intelligent diagnostic system for the causes of nuclear power unit shutdowns and outages. For example... Figure 6 As shown, the intelligent diagnostic system for the causes of nuclear power unit shutdown includes:

[0066] The information acquisition module 601 is used to acquire real-time alarm information.

[0067] Specifically, when a nuclear power unit experiences a fault or abnormality, the information acquisition module 601 obtains real-time alarm or abnormal information from the equipment management platform. Simultaneously, the information acquisition module 601 also obtains data from the equipment management platform, including the correspondence between equipment code, equipment category, equipment fault mode, fault symptoms, characteristic parameters, and measurement points, as well as the equipment fault tree and the cause of the fault mode.

[0068] The AI ​​semantic recognition and reasoning module 602 is used to perform semantic recognition, reasoning and location of real-time alarm information using AI technology, and to determine the list of matching fault tree nodes.

[0069] Specifically, the AI ​​semantic recognition and reasoning module 602 uses AI technology to perform semantic recognition and reasoning on the acquired real-time alarm information, so as to achieve rapid matching and location with fault tree nodes.

[0070] The fault tree analysis module 603 is used to perform cause analysis and summary based on the logical structure of the fault tree and the matching fault tree node list to obtain the initial fault cause.

[0071] Specifically, the fault tree analysis module 603 can parse the logical relationships of the fault tree to obtain the logical structure of the fault tree, and realize the cause summary and traversal analysis starting from the location node, as well as qualitative and quantitative calculations.

[0072] The cause elimination module 604 is used to combine real-time measurement point information and preset correspondence to eliminate the cause of the initial fault and obtain the target fault cause.

[0073] Specifically, the cause elimination module 604 combines real-time measurement point information and preset correspondence to automatically and / or manually eliminate the cause of the fault and visually display the elimination process.

[0074] The cause ranking and suggestion module 605 is used to rank the causes of the target fault based on the quantitative analysis results of the fault tree and output handling suggestions.

[0075] Specifically, the cause ranking and suggestion module 605 ranks the remaining fault causes based on the quantitative analysis results of the fault tree, and provides handling suggestions by combining historical experience feedback data and fault mode-fault mode root cause relationships.

[0076] The visualization and interaction module 606 is used to visualize the troubleshooting process and results.

[0077] Specifically, the visualization and interaction module 606 can display the troubleshooting process and results in a visual manner on the equipment management platform, while providing an interactive operation interface to facilitate operator operation.

[0078] Specifically, the detailed operational procedures between the modules in the intelligent diagnostic system for nuclear power unit shutdown causes can be found in the aforementioned intelligent diagnostic method for nuclear power unit shutdown causes, and will not be repeated here.

[0079] This system utilizes AI technology to quickly and accurately locate fault tree nodes, significantly shortening troubleshooting time and improving efficiency. It can quickly respond to alarms or anomalies in nuclear power units. Through in-depth analysis of the logical relationships in the fault tree, combined with real-time measurement point information and historical experience feedback data, it comprehensively and accurately investigates the causes of faults, improving the accuracy of fault investigation and reducing the risk of misjudgment and omission. Through a visual interface and interactive operation, it facilitates intuitive understanding of the fault investigation process and results, enabling manual intervention and decision-making, and improving the efficiency and reliability of fault handling.

[0080] Furthermore, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the intelligent diagnostic method for nuclear power unit shutdown causes as described above. Specifically, according to embodiments of the present invention, the processes described above with reference to the flowchart can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, when the computer program is downloaded, installed, and executed by an electronic device, it performs the functions defined in the methods of the embodiments of the present invention. The electronic device in the present invention can be a terminal such as a laptop, desktop computer, tablet computer, or smartphone, or it can be a server.

[0081] Furthermore, one type of storage medium of the present invention stores a computer program thereon, which, when executed by a processor, implements the intelligent diagnostic method for nuclear power unit shutdown and reactor failure reasons described above. Specifically, it should be noted that the storage medium described above in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0082] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0083] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0084] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0085] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0086] The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They do not limit the scope of protection of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A nuclear power unit shutdown and shutdown reason intelligent diagnosis method, characterized in that, The method comprises the following steps: obtaining real-time alarm information; performing semantic recognition and reasoning and positioning on the real-time alarm information by using AI technology to determine a matched fault tree node list; performing cause analysis and summary according to the logical structure of the fault tree and the matched fault tree node list to obtain an initial fault cause; performing cause elimination on the initial fault cause in combination with real-time measuring point information and a preset corresponding relationship to obtain a target fault cause; performing sorting on the target fault cause according to a quantitative analysis result of the fault tree and outputting a processing suggestion.

2. The nuclear power unit shutdown and reactor trip cause intelligent diagnostic method according to claim 1, characterized in that, The real-time alarm information comprises real-time alarm coding information or abnormal information. The performing semantic recognition and reasoning and positioning on the real-time alarm information by using AI technology to determine a matched fault tree node list comprises: performing recognition and reasoning on the real-time alarm coding information or abnormal description information in combination with alarm-related information in an alarm card and nuclear power basic knowledge by using AI technology to obtain key information; comparing the key information with fault tree node information to obtain the matched fault tree node list.

3. The nuclear power unit shutdown and reactor trip cause intelligent diagnostic method according to claim 1, characterized in that, The performing cause analysis and summary according to the logical structure of the fault tree and the matched fault tree node list to obtain an initial fault cause comprises: obtaining a positioned node based on the matched fault tree node list; traversing the fault tree model from the positioned node downwards according to the logical structure of the fault tree to obtain the initial fault cause.

4. The nuclear power unit shutdown and reactor trip reason intelligent diagnostic method according to any one of claims 1-3, characterized in that, The method further comprises: adopting a tree structure to visually display the fault cause analysis and summary process.

5. The nuclear power plant unit shutdown and reactor trip cause intelligent diagnostic method of claim 1, wherein, The preset corresponding relationship comprises a corresponding relationship of equipment coding-equipment category-equipment category fault mode-fault symptom-feature parameter-measuring point. According to the preset corresponding relationship and real-time measuring point information, the fault cause that is inconsistent with the real-time measuring point information is excluded from the initial fault cause to obtain the target fault cause.

6. The nuclear power unit shutdown and reactor trip cause intelligent diagnostic method according to claim 1 or 5, characterized in that, The method further comprises: visually displaying the fault cause elimination process.

7. The nuclear power plant unit shutdown and reactor trip cause intelligent diagnostic method of claim 1, wherein, The performing sorting on the target fault cause according to a quantitative analysis result of the fault tree and outputting a processing suggestion comprises: performing sorting on all target fault causes according to probability from high to low according to the quantitative analysis result of the fault tree to obtain a fault cause sorting list; generating and outputting the processing suggestion according to historical experience feedback data and / or AI technology.

8. An intelligent diagnosis system for nuclear power unit shutdown and shutdown cause, characterized in that, The method comprises: an information acquisition module configured to obtain real-time alarm information; an AI semantic recognition and reasoning module configured to perform semantic recognition and reasoning and positioning on the real-time alarm information by using AI technology to determine a matched fault tree node list; a fault tree analysis module configured to perform cause analysis and summary according to the logical structure of the fault tree and the matched fault tree node list to obtain an initial fault cause; a cause elimination module configured to perform cause elimination on the initial fault cause in combination with real-time measuring point information and a preset corresponding relationship to obtain a target fault cause; a cause sorting and suggestion module configured to perform sorting on the target fault cause according to a quantitative analysis result of the fault tree and output a processing suggestion; a visualization and interaction module configured to visually display the fault elimination process and results.

9. A storage medium, characterized by The storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the intelligent diagnosis method for shutdown and shutdown reasons of a nuclear power unit according to any one of claims 1 to 7.

10. An electronic device, comprising: The device comprises a memory and a processor, the memory stores a computer program, and the processor executes the steps of the intelligent diagnosis method for shutdown and shutdown reasons of a nuclear power unit according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images