Model analysis method and device of fault diagnosis model, equipment and storage medium

Abstract

The invention discloses a model analysis method and device for a fault diagnosis model, equipment and a storage medium, and the method comprises the steps: obtaining the fault diagnosis model, carrying out the analysis of a model structure of the fault diagnosis model, and generating a model analysis result of the fault diagnosis model; on the basis of the model analysis result, according to the depth of the nodes, feature tags and feature threshold conditions of branch nodes in the decision path corresponding to each fault type are stored in sequence, and a feature tag queue and a feature threshold condition queue are generated; and traversing a feature tag queue and a feature threshold condition queue corresponding to the target fault type based on a preset mapping relationship between standard business terms and business feature parameters, adding standard business term descriptions for feature tags and feature threshold conditions, and generating a target fault analysis description of the target fault type. Through the technical scheme, the interpretability of the model diagnosis result is improved.

Description

Technical Field

[0001] This invention relates to the fields of computer technology and nuclear power operation, and in particular to a model analysis method, apparatus, equipment and storage medium for fault diagnosis models. Background Technology

[0002] Modern pressurized water reactor nuclear power plants involve a great deal of complex work in operational decision-making, and it is often difficult to make judgments on different problems that are similar to certain initial phenomena that occur during the nuclear power plant's operation. With the continuous development of artificial intelligence technology, decision tree model algorithms, which are very similar to human judgment methods, are being increasingly utilized.

[0003] On the one hand, the underlying logic of decision trees is quite similar to the way humans judge such problems. It can not only achieve good accuracy, but also has better interpretability, making it particularly suitable for the nuclear power industry, which has extremely high requirements for safety and mechanism research.

[0004] On the other hand, because the nuclear power industry has extremely high safety requirements, nuclear power workers tend to focus on theoretical mechanism research and often distrust artificial intelligence diagnostic results that cannot explain the reasons. Therefore, it is necessary to ensure that the artificial intelligence diagnostic results have good interpretability. Summary of the Invention

[0005] This invention provides a model analysis method, apparatus, device, and storage medium for fault diagnosis models, in order to improve the persuasiveness and reliability of fault diagnosis results from fault diagnosis models.

[0006] According to one aspect of the present invention, a model analysis method for a fault diagnosis model is provided, the method comprising:

[0007] A fault diagnosis model is obtained, and the model structure of the fault diagnosis model is parsed to generate the model parsing result of the fault diagnosis model; wherein, the model parsing result includes the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path.

[0008] Based on the model analysis results, according to the depth of the nodes, the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type are stored in order to generate a feature label queue and a feature threshold condition queue.

[0009] Based on the preset mapping relationship between standard business terms and business feature parameters, the feature label queue and feature threshold condition queue corresponding to the target fault type are traversed, standard business term descriptions are added to the feature labels and feature threshold conditions, and a target fault parsing description of the target fault type is generated.

[0010] According to another aspect of the present invention, a model parsing apparatus for a fault diagnosis model is provided, the apparatus comprising:

[0011] The model parsing module is used to obtain the fault diagnosis model, parse the model structure of the fault diagnosis model, and generate the model parsing result of the fault diagnosis model; wherein, the model parsing result includes the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path.

[0012] The queue generation module is used to store the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type in order according to the depth of the nodes, based on the model parsing results, and generate a feature label queue and a feature threshold condition queue.

[0013] The model interpretation module is used to traverse the feature label queue and feature threshold condition queue corresponding to the target fault type based on the preset mapping relationship between standard business terms and business feature parameters, add standard business term descriptions to the feature labels and feature threshold conditions, and generate a target fault parsing description of the target fault type.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor;

[0016] and a memory communicatively connected to the at least one processor;

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the model parsing method of the fault diagnosis model according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the model parsing method of the fault diagnosis model according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the model parsing method of the fault diagnosis model according to any embodiment of the present invention.

[0020] The technical solution of this invention improves the interpretability of the model diagnosis results and the credibility of the model results for nuclear power engineers by parsing the model structure of the fault diagnosis model and converting the model parsing results into text parsing descriptions carrying standard business data.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a model parsing method for a fault diagnosis model provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of a model parsing method for a fault diagnosis model according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a model parsing device for a fault diagnosis model according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the model analysis method of the fault diagnosis model in the embodiments of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart illustrating a model parsing method for a fault diagnosis model, provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of parsing a trained fault diagnosis model to generate fault diagnosis logic. This method can be executed by a model parsing device for the fault diagnosis model, which can be implemented in hardware and / or software and can be configured in various general-purpose computing devices. For example... Figure 1 As shown, the method includes:

[0031] S110. Obtain the fault diagnosis model, parse the model structure of the fault diagnosis model, and generate the model parsing result of the fault diagnosis model.

[0032] The fault diagnosis model can be used to monitor the operating status of nuclear power equipment and perform fault diagnosis based on the real-time sensor data of the nuclear power equipment. It should be noted that the fault diagnosis model can have a tree-like structure.

[0033] The model analysis results can include the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path.

[0034] In this embodiment of the invention, different fault diagnosis models can be trained for different nuclear power equipment to accurately identify the fault types that occur during the operation of each nuclear power equipment.

[0035] Optionally, the training process of the fault diagnosis model includes: acquiring historical sensor data collected by sensors when a fault occurs in the target nuclear power equipment, and using the historical sensor data as the training set for training the fault diagnosis model; using the fault type that occurred in the target nuclear power equipment as the data label for the historical sensor data; and using the decision tree method to train the fault diagnosis model based on the training set to construct the fault diagnosis model.

[0036] The target nuclear power equipment can refer to the nuclear power equipment that needs to undergo fault diagnosis.

[0037] Sensor data may include temperature sensor data, pressure sensor data, and flow sensor data, etc. Those skilled in the art can adapt the data type of the sensor data to the specific equipment type of the target nuclear power plant.

[0038] Optionally, when training a fault diagnosis model using the decision tree method and performing feature classification, the Gini index can be used to select features to improve the training efficiency of the model.

[0039] By constructing a fault diagnosis model to diagnose faults in nuclear power equipment, the efficiency of fault diagnosis and fault handling for nuclear power equipment has been improved.

[0040] Optionally, before training the fault diagnosis model, the process includes: preprocessing the collected historical sensor data; data preprocessing operations may include data deduplication and data cleaning to remove useless data, missing values, and outliers from the collected historical sensor data; and normalizing the preprocessed historical sensor data. These processes aim to improve the data quality of the sample data.

[0041] Optionally, in this embodiment of the invention, a depth-first search algorithm or a breadth-first search algorithm can be used to parse the model structure of the fault diagnosis model. For example, the root node of the fault diagnosis model is taken as the current traversal node and added to the traversal path sequence; it is determined whether the current traversal node is a leaf node. If not, the child nodes of the current traversal node are taken as the current traversal nodes and traversed, and the current traversal node is added to the traversal path sequence; if yes, it indicates that the node path from the current traversal node to the root node has been traversed, and the remaining child nodes of the parent node of the current traversal node are traversed.

[0042] It should be noted that each leaf node corresponds to a traversal path sequence.

[0043] The model structure of the fault diagnosis model is analyzed by using a graph traversal algorithm, which improves the efficiency of model structure analysis.

[0044] S120. Based on the model analysis results, according to the depth of the nodes, the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type are stored in sequence to generate a feature label queue and a feature threshold condition queue.

[0045] Here, the decision path can refer to the path traversal sequence from the leaf node to the root node, the feature label of the branch node can refer to the classification features of the intermediate nodes in the path traversal sequence, and the feature threshold condition can refer to the classification condition of the intermediate node for the feature label. For example, the feature label can refer to temperature, humidity, and pressure, etc. The feature threshold condition can be the numerical relationship under the feature label dimension.

[0046] Specifically, after parsing the model structure of the fault diagnosis model, the parsing results can be stored in the form of readable data, and the model structure of the fault diagnosis model can be represented in the form of readable data.

[0047] S130. Based on the preset mapping relationship between standard business terms and business feature parameters, traverse the feature label queue and feature threshold condition queue corresponding to the target fault type, add standard business term descriptions to the feature labels and feature threshold conditions, and generate a target fault parsing description of the target fault type.

[0048] The target fault type can refer to the fault type corresponding to a leaf node. It should be noted that there is a one-to-one correspondence between leaf nodes and target fault types; the number of leaf nodes equals the number of target fault types.

[0049] The target fault description can be a textual diagnostic logic description of the target fault type of nuclear power equipment.

[0050] Standard business terminology can refer to the technical terms used in nuclear power business scenarios. Optionally, the mapping relationship between standard business terminology and business characteristic parameters can be adapted to suit the needs of those skilled in the art.

[0051] The technical solution of this invention improves the interpretability of the model diagnosis results and the credibility of the model results for nuclear power engineers by parsing the model structure of the fault diagnosis model and converting the model parsing results into text parsing descriptions carrying standard business data.

[0052] Example 2

[0053] Figure 2This is a flowchart of a model parsing method for a fault diagnosis model provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiment, providing specific steps for traversing the feature label queue and feature threshold condition queue corresponding to the target fault type based on the preset mapping relationship between standard business terms and business feature parameters, adding standard business terminology descriptions to the feature labels and feature threshold conditions, and generating a target fault parsing description for the target fault type. It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments, which will not be repeated here. Figure 2 As shown, the method includes:

[0054] S210. Obtain the fault diagnosis model, parse the model structure of the fault diagnosis model, and generate the model parsing result of the fault diagnosis model.

[0055] S220. Based on the model analysis results, according to the depth of the nodes, the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type are stored in sequence to generate a feature label queue and a feature threshold condition queue.

[0056] S230. During the process of traversing the feature label queue and feature threshold condition queue corresponding to the target fault type, determine the current feature label and current feature threshold condition corresponding to the current traversed object.

[0057] S240. Based on the preset mapping relationship between standard business terms and business feature parameters, determine the standard business term corresponding to the current feature label, and limit the numerical range of the standard business term according to the current feature threshold condition.

[0058] S250. Output the standard business terms after limiting the numerical range and the target fault type in a preset data parsing format to generate the target fault parsing description corresponding to the target fault type.

[0059] The target fault analysis description can include the complete decision path and decision rules for the target fault type, as well as the fault detection purpose determined based on the target fault type and decision rules. The decision path and decision rules for the target fault type can be used to characterize the mechanism of failure in nuclear power equipment.

[0060] Optionally, the matching between feature tags and standard business terms can be performed using semantic matching or keyword matching.

[0061] Optionally, in this embodiment of the invention, the preset data parsing format can be adapted to the needs of those skilled in the art. For example, it can be as follows:

[0062] Decision rule: Real-time hot section temperature sensor data <= hot section temperature 1, and real-time hot section flow sensor data <= hot section flow 1;

[0063] Target fault type: Hot-section sensor fault;

[0064] Fault diagnosis objective: To check the hot section sensor.

[0065] Specifically, the decision rule field in the target fault parsing description integrates the classification features and feature threshold conditions represented by each intermediate node in the traversal path sequence of the leaf nodes corresponding to the target fault type.

[0066] Optionally, in this embodiment of the invention, after generating the model analysis results of the fault diagnosis model, the method further includes: visualizing the fault diagnosis model based on the model analysis results. The visualized model structure enables nuclear power engineers to quickly identify the causes of faults and summarize the mechanistic reasons, thus making the data-driven artificial intelligence model interpretable.

[0067] The embodiments of the present invention traverse the feature label queue and feature threshold condition queue corresponding to the target fault type to determine the standard business terms corresponding to the feature labels, and generate a probability-based decision rule group description based on the standard business data and feature threshold conditions, so that nuclear power engineers can clearly and intuitively understand the diagnostic process and mechanism of the target fault type.

[0068] Example 3

[0069] Figure 3 This is a schematic diagram of the structure of a model parsing device for a fault diagnosis model provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0070] The model parsing module 310 is used to acquire the fault diagnosis model and parse the model structure of the fault diagnosis model to generate the model parsing result of the fault diagnosis model; wherein, the model parsing result includes the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path.

[0071] The queue generation module 320 is used to store the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type in order according to the depth of the nodes, based on the model parsing results, and generate a feature label queue and a feature threshold condition queue.

[0072] The model interpretation module 330 is used to traverse the feature label queue and feature threshold condition queue corresponding to the target fault type based on the preset mapping relationship between standard business terms and business feature parameters, add standard business term descriptions to the feature labels and feature threshold conditions, and generate a target fault parsing description of the target fault type.

[0073] The technical solution of this invention improves the interpretability of the model diagnosis results and the credibility of the model results for nuclear power engineers by parsing the model structure of the fault diagnosis model and converting the model parsing results into text parsing descriptions carrying standard business data.

[0074] Optionally, the model interpretation module 330 includes:

[0075] The queue traversal unit is used to determine the current feature label and the current feature threshold condition corresponding to the current traversed object during the traversal of the feature label queue and feature threshold condition queue corresponding to the target fault type.

[0076] The standard term matching unit is used to determine the standard business term corresponding to the current feature label based on the preset mapping relationship between standard business terms and business feature parameters, and to limit the numerical range of the standard business term according to the current feature threshold condition.

[0077] The fault description unit is used to output the standard business terms after limiting the numerical range and the target fault type in a preset data parsing format to generate the target fault parsing description corresponding to the target fault type.

[0078] Optionally, the target fault analysis description includes a complete decision path and decision rules for the target fault type, as well as the fault detection objective determined based on the target fault type and decision rules.

[0079] Optionally, the model parsing module 310 can be specifically used for:

[0080] The root node of the fault diagnosis model is taken as the current traversal node, and the current traversal node is added to the traversal path sequence.

[0081] Determine whether the currently traversed node is a leaf node. If not, traverse the child nodes of the currently traversed node as the current traversed node and add the current traversed node to the traversal path sequence. If yes, it indicates that the node path from the current traversed node to the root node has been traversed. Treat the current traversed node as the last node in the traversal path sequence and traverse the remaining child nodes of the parent node of the current traversed node.

[0082] Optionally, the training process of the fault diagnosis model includes:

[0083] The system acquires historical sensor data collected by sensors when a fault occurs in the target nuclear power equipment, and uses the historical sensor data as a training set for training the fault diagnosis model; the sensor data includes temperature sensor data, pressure sensor data, and flow sensor data.

[0084] The type of fault that occurred in the target nuclear power equipment is used as the data label for this historical sensor data;

[0085] Based on the training set, the fault diagnosis model is trained using the decision tree method to construct the fault diagnosis model.

[0086] Optionally, the device may also include:

[0087] The model visualization module is used to visualize the fault diagnosis model based on the model analysis results after the model analysis results of the fault diagnosis model are generated.

[0088] The model parsing device for the fault diagnosis model provided in this embodiment of the invention can execute the model parsing method for the fault diagnosis model provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0089] Example 4

[0090] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0091] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0092] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0093] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the model parsing method for a fault diagnosis model.

[0094] In some embodiments, the model parsing method for the fault diagnosis model can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the model parsing method for the fault diagnosis model described above can be performed. Alternatively, in other embodiments, processor 411 can be configured to perform the model parsing method for the fault diagnosis model by any other suitable means (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0099] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0100] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0101] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0102] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A model analysis method for a fault diagnosis model, characterized in that, include: A fault diagnosis model is obtained, and the model structure of the fault diagnosis model is parsed to generate the model parsing result of the fault diagnosis model; wherein, the model parsing result includes the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path. Based on the model analysis results, according to the depth of the nodes, the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type are stored in order to generate a feature label queue and a feature threshold condition queue. Based on the preset mapping relationship between standard business terms and business feature parameters, the feature label queue and feature threshold condition queue corresponding to the target fault type are traversed, standard business term descriptions are added to the feature labels and feature threshold conditions, and a target fault parsing description of the target fault type is generated.

2. The method according to claim 1, characterized in that, Based on the preset mapping relationship between standard business terms and business feature parameters, the feature label queue and feature threshold condition queue corresponding to the target fault type are traversed, standard business terminology descriptions are added to the feature labels and feature threshold conditions, and a target fault parsing description of the target fault type is generated, including: During the process of traversing the feature label queue and feature threshold condition queue corresponding to the target fault type, the current feature label and current feature threshold condition corresponding to the current traversed object are determined. Based on the preset mapping relationship between standard business terms and business feature parameters, determine the standard business term corresponding to the current feature label, and limit the numerical range of the standard business term according to the current feature threshold condition; The standard business terms, after being limited to a numerical range, and the target fault type are output in a preset data parsing format to generate a target fault parsing description corresponding to the target fault type.

3. The method according to claim 2, characterized in that, The target fault analysis description includes the complete decision path and decision rules for the target fault type, as well as the fault detection objective determined based on the target fault type and decision rules.

4. The method according to claim 1, characterized in that, The step of parsing the model structure of the fault diagnosis model includes: The root node of the fault diagnosis model is taken as the current traversal node, and the current traversal node is added to the traversal path sequence. Determine whether the currently traversed node is a leaf node. If not, traverse the child nodes of the currently traversed node as the current traversed node and add the current traversed node to the traversal path sequence. If yes, it indicates that the node path from the current traversed node to the root node has been traversed. Treat the current traversed node as the last node in the traversal path sequence and traverse the remaining child nodes of the parent node of the current traversed node.

5. The method according to claim 1, characterized in that, The training process of the fault diagnosis model includes: The system acquires historical sensor data collected by sensors when a fault occurs in the target nuclear power equipment, and uses the historical sensor data as a training set for training the fault diagnosis model; the sensor data includes temperature sensor data, pressure sensor data, and flow sensor data. The type of fault that occurred in the target nuclear power equipment is used as the data label for this historical sensor data; Based on the training set, the fault diagnosis model is trained using the decision tree method to construct the fault diagnosis model.

6. The method according to claim 1, characterized in that, After generating the model analysis results of the fault diagnosis model, the following is also included: The fault diagnosis model is visualized based on the model analysis results.

7. A model parsing device for a fault diagnosis model, characterized in that, include: The model parsing module is used to obtain the fault diagnosis model, parse the model structure of the fault diagnosis model, and generate the model parsing result of the fault diagnosis model; wherein, the model parsing result includes the decision path of the fault type, the feature labels and feature threshold conditions of the branch nodes in the decision path, and the fault type of the leaf nodes in the decision path. The queue generation module is used to store the feature labels and feature threshold conditions of the branch nodes in the decision path corresponding to each fault type in order according to the depth of the nodes, based on the model parsing results, and generate a feature label queue and a feature threshold condition queue. The model interpretation module is used to traverse the feature label queue and feature threshold condition queue corresponding to the target fault type based on the preset mapping relationship between standard business terms and business feature parameters, add standard business term descriptions to the feature labels and feature threshold conditions, and generate a target fault parsing description of the target fault type.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the model analysis method of the fault diagnosis model according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the model parsing method of the fault diagnosis model according to any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the model parsing method for the fault diagnosis model according to any one of claims 1-6.

Images