Nuclear power station equipment fault diagnosis method and system

Abstract

The invention relates to the technical field of fault diagnosis, and provides a nuclear power station equipment fault diagnosis method and system, which can reflect the state of each piece of equipment and the health condition of the whole system in real time by collecting equipment operation data in real time and dynamically constructing and updating an equipment relation graph by using physical connection and function dependency relationship among the equipment. Besides, probability calculation of equipment fault influence is introduced in the method, and the possible influence of the fault equipment on other parts of the system can be accurately analyzed based on the total score of the equipment and the dependency relationship between the equipment, so that quicker and more effective response is made; the problem that an existing method is difficult to accurately analyze the complex dependency relationship and the interaction influence between devices is solved.

Description

Technical Field

[0001] The present invention relates to the technical field related to fault diagnosis, and in particular to a method and system for diagnosing nuclear power plant equipment faults. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In the operation and maintenance of nuclear power plants, timely diagnosis and treatment of equipment failures are key factors in ensuring safety and efficiency. In recent years, with the rapid development of information technology and intelligent technology, the diagnosis methods of nuclear power plant equipment failures have also been continuously improved. Existing fault diagnosis technologies mainly rely on periodic equipment inspections and post-analysis of operating data. Although these methods can discover and solve problems to a certain extent, they often lack real-time and predictive capabilities. The existing problems include the following:

[0004] 1) Lack of real-time performance: Traditional fault diagnosis methods rely on periodic inspections and post-data analysis, which lack real-time performance and make it difficult to detect equipment failures in a timely manner.

[0005] 2) The analysis of complex dependencies is not accurate enough: Existing methods cannot accurately analyze the complex dependencies and interactions between equipment in nuclear power plants, and cannot effectively predict and prevent potential problems.

[0006] 3) Limitations of fault impact assessment: Existing methods usually rely on historical fault data and empirical rules, with low prediction accuracy and difficulty in adapting to rapid changes in equipment and operating environment. Especially when introducing new equipment or upgrading existing equipment, the adjustment and verification process is time-consuming and affects safe operation. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes a method and system for diagnosing equipment faults in nuclear power plants. By collecting equipment operation data in real time and dynamically building and updating equipment relationship diagrams using physical connections and functional dependencies between devices, the present invention can reflect the status of each device and the health status of the entire system in real time. In addition, the method of the present invention also introduces the probability calculation of the impact of equipment failures, which can accurately analyze the impact that a faulty device may have on other parts of the system based on the total score of the equipment and the dependencies between them, thereby making a faster and more effective response; solving the problem that existing methods are difficult to accurately analyze the complex dependencies and interactive effects between devices.

[0008] In order to achieve the above object, the present invention adopts the following technical solution:

[0009] One or more embodiments provide a method for diagnosing a nuclear power plant equipment fault, comprising the following steps:

[0010] Acquire nuclear power plant equipment data in real time and perform data preprocessing;

[0011] Based on the physical connections and functional dependencies between devices, a device relationship diagram is constructed to reflect the relationship between all devices;

[0012] Using the real-time data of nuclear power plant equipment, update the node status in the equipment relationship diagram and mark the equipment with abnormal operating data;

[0013] Based on the updated equipment relationship diagram, calculate the probability of the impact on other equipment in the nuclear power plant when an abnormal equipment node fails;

[0014] Identify the fault impact area based on the impact probability, and perform fault diagnosis and response.

[0015] One or more embodiments provide a nuclear power plant equipment fault diagnosis system, including:

[0016] A data acquisition module is configured to acquire nuclear power plant equipment data in real time and perform data preprocessing;

[0017] A device relationship graph module is configured to construct a device relationship graph reflecting the relationship between all devices according to the physical connections and functional dependencies between the devices;

[0018] The abnormal equipment module is configured to update the node status in the equipment relationship diagram using the real-time acquired nuclear power plant equipment data, and mark the equipment with abnormal operation data;

[0019] An impact probability analysis module is configured to calculate the impact probability of other equipment in the nuclear power plant when an abnormal equipment node fails based on the updated equipment relationship diagram;

[0020] The fault diagnosis module is configured to identify the fault impact area according to the impact probability, and perform fault diagnosis and response.

[0021] An electronic device comprises a memory and a processor and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above-mentioned method for diagnosing faults of nuclear power plant equipment are completed.

[0022] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the steps in the above-mentioned nuclear power plant equipment fault diagnosis method are completed.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention uses real-time collected data and dynamically updated equipment relationship diagrams to quickly detect faults when equipment anomalies occur, thereby significantly shortening the fault detection time; by real-time collection of nuclear power plant equipment data and construction of equipment relationship diagrams, rapid capture and dynamic management of equipment status are achieved. By updating node status in real time and marking anomalies, as well as analyzing potential fault impacts, the accuracy and response speed of fault diagnosis are improved. Through precise risk assessment and hierarchical fault response, the system stability and safety of nuclear power plants are effectively improved, maintenance strategies and resource allocation are significantly optimized, and the ability to prevent and control large-scale faults is enhanced.

[0025] The advantages of the present invention and additional advantages will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their description are used to explain the present invention but do not constitute a limitation of the present invention.

[0027] Figure 1 is a method flow chart of a method for diagnosing faults of nuclear power plant equipment according to embodiment 1 of the present invention;

[0028] Figure 2 It is a system block diagram of a nuclear power plant equipment fault diagnosis system according to embodiment 2 of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof. It should be noted that, in the absence of conflict, the various embodiments of the present invention and the features in the embodiments can be combined with each other. The embodiments will be described in detail below in conjunction with the accompanying drawings.

[0032] Example 1

[0033] In the technical solutions disclosed in one or more embodiments, Figure 1 As shown, a method for diagnosing faults of nuclear power plant equipment comprises the following steps:

[0034] Step S1, real-time acquisition of nuclear power plant equipment data, and data preprocessing;

[0035] Step S2: construct a device relationship diagram reflecting the relationship between all devices based on the physical connections and functional dependencies between the devices;

[0036] Step S3: using the real-time acquired nuclear power plant equipment data, updating the node status in the equipment relationship diagram, and marking the equipment with abnormal operating data;

[0037] Step S4: Based on the updated equipment relationship diagram, calculate the probability of the impact on other equipment in the nuclear power plant when an abnormal equipment node fails;

[0038] Step S5: Identify the fault impact area according to the impact probability, and perform fault diagnosis and response.

[0039] In this embodiment, by using real-time collected data and dynamically updated equipment relationship diagrams, faults can be quickly detected when equipment abnormalities occur, thereby significantly shortening the fault detection time; by real-time collection of nuclear power plant equipment data and construction of equipment relationship diagrams, rapid capture and dynamic management of equipment status are achieved. By updating node status in real time and marking abnormalities, as well as analyzing potential fault impacts, the accuracy and response speed of fault diagnosis are improved. Through accurate risk assessment and hierarchical fault response, the system stability and safety of nuclear power plants are effectively improved, maintenance strategies and resource allocation are significantly optimized, and the ability to prevent and control large-scale faults is enhanced.

[0040] In some embodiments, step S1, real-time collection of nuclear power plant equipment data and data preprocessing, wherein the nuclear power plant equipment data includes equipment operation data, equipment physical connection information, equipment function dependency information, historical maintenance fault logs and operation logs;

[0041] Equipment operation data, including equipment temperature, pressure, flow rate, current, voltage, etc., and data cleaning of equipment operation data;

[0042] Physical connection information of devices, including wire and pipe connections between devices. This information is the basis for building a physical connection diagram between devices.

[0043] Equipment function dependency information, which records the functional dependencies between equipment, such as the operation of a pump depends on the switch status of a specific valve;

[0044] Historical maintenance fault information, which records the historical maintenance activities of the equipment, such as replacement of parts, regular inspection results, etc., the type, time, treatment measures and recovery status of historical equipment faults;

[0045] Operation logs include records of operator operations on equipment, including all manual or automatic control activities.

[0046] A feasible technical solution is to perform data preprocessing and perform corresponding preprocessing for different data;

[0047] 1.1) Preprocessing of equipment operation data;

[0048] Equipment operation data usually includes equipment temperature, pressure, flow rate, current, voltage and other information. Effective preprocessing of these data can ensure the accuracy and consistency of the data and provide a reliable basis for subsequent analysis. Preprocessing methods include sequentially performing data cleaning, data standardization and normalization, data interpolation and smoothing;

[0049] Clean the equipment operation data, including:

[0050] Missing value processing: fill in missing data or perform interpolation based on historical trends;

[0051] Outlier detection and processing: Identify and correct abnormal data points through statistical analysis methods (such as Z score, IQR);

[0052] Denoising: Use filters (such as Kalman filtering, low-pass filtering) to remove noise from the data.

[0053] Data standardization and normalization:

[0054] Standardization: Convert data into a standard normal distribution to facilitate comparison of data of different dimensions.

[0055] Normalization: Scaling data to a specific range (such as [0,1]) to facilitate training using machine learning models.

[0056] Data interpolation and smoothing:

[0057] Interpolation: Interpolate intervals in a time series, such as using linear interpolation or polynomial interpolation.

[0058] Smoothing: Reduce short-term fluctuations and highlight long-term trends through moving average or exponential smoothing.

[0059] In this embodiment, through denoising and smoothing, random fluctuations in the data are reduced, long-term trends are highlighted, and the monitoring of the equipment operating status is made more stable and reliable;

[0060] 1.2) Preprocessing of device physical connection information;

[0061] The physical connection information of the equipment records the physical connection relationship between the wires, pipes, etc. between the equipment, which is the basis for building the physical connection diagram between the equipment. The preprocessing method includes sequentially performing data formatting, removing redundant information and verifying the topological relationship;

[0062] Data formatting: Convert the physical connection information in different data sources into a unified format, which can be converted into the adjacency matrix or adjacency list of the graph to achieve unified format;

[0063] Redundant information removal: remove duplicate connection information to ensure the simplicity and accuracy of connection data;

[0064] Topology verification: By analyzing the physical connection diagram, verify the correctness of the connection information and ensure that there are no unreasonable loops or breakpoints.

[0065] 1.3) Preprocessing of device function dependency information;

[0066] Equipment functional dependency information records the functional dependency between equipment, such as the operation of a pump depends on the switch state of a specific valve. The preprocessing method includes sequentially performing logic consistency check, dependency reorganization, and functional dependency graph construction;

[0067] Logical consistency check: Check the logical consistency of dependencies to ensure that the dependency chain of each device is reasonable and conflict-free. For example, ensure that there is no circular dependency or deadlock;

[0068] Dependency reorganization: adjust and optimize functional dependencies based on actual operation data and historical records to reflect the real dependencies between devices;

[0069] Functional dependency graph construction: Build a functional dependency graph of equipment, and use graph theory algorithms to analyze critical paths or bottleneck equipment.

[0070] 1.4) Preprocessing of historical maintenance fault information;

[0071] The historical maintenance fault information includes the historical maintenance records and fault logs of the equipment. The preprocessing method includes sequentially performing data classification and labeling, time series analysis, and correlation analysis;

[0072] Data classification and labeling: Classify maintenance activities (such as replacement of parts, regular inspection) and label the fault type for subsequent analysis;

[0073] Time series analysis: Convert fault events and maintenance records into time series data to analyze the periodicity of fault occurrence or its correlation with specific operations;

[0074] Correlation analysis: Through data mining technology, the relationship between failure types and maintenance measures is analyzed to identify potential failure modes or root causes.

[0075] 1.5) Preprocessing of operation logs;

[0076] The operation log records all the operator's operation activities on the equipment, including manual or automatic control. The preprocessing method includes sequentially performing log parsing and structured processing, operation sequence analysis, and operation and fault correlation analysis;

[0077] Log parsing and structuring: Parse the operation logs and convert the text-formatted operation records into structured data (such as tables in a database) for further analysis.

[0078] Operation sequence analysis: Analyze the operation sequence, identify high-frequency operation modes or abnormal operation behaviors, and conduct correlation analysis with the equipment operation status;

[0079] Operation and fault correlation analysis: Combined with fault logs, analyze the potential relationship between operation behavior and equipment failure, and identify misoperation or operational errors that may cause failures.

[0080] Through the above preprocessing method, different data are preprocessed so that data of different dimensions can be processed uniformly, thus realizing the integrated fusion of data.

[0081] In some embodiments, in step S2, a device relationship graph reflecting the relationship between all key devices is constructed based on the physical connection and functional dependency between devices; the device relationship graph includes nodes and edges, each node represents a device, each edge represents a connection or dependency between devices, and each edge is assigned specific attributes and weights, reflecting its connection strength and importance in the system;

[0082] The method of this embodiment takes into account the physical connection and functional dependency between devices, and can locate the faulty device more accurately, so the accuracy of fault diagnosis is higher.

[0083] Furthermore, the equipment is scored according to their importance and organized hierarchically according to the total equipment score in the equipment relationship diagram;

[0084] Optionally, nodes in the device relationship graph contain device attributes, and edges in the device relationship graph include connection type (physical or functional), as well as additional attributes such as connection strength and operation dependency level.

[0085] For further technical solutions, the total equipment score is calculated based on the importance of equipment functions, the impact of equipment failures, equipment dependencies, and equipment safety levels, expressed as:

[0086] SC=(F×WF )+(I×W I )+(D×W D )+(S×w S )

[0087] Among them, SC is the total score of the equipment, F is the importance of the equipment function, and w F is the importance weight of equipment function, I is the impact of equipment failure, and w I is the impact weight of equipment failure, D is the equipment system dependency, and w D is the device system dependency weight, S is the device security level, and w S Weight for equipment safety rating; Determine the weight of each factor to reflect its importance in the total score;

[0088] Furthermore, in the calculation formula for the total equipment score, the quantification method of each factor is:

[0089] The functional importance of the equipment F is based on the percentage of the equipment's operating time to the total operating time (operating load) and the equipment's contribution to production capacity (capacity contribution);

[0090] Equipment failure impact I is: the frequency based on the equipment failure history and the downtime caused by the most recent failure (failure downtime).

[0091] The device system dependency D is based on the number of calls (system calls) to the device when other systems are started.

[0092] The equipment safety level S is based on the number of records related to equipment and safety accidents (safety accident records).

[0093] A further technical solution is to organize hierarchies according to the total score of the device. The number of layers can be set as needed. In this embodiment, it can be set to three levels. Specifically: a low threshold of the total score of the device and a high threshold of the total score of the device are set. If the SC is less than or equal to the low threshold of the total score of the device, it is set to an auxiliary layer. If the SC is greater than the low threshold of the total score of the device and less than or equal to the high threshold of the total score of the device, it is set to a supporting layer. If the SC is greater than the high threshold of the total score of the device, it is set to a core layer; the low score threshold is less than the high threshold of the total score;

[0094] In the scheme of the above steps, by utilizing the real-time collected data and the dynamically updated equipment relationship diagram, the fault can be quickly detected when the equipment is abnormal, thereby significantly shortening the fault detection time.

[0095] In step S3, the node status in the equipment relationship diagram is updated using the real-time collected nuclear power plant equipment data, and the equipment with abnormal operating data is marked. Specifically:

[0096] A normal operating range is set for the equipment operating data of each device, and the equipment operating data is monitored in real time. If the collected equipment operating data exceeds the normal operating range, the device with abnormal operating data is marked, and the node of the device with abnormal operating data flashes.

[0097] In step S4, based on the established and updated device relationship diagram, the probability of the impact on other devices when an abnormal device node fails is analyzed; the probability of the abnormal device failure affecting other devices is calculated, and the calculation formula is:

[0098]

[0099] Among them, P ij is the probability that the failure of device i affects device j, α is the adjustment coefficient, W ij is the connection weight from device i to device j, SC i is the total score of device i, SC j is the total score of device j, β is the adjustment coefficient, L ij It is the hierarchical factor. Different layers have different hierarchical factors. The hierarchical factor of the core layer is greater than the hierarchical factor of the supporting layer, which is greater than the hierarchical factor of the auxiliary layer.

[0100] The method of this embodiment can more accurately evaluate the impact of a faulty device on other devices by calculating the impact probability of device failure, thereby improving the accuracy of fault impact assessment.

[0101] In step S5, the fault impact area is identified according to the impact probability, and fault diagnosis and response are performed.

[0102] Step S51: Calculate the device failure impact score based on the obtained probability that the failure of device i affects device j and the total score of the device, expressed as:

[0103]

[0104] Among them, ISc i is the device failure impact score of device i, and adj(i) is the set of all devices directly connected to device i.

[0105] Step S52: Delineating an impact area according to the calculated equipment failure impact score;

[0106] Specifically, set the low threshold of the device failure impact score and the high threshold of the device failure impact score. i If the device failure impact score is less than or equal to the low threshold, it is a low-risk area. i If the ISc is greater than the low threshold of the equipment failure impact score and less than or equal to the high threshold of the equipment failure impact score, it is a medium-risk area. iIf the impact score is greater than the high threshold of the equipment failure impact score, it is a high-risk area.

[0107] Step S53: Perform integrated fault response based on the affected area and device level:

[0108] 1) For the impact area processing, the same-level equipment is processed according to the priority of high-risk area, medium-risk area and low-risk area; wherein, in this embodiment, the level refers to the three levels of core layer, support layer and auxiliary layer, and each level is divided into high-risk area, medium-risk area and low-risk area;

[0109] 2) For equipment level processing, the equipment in the same level of impact area shall be processed according to the priority of core layer, support layer and auxiliary layer; the same level of impact area is any area level of low risk area, medium risk area and high risk area;

[0110] If the abnormal device is a core layer device, if it is in a high-risk area, take immediate action to start the backup system or emergency repair; if it is in a medium-risk area, arrange for rapid inspection and maintenance; if it is in a low-risk area, arrange for inspection and maintenance and complete it within the specified time;

[0111] If the abnormal equipment is a support layer equipment, if it is in a high-risk area, quickly check the equipment status and prepare maintenance measures; if it is in a medium-risk area, plan to inspect and maintain it in the short term; if it is in a low-risk area, monitor the operation of the equipment and arrange for inspection during the regular maintenance cycle;

[0112] If the abnormal device is an auxiliary layer device and is in a high-risk area, check whether the device affects higher-level devices. If it affects higher-level devices, increase the processing priority; if it is in a medium-risk area, perform inspection and maintenance within the set time; if it is in a low-risk area, continue to monitor to ensure that it does not escalate to a higher risk.

[0113] For a device directly connected to an abnormal device, if it is a higher level connected device than the abnormal device, regardless of ISc i No matter what, it is necessary to prioritize stable operation and avoid system-level chain reactions. If it is a connected device at a lower level than the abnormal device, according to ISc i Adjust processing priorities.

[0114] The method of this embodiment optimizes the allocation of maintenance resources and improves the utilization efficiency of maintenance resources through a hierarchical fault response strategy. Since it can quickly detect and respond to faults, the method of the present invention shows a higher ability in preventing and controlling large-scale faults. The method of the present invention can respond quickly by updating and analyzing the device status in real time, which significantly improves the response speed.

[0115] In order to verify the technical effect adopted in this embodiment, the actual effect of this method is verified.

[0116] Simulation conditions:

[0117] Number of equipment: 500 key equipment

[0118] Operation data types: temperature, pressure, flow rate, current, voltage

[0119] Simulation time: 1000 hours

[0120] Fault type: Random equipment failure, including sensor failure, mechanical failure, electrical failure, etc.

[0121] Failure rate: 0.01% failure probability per device per hour

[0122] The traditional method refers to periodic equipment inspection and post-analysis of operating data, which mainly relies on the operator's experience and historical data for fault diagnosis and impact assessment, lacking real-time and predictive capabilities.

[0123] The detection method of this embodiment and the traditional method are used to perform detection at the same time, and the detection comparison results are shown in Table 1 below:

[0124] Table 1 Comparison table between the method of this embodiment and the traditional method

[0125] Evaluation indicators The method of this embodiment Traditional methods Fault detection time (average) 2 minutes 30 minutes Fault diagnosis accuracy 95％ 70％ Fault impact assessment accuracy 92％ 65％ System stability improvement rate 30％ 10％ Maintenance resource optimization rate 25％ 5％ Large-scale fault prevention and control capability (index) high middle Response speed Quick response (<5 minutes) Slow response (30 minutes to 1 hour)

[0126] As can be seen from the table, the method of this embodiment greatly shortens the fault detection time, which only takes 2 minutes, while the traditional method takes 30 minutes, and the response speed is fast; the fault diagnosis accuracy of the method of this embodiment reaches 95%, which is much higher than the 70% of the traditional method, and can locate the problem more accurately; the method of this embodiment can improve the system stability by 30%, which is 20 percentage points higher than the traditional method, and significantly improves the stability of the system; the method of this embodiment can optimize 25% of maintenance resources, which is much higher than the 5% of the traditional method, and utilizes resources more efficiently; the method of this embodiment has outstanding performance in response speed, and can respond quickly within 5 minutes, while the traditional method takes 30 minutes to 1 hour, which greatly improves the response efficiency; It can be seen that the method of this embodiment is superior to the traditional method in multiple key evaluation indicators, showing faster and more accurate detection and diagnosis, more significant improvement in system stability, more efficient resource utilization, and stronger fault prevention and control capabilities.

[0127] Example 2

[0128] Based on Example 1, Figure 2 As shown, this embodiment provides a nuclear power plant equipment fault diagnosis system, including:

[0129] A data acquisition module is configured to acquire nuclear power plant equipment data in real time and perform data preprocessing;

[0130] A device relationship graph module is configured to construct a device relationship graph reflecting the relationship between all devices according to the physical connections and functional dependencies between the devices;

[0131] The abnormal equipment module is configured to update the node status in the equipment relationship diagram using the real-time acquired nuclear power plant equipment data, and mark the equipment with abnormal operation data;

[0132] An impact probability analysis module is configured to calculate the impact probability of other equipment in the nuclear power plant when an abnormal equipment node fails based on the updated equipment relationship diagram;

[0133] A fault response module is configured to identify a fault impact area according to an impact probability, and perform fault diagnosis and response;

[0134] It should be noted here that the various modules in this embodiment correspond one-to-one to the various steps in Example 1, and the specific implementation process is the same, which will not be repeated here.

[0135] Example 3

[0136] Based on Example 1, this embodiment provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, the steps in a nuclear power plant equipment fault diagnosis method described in Example 1 are completed.

[0137] Example 4

[0138] Based on Example 1, this embodiment provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps in a nuclear power plant equipment fault diagnosis method described in Example 1 are completed.

[0139] The electronic device proposed in the present invention can be a mobile terminal or a non-mobile terminal. The non-mobile terminal includes a desktop computer, and the mobile terminal includes a smart phone (such as an Android phone, an IOS phone, etc.), smart glasses, a smart watch, a smart bracelet, a tablet computer, a laptop computer, a personal digital assistant, and other mobile Internet devices that can perform wireless communication.

[0140] It should be understood that in the present invention, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0141] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor, and a portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0142] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in the present invention can be directly embodied as being executed by a hardware processor, or being executed by a combination of hardware and software modules in a processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here. A person of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0144] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a division of logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0145] 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, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0147] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for diagnosing faults in nuclear power plant equipment, characterized in that: The steps include: Acquire nuclear power plant equipment data in real time and perform data preprocessing; Based on the physical connections and functional dependencies between devices, a device relationship diagram is constructed to reflect the relationship between all devices; Using the real-time data of nuclear power plant equipment, update the node status in the equipment relationship diagram and mark the equipment with abnormal operating data; Based on the updated equipment relationship diagram, calculate the probability of the impact on other equipment in the nuclear power plant when an abnormal equipment node fails; Identify the fault impact area based on the impact probability, and perform fault diagnosis and response.

2. A method for diagnosing faults in nuclear power plant equipment according to claim 1, characterized in that: Nuclear power plant equipment data includes equipment operation data, equipment physical connection information, equipment function dependency information, historical maintenance fault logs, and operation logs; The preprocessing of equipment operation data includes data cleaning, data standardization and normalization, data interpolation and smoothing in sequence; Preprocessing of the physical connection information of the device includes sequentially performing data formatting, removing redundant information, and verifying the topological relationship; Preprocessing of device functional dependency information, including sequentially performing logic consistency checks, dependency reorganization, and functional dependency graph construction; The preprocessing of historical maintenance fault information includes sequentially performing data classification and labeling, time series analysis, and correlation analysis; The preprocessing of operation logs includes sequentially performing log parsing and structured processing, operation sequence analysis, and operation and fault correlation analysis.

3. A method for diagnosing nuclear power plant equipment faults according to claim 1, characterized in that: Based on the physical connections and functional dependencies between devices, build a device relationship diagram that reflects the relationships between all key devices; The device relationship graph consists of nodes and edges. Each node represents a device, and each edge represents the connection or dependency between devices. Each edge is assigned specific attributes and weights to reflect its connection strength and importance in the system.

4. A method for diagnosing nuclear power plant equipment faults as claimed in claim 3, characterized in that: Equipment is scored according to its importance and organized hierarchically according to its total score in the equipment relationship diagram. The total score of equipment is scored based on the importance of equipment functions, the impact of equipment failures, equipment dependencies and equipment safety levels. The total score of equipment is the weighted sum of the values ​​of each factor and the product of its weights.

5. A method for diagnosing nuclear power plant equipment faults as claimed in claim 4, characterized in that: The devices are organized into layers according to their total scores. Specifically, a low threshold and a high threshold of the total score of the devices are set. If the SC is less than or equal to the low threshold of the total score of the devices, the device is set as an auxiliary layer. If the SC is greater than the low threshold of the total score of the devices and less than or equal to the high threshold of the total score of the devices, the device is set as a support layer. If the SC is greater than the high threshold of the total score of the devices, the device is set as a core layer. The low score threshold is less than the high threshold of the total score.

6. A method for diagnosing faults in nuclear power plant equipment according to claim 1, characterized in that: Calculate the probability that abnormal equipment failure affects other equipment. The calculation formula is: Among them, P ij is the probability that the failure of device i affects device j, α is the adjustment coefficient, W ij is the connection weight from device i to device j, SC i is the total score of device i, SC j is the total score of device j, β is the adjustment coefficient, L ij It is the hierarchical factor in the device relationship diagram. The hierarchical factors of different layers are different.

7. A method for diagnosing faults in nuclear power plant equipment according to claim 1, characterized in that: Identify the fault impact area based on the impact probability, perform fault diagnosis and response, including the following steps: Calculate the equipment failure impact score based on the probability that the failure of equipment i affects equipment j and the total equipment score; Delineate the impact area based on the calculated equipment failure impact score; Integrated fault response based on the affected area and device level: For the affected area processing, the equipment at the same level is processed according to the priority of high-risk area, medium-risk area and low-risk area; For device-level processing, devices in the same level of impact area are processed according to the priority of core layer, support layer, and auxiliary layer.

8. A nuclear power plant equipment fault diagnosis system, characterized in that: include: A data acquisition module is configured to acquire nuclear power plant equipment data in real time and perform data preprocessing; A device relationship graph module is configured to construct a device relationship graph reflecting the relationship between all devices according to the physical connections and functional dependencies between the devices; The abnormal equipment module is configured to update the node status in the equipment relationship diagram using the real-time acquired nuclear power plant equipment data, and mark the equipment with abnormal operation data; An impact probability analysis module is configured to calculate the impact probability of other equipment in the nuclear power plant when an abnormal equipment node fails based on the updated equipment relationship diagram; The fault diagnosis module is configured to identify the fault impact area according to the impact probability, and perform fault diagnosis and response.

9. An electronic device, characterized in that: The method comprises a memory and a processor and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the method for diagnosing faults of nuclear power plant equipment described in any one of claims 1 to 7 are completed.

10. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of a nuclear power plant equipment fault diagnosis method as described in any one of claims 1-7.

Images