Nuclear power DCS system communication server fault prediction method, system, device, medium and product
The method uses LSTM and CNN models to analyze real-time data from nuclear DCS system communication servers, predicting faults and improving their safety and reliability through proactive maintenance.
Patent Information
- Application Number
- CN202411803677.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-10
- Publication Date
- 2025-03-28
AI Technical Summary
Nuclear digital control systems (DCS) communication servers in nuclear power plants face challenges in predictive maintenance, often managed reactively, which affects their safety and reliability.
A method utilizing trained long short-term memory (LSTM) and convolutional neural networks (CNN) to predict server failures by analyzing real-time data such as CPU temperature, memory usage, and communication rates, categorizing failures as no fault, minor, general, severe, or catastrophic.
Enhances the safety and reliability of nuclear DCS system communication servers by enabling proactive fault prediction and prevention.
Smart Images
Figure CN119720033A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of fault prediction, and in particular to a method, system, device, medium and product for predicting a fault of a communication server in a nuclear power DCS system. Background Art
[0002] The nuclear safety-grade digital control system (DCS) is the "brain and nervous system" of a nuclear power plant. The design, manufacturing, operation, and maintenance of the nuclear power DCS system communication server all need to take into account complex working conditions and environments, and have high safety and reliability requirements. In China's nuclear power plants and other industrial sectors, most electronic equipment is still in a passive management state, that is, corrective processing can only be performed after a fault occurs, which affects the safety and reliability of the operation of the nuclear power DCS system communication server.
[0003] Therefore, a fault prediction method for a communication server of a nuclear power DCS system is needed. Summary of the invention
[0004] The purpose of this application is to provide a method, system, device, medium and product for predicting the fault of a communication server of a nuclear power DCS system, so as to realize the prediction of the fault of a communication server of a nuclear power DCS system.
[0005] To achieve the above objectives, this application provides the following solutions:
[0006] In a first aspect, the present application provides a method for predicting a fault of a communication server of a nuclear power DCS system, comprising:
[0007] Obtaining the operating data of the target server at each moment in the current period; the target server is the communication server of the nuclear power DCS system to be predicted, and the operating data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operating status of each network port, operating status and resource occupancy rate of each system service and software, database cache hit rate and result delivery degree of data cycle processing;
[0008] Determine the predicted value of the target server's operating data at the time to be predicted by using the operating data prediction model and the operating data of the target server at each time in the current period; the operating data prediction model is obtained by training a long short-term memory neural network;
[0009] The predicted value of the operating data of the target server at the time to be predicted is input into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training a convolutional neural network, and the fault result is: no fault, minor fault, general fault, serious fault or catastrophic fault.
[0010] Optionally, the process of determining the running data prediction model includes:
[0011] Acquire a training set; the training set includes a plurality of sample operation data groups; the operation sample data group includes: sample data of N consecutive training historical moments of the training communication server, N>1; wherein the sample data of the first N-1 consecutive training historical moments include the measured values of the operation data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the measured value of the operation data of the Nth training historical moment;
[0012] Constructing long short-term memory neural networks;
[0013] The long short-term memory neural network is trained using the training set to obtain the operation data prediction model.
[0014] Optionally, using the training set to train the long short-term memory neural network to obtain the operation data prediction model includes:
[0015] Preprocessing each sample data group in the training set to obtain a corresponding preprocessed sample data group; the preprocessed sample data group includes: preprocessed sample data of N consecutive training historical moments of the training communication server; wherein the preprocessed sample data of the first N-1 consecutive training historical moments include the preprocessed running data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the preprocessed running data of the Nth training historical moment;
[0016] The long short-term memory neural network is trained by taking the preprocessed operation data of the first N-1 consecutive training historical moments in each preprocessed sample data group as input and the preprocessed operation data of the Nth training historical moment in the corresponding preprocessed sample data group as output to obtain the operation data prediction model.
[0017] Optionally, using the operation data prediction model and the operation data of the target server at each time in the current period to determine the predicted value of the operation data of the target server at the time to be predicted includes:
[0018] Preprocessing the operation data of the target server at each moment in the current period to obtain the preprocessed operation data of the target server at each moment in the current period;
[0019] The preprocessed operation data of the target server at each moment in the current time period is input into the operation data prediction model to obtain the predicted value of the operation data of the target server at the moment to be predicted.
[0020] Optionally, the preprocessing includes: data cleaning, data standardization and data integration.
[0021] Optionally, the process of determining the fault prediction model includes:
[0022] Obtaining historical operation data of multiple sample communication servers and manually calibrated values of corresponding fault results;
[0023] Constructing the convolutional neural network;
[0024] The convolutional neural network is trained using the historical operation data of each sample communication server and the manually calibrated values of the corresponding fault results to obtain the fault prediction model.
[0025] In a second aspect, the present application provides a nuclear power DCS system communication server fault prediction system, comprising:
[0026] The operation data acquisition module is used to acquire the operation data of the target server at each moment in the current period; the target server is the communication server of the nuclear power DCS system to be predicted, and the operation data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operation status of each network port, operation status and resource occupancy rate of each system service and software, database cache hit rate and result delivery degree of data cycle processing;
[0027] An operation data prediction module is used to determine the predicted value of the operation data of the target server at the time to be predicted by using the operation data prediction model and the operation data of the target server at each time in the current period; the operation data prediction model is obtained by training the long short-term memory neural network;
[0028] The fault prediction module is used to input the predicted value of the operating data of the target server at the time to be predicted into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training the convolutional neural network, and the fault result is: no fault, minor fault, general fault, serious fault or catastrophic fault.
[0029] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned methods for predicting a nuclear power DCS system communication server fault.
[0030] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for predicting a nuclear power DCS system communication server failure.
[0031] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting a nuclear power DCS system communication server failure.
[0032] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0033] The present application discloses a method, system, device, medium and product for predicting a fault of a communication server of a nuclear power DCS system. First, the operation data of the target server at each moment in the current period is obtained; then, the predicted value of the operation data of the target server at the time to be predicted is determined by using the operation data prediction model and the operation data of the target server at each moment in the current period; the operation data prediction model is obtained by training a long short-term memory neural network; finally, the predicted value of the operation data of the target server at the time to be predicted is input into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training a convolutional neural network, and the fault result is: no fault, minor fault, general fault, serious fault or catastrophic fault. The present application realizes the fault prediction of the communication server of the nuclear power DCS system by using the operation data prediction model obtained by training the long short-term memory neural network and the fault prediction model obtained by training the convolutional neural network, and improves the operation safety and reliability of the communication server of the nuclear power DCS system. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 A schematic flow chart of a method for predicting a fault in a communication server of a nuclear power DCS system provided in one embodiment of the present application;
[0036] Figure 2 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0038] The purpose of this application is to provide a method, system, device, medium and product for predicting the fault of a communication server of a nuclear power DCS system, aiming to realize the fault prediction of a communication server of a nuclear power DCS system.
[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0040] In an exemplary embodiment, Figure 1 As shown, the nuclear power DCS system communication server fault prediction method in this embodiment includes:
[0041] Step 1: Get the target server's running data at each time in the current period.
[0042] The target server is the communication server of the nuclear power DCS system to be predicted, and the operating data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operating status of each network port, operating status and resource occupancy of each system service and software, database cache hit rate and result delivery degree of data cycle processing.
[0043] Step 2: Using the operation data prediction model and the operation data of the target server at each time in the current period, determine the predicted value of the operation data of the target server at the time to be predicted.
[0044] Among them, the running data prediction model is obtained by training the long short-term memory neural network.
[0045] As an optional implementation, in step 2, the process of determining the running data prediction model includes:
[0046] Step 211: Obtain a training set; the training set includes multiple sample operation data groups; the operation sample data group includes: sample data of N consecutive training historical moments of the training communication server, N>1; wherein, the sample data of the first N-1 consecutive training historical moments include the measured values of the operation data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the measured value of the operation data of the Nth training historical moment.
[0047] Step 212: Construct a long short-term memory neural network.
[0048] Step 213: Use the training set to train the long short-term memory neural network to obtain an operation data prediction model.
[0049] As an optional implementation, step 213 includes:
[0050] Step 2131: Preprocess each sample data group in the training set to obtain a corresponding preprocessed sample data group; the preprocessed sample data group includes: preprocessed sample data of N consecutive training historical moments of the training communication server; wherein, the preprocessed sample data of the first N-1 consecutive training historical moments include the preprocessed running data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the preprocessed running data of the Nth training historical moment.
[0051] Step 2132: Using the preprocessed operation data of the first N-1 consecutive training historical moments in each preprocessed sample data group as input and the preprocessed operation data of the Nth training historical moment in the corresponding preprocessed sample data group as output, train the long short-term memory neural network to obtain an operation data prediction model.
[0052] As an optional implementation, step 2 includes:
[0053] Step 221: pre-processing the operation data of the target server at each moment in the current period to obtain the pre-processed operation data of the target server at each moment in the current period.
[0054] Step 222: input the preprocessed operation data of the target server at each time in the current time period into the operation data prediction model to obtain the predicted value of the operation data of the target server at the time to be predicted.
[0055] Step 3: Input the predicted value of the operating data of the target server at the time to be predicted into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted.
[0056] Among them, the fault prediction model is obtained by training the convolutional neural network, and the fault results are: no fault, minor fault, general fault, serious fault or catastrophic fault.
[0057] As an optional implementation, preprocessing includes: data cleaning, data standardization and data integration.
[0058] Specifically, data cleaning includes:
[0059] (1) Noise removal: Identify and remove outliers and noise in the operating data. For example, CPU temperature and hard disk space usage should not have negative values, and any negative values can be considered as erroneous data and removed.
[0060] (2) Handling missing values: For missing operating data, linear interpolation is used to fill the missing values, that is, the average value of the previous moment and the next moment of the missing operating data is used as the missing operating data.
[0061] (3) Time synchronization: Ensure that all data points are synchronized according to a unified timestamp.
[0062] Data standardization includes:
[0063] (1) For numerical operating data (such as CPU temperature), use the following formula to scale the data to a uniform range of 0 to 1:
[0064]
[0065] Among them, x' i The standardized value of the running data x for the data at the i-th moment; x i is the value of the data running data x at the ith moment before normalization; min(x) is the minimum value of the data running data x at all moments; max(x) is the maximum value of the data running data x at all moments.
[0066] (2) Category data encoding: For the operating data used for classification (such as memory model compatibility, network port operating status, etc.), label encoding is used to convert it into numerical data of [0, 1].
[0067] Data integration includes: integrating the standardized operating data into feature vectors.
[0068] As an optional implementation, in step 2, the process of determining the fault prediction model includes:
[0069] Step 31: Obtain historical operation data of multiple sample communication servers and manually calibrated values of corresponding fault results.
[0070] Step 32: Build a convolutional neural network.
[0071] Step 33: Use the historical operation data of each sample communication server and the manually calibrated values of the corresponding fault results to train the convolutional neural network to obtain a fault prediction model.
[0072] Specifically, step 33 includes:
[0073] Step 331: pre-process the historical operation data of each sample communication server to obtain the pre-processed historical operation data of each sample communication server.
[0074] Step 332: Using the pre-processed historical operation data of each sample communication server as input and the manually calibrated value of the corresponding fault result as output, the convolutional neural network is trained to obtain a fault prediction model.
[0075] Specifically, the manual calibration value is adjusted according to the actual situation. For example, the normal value range of the CPU temperature is (0℃~50℃], and the abnormal value range is (50℃~120℃]. When the CPU temperature is (0℃~50℃], the manual calibration value of the fault result is no fault; when the CPU temperature is (50℃~60℃], the manual calibration value of the fault result is a minor fault; when the CPU temperature is (60℃~70℃], the manual calibration value of the fault result is a general fault; when the CPU temperature is (70℃~95℃], the manual calibration value of the fault result is a serious fault; when the CPU temperature is (95℃~120℃], the manual calibration value of the fault result is a catastrophic fault.
[0076] In an exemplary embodiment, a nuclear power DCS system communication server fault prediction system is provided, comprising:
[0077] The operation data acquisition module is used to obtain the operation data of the target server at each moment in the current period; the target server is the nuclear power DCS system communication server to be predicted, and the operation data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operation status of each network port, operation status and resource occupancy rate of each system service and software, database cache hit rate and result delivery degree of data cycle processing.
[0078] The operation data prediction module is used to determine the predicted value of the operation data of the target server at the time to be predicted by using the operation data prediction model and the operation data of the target server at each moment in the current period; the operation data prediction model is obtained by training the long short-term memory neural network.
[0079] The fault prediction module is used to input the predicted value of the operating data of the target server at the time to be predicted into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training the convolutional neural network, and the fault results are: no fault, minor fault, general fault, serious fault or catastrophic fault.
[0080] In an exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for predicting a fault of a communication server of a nuclear power DCS system.
[0081] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for predicting a fault of a communication server of a nuclear power DCS system is implemented.
[0082] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements a method for predicting a nuclear power DCS system communication server failure when executed by a processor.
[0083] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 2 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting a fault of a communication server of a nuclear power DCS system is implemented.
[0084] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0086] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0087] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0089] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0090] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for predicting a fault in a communication server of a nuclear power DCS system, characterized in that: The method for predicting a nuclear power DCS system communication server failure comprises: Obtaining the operating data of the target server at each moment in the current period; the target server is the communication server of the nuclear power DCS system to be predicted, and the operating data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operating status of each network port, operating status and resource occupancy rate of each system service and software, database cache hit rate and result delivery degree of data cycle processing; Determine the predicted value of the target server's operating data at the time to be predicted by using the operating data prediction model and the operating data of the target server at each time in the current period; the operating data prediction model is obtained by training a long short-term memory neural network; The predicted value of the operating data of the target server at the time to be predicted is input into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training a convolutional neural network, and the fault result is: no fault, minor fault, general fault, serious fault or catastrophic fault.
2. The method for predicting a fault of a communication server of a nuclear power DCS system according to claim 1, characterized in that: The process of determining the operation data prediction model includes: Acquire a training set; the training set includes a plurality of sample operation data groups; the operation sample data group includes: sample data of N consecutive training historical moments of the training communication server, N>1; wherein the sample data of the first N-1 consecutive training historical moments include the measured values of the operation data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the measured value of the operation data of the Nth training historical moment; Constructing long short-term memory neural networks; The long short-term memory neural network is trained using the training set to obtain the operation data prediction model.
3. The method for predicting a nuclear power DCS system communication server failure according to claim 2, characterized in that: Using the training set to train the long short-term memory neural network to obtain the operation data prediction model includes: Preprocessing each sample data group in the training set to obtain a corresponding preprocessed sample data group; the preprocessed sample data group includes: preprocessed sample data of N consecutive training historical moments of the training communication server; wherein the preprocessed sample data of the first N-1 consecutive training historical moments include the preprocessed running data of the first N-1 consecutive training historical moments, and the sample data of the Nth training historical moment is the preprocessed running data of the Nth training historical moment; The long short-term memory neural network is trained by taking the preprocessed operation data of the first N-1 consecutive training historical moments in each preprocessed sample data group as input and the preprocessed operation data of the Nth training historical moment in the corresponding preprocessed sample data group as output to obtain the operation data prediction model.
4. The method for predicting a nuclear power DCS system communication server failure according to claim 3, characterized in that: Using the operation data prediction model and the operation data of the target server at each time in the current period, the predicted value of the operation data of the target server at the time to be predicted is determined, including: Preprocessing the operation data of the target server at each moment in the current period to obtain the preprocessed operation data of the target server at each moment in the current period; The preprocessed operation data of the target server at each moment in the current time period is input into the operation data prediction model to obtain the predicted value of the operation data of the target server at the moment to be predicted.
5. The method for predicting a nuclear power DCS system communication server failure according to claim 4, characterized in that: The preprocessing includes: data cleaning, data standardization and data integration.
6. The method for predicting a fault of a communication server of a nuclear power DCS system according to claim 1, characterized in that: The determination process of the fault prediction model includes: Obtaining historical operation data of multiple sample communication servers and manually calibrated values of corresponding fault results; Constructing the convolutional neural network; The convolutional neural network is trained using the historical operation data of each sample communication server and the manually calibrated values of the corresponding fault results to obtain the fault prediction model.
7. A nuclear power DCS system communication server fault prediction system, characterized in that: The nuclear power DCS system communication server fault prediction system includes: The operation data acquisition module is used to acquire the operation data of the target server at each moment in the current period; the target server is the communication server of the nuclear power DCS system to be predicted, and the operation data includes: CPU temperature and load, memory usage and model compatibility, hard disk space usage, communication rate and operation status of each network port, operation status and resource occupancy rate of each system service and software, database cache hit rate and result delivery degree of data cycle processing; An operation data prediction module is used to determine the predicted value of the operation data of the target server at the time to be predicted by using the operation data prediction model and the operation data of the target server at each time in the current period; the operation data prediction model is obtained by training the long short-term memory neural network; The fault prediction module is used to input the predicted value of the operating data of the target server at the time to be predicted into the fault prediction model to obtain the predicted value of the fault result of the target server at the time to be predicted; the fault prediction model is obtained by training the convolutional neural network, and the fault result is: no fault, minor fault, general fault, serious fault or catastrophic fault.
8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting a nuclear power DCS system communication server fault as described in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting a nuclear power DCS system communication server failure as described in any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting a nuclear power DCS system communication server failure as described in any one of claims 1 to 6 is implemented.