A method, apparatus, device, and medium for maintenance decision of a nuclear reactor

Abstract

The application provides a nuclear reactor maintenance decision method, device, equipment and medium, and relates to the fields of nuclear reactors and data processing. The method comprises the following steps: obtaining operation data and field environment information of a nuclear reactor, and performing fault diagnosis analysis based on the operation data and the field environment information to determine a fault device of the nuclear reactor; determining a fault level and a fault influence value of the fault device based on a fault determination index; determining the importance of the fault device to the nuclear reactor based on a structure tree of the nuclear reactor, and configuring a weight value of the fault device based on the importance; calculating a health degree contribution value of the fault device according to the fault influence value and the weight value of the fault device; summing up the health degree contribution values of all the fault devices of the nuclear reactor to obtain a health degree score of the nuclear reactor; determining a health state of the nuclear reactor based on the health degree score and a health state evaluation strategy, and determining a maintenance strategy according to the health state of the nuclear reactor.

Description

Technical Field

[0001] This application relates to the field of nuclear reactors and data processing, and in particular to a method, apparatus, equipment and medium for making maintenance decisions for nuclear reactors. Background Technology

[0002] Nuclear reactors are the core devices for nuclear energy utilization, and their operational stability and safety directly affect energy supply, the ecological environment, and public interests. Their systems are complex, and critical equipment operates under high temperature, high pressure, and strong radiation environments for extended periods, making them prone to aging and performance degradation. Failure to address these issues promptly can lead to equipment failure or safety accidents. Current nuclear reactor maintenance decisions primarily rely on traditional preventative and reactive maintenance models, which have significant shortcomings and are insufficient to meet the requirements for long-term stable operation. Summary of the Invention

[0003] In view of this, this application provides a method, apparatus, equipment, and medium for making maintenance decisions for nuclear reactors to solve the above-mentioned technical problems.

[0004] In a first aspect, embodiments of this application provide a method for making maintenance decisions for a nuclear reactor, including: Acquire nuclear reactor operating data and on-site environmental information, and use fault diagnosis strategies to perform fault diagnosis analysis on the acquired operating data and on-site environmental information to identify faulty equipment in the nuclear reactor; Based on the fault determination indicators, the fault level of the faulty equipment and the corresponding fault impact value are determined. Based on the nuclear reactor's structure tree, the importance of faulty equipment to the nuclear reactor is determined, and the weight value of the faulty equipment is configured based on the importance. Calculate the health contribution value of the faulty equipment based on its fault impact value and weight value. The health contribution values ​​of all faulty equipment in the nuclear reactor are summed to obtain the health score of the nuclear reactor; The health status of the nuclear reactor and the corresponding maintenance strategy are determined based on health scores and health status assessment strategies.

[0005] Secondly, embodiments of this application provide a maintenance decision-making device for a nuclear reactor, comprising: The data acquisition module is used to acquire the nuclear reactor's operating data and on-site environmental information; The fault diagnosis module is used to perform fault diagnosis analysis on the acquired operating data and on-site environmental information using fault diagnosis strategies to identify faulty equipment in the nuclear reactor. The impact value determination module is used to determine the fault level of the faulty equipment and the corresponding fault impact value based on the fault judgment index. The weight value determination module is used to determine the importance of faulty equipment to the nuclear reactor based on the nuclear reactor's structure tree, and to configure the weight value of the faulty equipment based on the importance. The health rating module is used to calculate the health contribution value of the faulty equipment based on the fault impact value and weight value of the faulty equipment, and to sum the health contribution values ​​of all faulty equipment in the nuclear reactor to obtain the health rating of the nuclear reactor. The maintenance strategy determination module is used to determine the health status of the nuclear reactor and the corresponding maintenance strategy based on the health score and health status assessment strategy.

[0006] Thirdly, embodiments of this application provide a computer device including a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions implementing the steps of the method as described in the first aspect when executed by the processor.

[0007] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect.

[0008] The nuclear reactor maintenance decision-making method, apparatus, computer equipment, and readable storage medium of this application, based on nuclear reactor operating data and on-site environmental information, determine the fault level of faulty equipment and the importance of the faulty equipment to the nuclear reactor, thereby obtaining a nuclear reactor health score. This enables the assessment of the nuclear reactor's health status and maintenance decisions, achieving the identification of potential faults and timely, scientific, precise, and automated maintenance decisions. This improves maintenance efficiency, ensures long-term stable equipment operation, and enhances overall reliability and availability. Furthermore, maintenance decisions can avoid over-maintenance, reduce unnecessary repairs, and minimize production losses caused by unplanned downtime.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a nuclear reactor maintenance decision-making method according to an embodiment of this application is shown; Figure 2A structural block diagram of a nuclear reactor maintenance decision-making device according to an embodiment of this application is shown; Figure 3 A structural block diagram of a computer device according to an embodiment of this application is shown. Detailed Implementation

[0011] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0013] The following description, in conjunction with the accompanying drawings, details the nuclear reactor maintenance decision-making method, apparatus, computer equipment, and readable storage medium provided in this application through specific embodiments and application scenarios. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0014] This application provides a method for making maintenance decisions for nuclear reactors, such as... Figure 1 As shown, the method includes: Step 101: Obtain the operating data and on-site environmental information of the nuclear reactor, and use a fault diagnosis strategy to perform fault diagnosis analysis on the obtained operating data and on-site environmental information to determine the faulty equipment of the nuclear reactor.

[0015] In this step, a series of sensors are installed on the nuclear reactor and its related systems to collect real-time operational data and on-site environmental information. This data is collected through an information management service of an instrumentation and control system and stored in a dedicated database for analysis. Sensors include visible light cameras, infrared thermal imagers, sound sensors, radiation probes, ultrasonic sensors, and other existing instruments in the instrumentation and control system. On-site environmental information includes high-resolution images, temperature distribution images, ambient audio, radiation dose, and other on-site information. Operational data includes condition data and performance data. Condition data includes equipment uptime, downtime, maintenance frequency, maintenance time and cost, expected failure types, failure causes, and repair times. Performance data includes process system temperature, pressure, vibration, flow rate, current, and voltage.

[0016] Furthermore, fault diagnosis strategies are employed to analyze the collected operational data and on-site environmental information to diagnose nuclear reactor faults. For example, when the reactor's coolant system temperature, flow rate, etc., exceed the normal range, and the intelligent algorithm identifies abnormal increases in equipment temperature or sharp airflow noises on-site, the fault diagnosis system will issue a warning and indicate possible causes of the fault.

[0017] Specifically, a fault diagnosis model based on the coupling of multiple physics fields in a nuclear reactor is established. This model includes a rule layer, an intelligent algorithm layer, and a decision layer. A dynamic threshold rule base is established by integrating thermal-hydraulic data (gradient change rates of temperature, pressure, flow rate, etc.) with neutron flux monitoring data (neutron flux distribution, reactivity changes, etc.). The operation of a nuclear reactor is a process of high coupling between the thermal-hydraulic field and the neutron physics field. For example, an abnormal increase in neutron flux can lead to a sharp increase in the temperature gradient of the primary coolant. The core of the fault diagnosis model is to establish the correlation between the two physics field data. Instead of analyzing temperature or neutron flux changes in isolation, the model uses the gradient change rates of both (such as the rate of temperature change over time and the spatial distribution differences of neutron flux) as the basic features for fault diagnosis, capturing the multi-physics field linkage signals triggered by the fault.

[0018] For the rule layer, a dynamic threshold rule base is established for key parameters such as thermal hydraulics and neutron flux. Unlike fixed thresholds, dynamic thresholds are adjusted in real time according to the reactor's operating conditions. When the gradient change rate of the monitored data exceeds the threshold range, the rule engine will directly trigger a preliminary fault alarm, which is equivalent to the first line of defense for diagnosis.

[0019] For the intelligent algorithm layer, for unstructured data such as sound and images on site, three types of intelligent algorithms are used to perform deep feature extraction to make up for the blind spots of traditional parameter monitoring: (1) Time-frequency domain analysis: Process the sound signals of reactor operation, such as pump and valve failures will produce abnormal noises at specific frequencies. Through Fourier transform, wavelet analysis and other methods, the fault type is identified from the time-frequency features of the sound; (2) Convolutional Neural Network (CNN): Focuses on extracting deep abstract features of image / sound data, which can capture weak fault signals better than traditional time-frequency domain analysis; (3) YOLO image processing model: For visual monitoring images of reactor site, realize real-time target detection, such as identifying whether the valve opening and closing status is abnormal, whether the pipeline is deformed, whether there are traces of leakage on site, etc., and quickly locate the physical location of the fault.

[0020] For the decision-making level, a weighted voting fusion model is used to determine the final result. Inconsistencies may exist between the alarm results from the rule engine and the analysis results from the intelligent algorithm; therefore, a decision-level fusion model is needed for the final judgment. Confidence-weighted voting: Each diagnostic result is assigned a confidence level. For example, the confidence level of a CNN identifying a fault is 90%, while the confidence level of the rule engine is 60%. The final score is calculated by weighting the confidence levels. Historical accuracy-weighted voting: Weights are assigned based on the past diagnostic accuracy of each diagnosis. For example, the historical accuracy of the YOLO model for valve faults is 95%, so its weight is higher than that of time-frequency domain analysis with an accuracy of 80%. Finally, through weighted fusion, the most reliable fault diagnosis conclusion is output.

[0021] Step 102: Based on the fault determination index, determine the fault level of the faulty equipment and the corresponding fault impact value.

[0022] In this step, various faults are pre-classified into different levels. For example, a fault in the reactor coolant system that will lead to system shutdown is classified as a Level 1 fault, while a minor leak in the cooling water system that will reduce cooling performance is classified as a Level 2 fault. Based on the fault determination criteria, the fault level of the faulty equipment and the corresponding fault impact value are determined. For example, the fault levels can include Level 1, Level 2, Level 3, and Level 4 faults, with a fault impact value of 0.5 for Level 1, 0.3 for Level 2, 0.1 for Level 3, and 0.05 for Level 4.

[0023] In one embodiment of this application, determining the fault level of the faulty equipment and the corresponding fault impact value based on fault determination indicators includes: Based on the operating characteristics of the equipment, determine the fault judgment strategy corresponding to each fault level; Determine the target fault determination strategy that the fault determination indicators of the faulty equipment meet, and use the fault level corresponding to the target fault determination strategy as the fault level of the faulty equipment; wherein, the fault determination indicators include at least one of the following: downtime, repair time, fault impact range, fault frequency, and maintenance cost.

[0024] In this embodiment, different fault levels are first classified according to the degree of impact of the fault. The fault levels include Level 1 fault, Level 2 fault, Level 3 fault, and Level 4 fault. Among them, Level 1 fault refers to a fault that directly causes system downtime, safety risks, or significant economic losses, and cannot be repaired in a short time, which is a major fault; Level 2 fault refers to a fault that severely degrades the performance of the equipment, but can still operate to a limited extent, and requires repair as soon as possible, which is a serious fault; Level 3 fault refers to a fault that affects some functions of the equipment and requires planned maintenance, which is a moderate fault; and Level 4 fault refers to a fault that has a minor impact on the operation of the equipment and can be handled during routine maintenance, which is a minor fault.

[0025] Based on the characteristics and operational requirements of nuclear power equipment, a fault diagnosis strategy is determined for each fault level. This involves selecting the necessary diagnostic indicators and setting threshold values ​​for each fault level, according to the characteristics and operational requirements of the nuclear power equipment. The diagnostic indicators and threshold values ​​may differ for different equipment under different operating conditions.

[0026] Furthermore, the fault determination indicators of the faulty equipment are determined to meet the target fault determination strategy, and the fault level corresponding to the target fault determination strategy is taken as the fault level of the faulty equipment.

[0027] Step 103: Based on the nuclear reactor's structure tree, determine the importance of the faulty equipment to the nuclear reactor, and configure the weight value of the faulty equipment based on its importance.

[0028] In this step, a structure tree for the nuclear reactor is established. The structure tree decomposes the reactor's equipment into different levels, from the top-level system to each subsystem and component; that is, the structure tree includes equipment at multiple levels. Key performance indicators of the equipment are analyzed to determine the importance of faulty equipment to the nuclear reactor, and its weight is determined based on this importance.

[0029] In one embodiment of this application, based on the nuclear reactor's structure tree, the importance of a faulty device to the nuclear reactor is determined, and a weight value for the faulty device is configured based on its importance, including: Obtain the failure rate of the lowest-level equipment in the nuclear reactor's structure tree, and deduce the failure rate of the upper-level equipment based on the hierarchical relationship of the structure tree; The importance of the faulty equipment to the nuclear reactor is evaluated based on the failure rate and key performance indicators of the faulty equipment. The weight value of the faulty equipment is configured based on its importance; the higher the importance of the faulty equipment, the greater its weight value.

[0030] In this embodiment, the failure rate of the device at the bottom of the tree structure is obtained. The failure rate of the device at the bottom is usually provided by the component manufacturer or estimated by statistical data. The failure rate of the device at the upper level is inferred based on the hierarchical relationship. The failure rate is the core indicator for measuring the probability of a device failing within a unit of time. It reflects the reliability level of the device. The higher the failure rate, the greater the probability of the device failing within a unit of time and the worse the reliability.

[0031] In a series structure scenario, the upper system can only function normally if all lower-level subsystems are operating correctly; if any one subsystem fails, the upper system will also fail. In this case, the failure rate of the upper system is equal to 1 minus the product of the normal operating probabilities of all lower-level subsystems. For example, if a reactor coolant branch consists of pumps, pipes, and valves connected in series, the failure rate of that branch is 1 minus the failure rate of the pumps multiplied by the failure rate of the pipes multiplied by the failure rate of the valves.

[0032] In a parallel architecture, the upper system can continue operating as long as one lower-level subsystem is functioning normally; the upper system will only fail if all subsystems fail simultaneously. In this case, the failure rate of the upper system is much lower than that of a single subsystem, and the more subsystems connected in parallel, the lower the failure rate of the upper system. For example, when multiple emergency diesel generators are connected in parallel in a reactor, the failure rate of the generator system is significantly lower than that of a single generator.

[0033] In a hybrid series-parallel structure scenario, a nuclear reactor system consists of multiple series modules, with some modules containing parallel redundant subsystems. The derivation approach is to proceed from the local to the global: First, calculate each parallel redundant submodule as an equivalent subsystem and obtain its failure rate; second, calculate the failure rate of the higher-level system by combining all equivalent subsystems and other series subsystems according to the rules of a series structure; and so on, ultimately deriving the failure rate of the top-level system.

[0034] Furthermore, by combining key performance indicators of the equipment, such as mean time between failures (MTBF), mean time to repair (MTTR), failure frequency, and operating efficiency, the importance of the equipment to the overall nuclear reactor is comprehensively evaluated. Specifically, the probability of failure is assessed using the equipment failure rate as the core; a higher failure rate indicates a greater probability of equipment failure per unit time. Simultaneously, indicators derived from the failure rate, such as mean time between failures (MTBF = 1 / failure rate) and failure frequency, can be used to further refine the frequency of failures. The impact of a failure is assessed based on key performance indicators to determine its consequences. For example, a longer mean time to repair (MTTR) indicates a longer system downtime after a failure; lower operating efficiency indicators indicate a more significant weakening of system functionality. The equipment's hierarchical position must also be considered. If the equipment is a core component of its subsystem, or if its subsystem is a critical link in the overall system, a failure will trigger a chain reaction, significantly increasing the scope and severity of its impact.

[0035] The importance of a device is determined by a weighted average of its failure probability and impact. Devices with a high failure probability and significant impact are considered more important to the overall system, while those with a low failure probability and low impact are considered less important. In short, the key is to determine whether a device is prone to failure, then assess the impact of its failure on the system; combining these two factors determines the device's importance to the overall system.

[0036] Then, based on the importance of each level of equipment, a corresponding weight value is assigned to each piece of equipment. These weight values ​​reflect the contribution of each piece of equipment to the overall health of the nuclear reactor. The higher the importance of the faulty equipment, the greater its weight value.

[0037] Step 104: Calculate the health contribution value of the faulty equipment based on its fault impact value and weight value.

[0038] In one embodiment of this application, the health contribution value of the faulty device is calculated based on the fault impact value and weight value of the faulty device, including: Based on the fault impact value and weight value of the faulty equipment, the health contribution value of the faulty equipment is calculated according to the first formula; the first formula is:

[0039] in, Contribution value to health These are weighted values ​​that reflect their importance within the entire nuclear reactor system. The failure impact value reflects the negative impact of the failure on the overall health of the nuclear reactor system. t is the time-related degradation factor, k is the equipment aging coefficient, and t is time.

[0040] In this embodiment, for each device, the impact of its weight value in the structure tree and the fault impact value corresponding to the fault level on the overall health is considered. The health contribution value of a single device can be calculated using the first formula described above.

[0041] Step 105: Sum the health contribution values ​​of all faulty equipment in the nuclear reactor to obtain the health score of the nuclear reactor.

[0042] In this step, the health contribution values ​​of all faulty equipment are summed to obtain the nuclear reactor's health score. The health score can be expressed as:

[0043] in, This indicates the health score of the nuclear reactor.

[0044] Step 106: Determine the health status of the nuclear reactor and the corresponding maintenance strategy based on the health score and health status assessment strategy.

[0045] In this step, based on the health score and the established health status assessment strategy, the health status of the nuclear reactor is determined, and then the maintenance strategy for the nuclear reactor is determined based on the health status.

[0046] In one embodiment of this application, the health status of a nuclear reactor is determined based on a health score and a health status assessment strategy, including: Determine the target range for the health score; Based on the mapping relationship between numerical range and health status, the health status corresponding to the target numerical range is taken as the health status of the nuclear reactor.

[0047] In this embodiment, the health status assessment strategy is to determine the corresponding health status and maintenance decision based on the numerical range of the health score; that is, to predefine the health status and maintenance decision corresponding to different health scores. For example, when If the value is within the range of [0, 0.3], it indicates that the equipment is in very poor health and should be repaired immediately to prevent serious malfunctions. A value within the range (0.3, 0.5) indicates poor equipment health and requires prompt repair to avoid downtime. Within the range of (0.5, 0.7), the equipment's health status is generally good; monitoring should be strengthened and a maintenance plan should be developed. Within the range of (0.7, 0.9), it indicates that the equipment is in good health and should be scheduled for maintenance and monitored. A value within the range of (0.9, 1.0) indicates that the equipment is in excellent health and should be routinely maintained and regularly inspected.

[0048] This application provides a maintenance decision-making method based on the health status of a nuclear reactor. Based on the reactor's operating data and on-site environmental information, it determines the fault level of faulty equipment and its importance to the reactor, resulting in a reactor health score. This method assesses the reactor's health status and makes maintenance decisions, enabling the identification of potential faults and timely, scientific, precise, and automated maintenance decisions. This improves maintenance efficiency, ensures stable long-term equipment operation, and enhances overall reliability and availability. Furthermore, maintenance decisions can avoid over-maintenance, reduce unnecessary repairs, and minimize production losses caused by unplanned downtime.

[0049] In one embodiment of this application, after determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: constructing a field digital twin model of the nuclear reactor, and providing operating data and fault information of each faulty device based on the field digital twin model.

[0050] In this embodiment, a three-dimensional digital twin model of the site is reconstructed based on the plant design drawings and on-site environmental information collected by devices such as visible light cameras and ultrasonic sensors. When a fault is detected, information such as temperature, pressure, and radiation dose is automatically marked on the twin model, and the operator is notified of the fault. The operator can view the fault information such as temperature, flow rate, and pressure of the points that need to be monitored.

[0051] In one embodiment of this application, after determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: generating a maintenance manual, which includes at least one of the following: equipment operating principles, component structure, maintenance procedures, fault code explanations, maintenance steps, parts replacement methods, and safety precautions.

[0052] In this embodiment, a maintenance manual is generated. This manual provides guidance for equipment maintenance, troubleshooting, and repair, including the operating principles of each piece of equipment, component structure, maintenance procedures, fault code explanations, repair steps, parts replacement methods, and necessary safety precautions. When a fault is detected, the maintenance manual is automatically retrieved based on the faulty system or equipment and the fault type. This manual, along with the fault annotations in the on-site 3D digital twin model, is provided to the operator. Simultaneously, considering the system damage that would result from not repairing the fault, and the downtime and economic losses that would result from repairing it, maintenance recommendations are given to maintain the highest overall system operating efficiency.

[0053] In one embodiment of this application, after determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: recording information on the fault diagnosis process and maintenance process of the faulty equipment to form a maintenance case library.

[0054] In this embodiment, a maintenance case library is established. The maintenance cases demonstrate the records of equipment fault diagnosis, maintenance procedures and results through specific examples. All maintenance history during the operation of the nuclear reactor is recorded in the library for the maintenance team to refer to.

[0055] This application provides a maintenance decision-making method based on the health status of a nuclear reactor, aiming to improve the operating efficiency and maintenance quality of nuclear power equipment by establishing a comprehensive management system. The method includes the following key components: First, real-time acquisition of system operating data through a data collection and monitoring system; second, fault diagnosis techniques such as physical field coupling diagnostic models, convolutional neural networks, and image processing algorithms are used to analyze the collected data for fault analysis; third, faults are graded according to equipment characteristics and operating requirements, and their impact values ​​are determined; a health indicator system is then constructed, and the importance of each component or subsystem to the overall system is determined by analyzing its key performance indicators, and corresponding weights are assigned; furthermore, a comprehensive health indicator for the entire equipment is calculated to assess its health status; finally, a three-dimensional digital twin model is established on-site, and after a fault occurs, it is marked in the model to remind operators. Combined with maintenance manuals, maintenance cases, and system operating data, the system damage caused by not repairing the fault, as well as the downtime and economic losses caused by repairing the fault, are calculated to provide maintenance recommendations that maximize the overall operating efficiency of the system. This method enables real-time monitoring and accurate assessment of the health status of nuclear reactors, allowing for the timely detection and handling of potential faults, ensuring stable equipment operation and extending service life. Furthermore, it helps optimize the allocation of maintenance resources, reduce maintenance costs, and improve the overall economic efficiency and safety of nuclear reactors.

[0056] As a specific implementation of the aforementioned nuclear reactor maintenance decision-making method, this application provides a nuclear reactor maintenance decision-making device. For example... Figure 2 As shown, the maintenance decision-making device 200 for the nuclear reactor includes: a data acquisition module 201, a fault diagnosis module 202, an impact value determination module 203, a weight value determination module 204, a health rating module 205, and a maintenance strategy determination module 206.

[0057] Among them, the data acquisition module 201 is used to acquire the operating data of the nuclear reactor and the on-site environmental information; The fault diagnosis module 202 is used to perform fault diagnosis analysis on the acquired operating data and on-site environmental information using fault diagnosis strategies to identify faulty equipment in the nuclear reactor. The impact value determination module 203 is used to determine the fault level of the faulty equipment and the corresponding fault impact value based on the fault judgment index. The weight value determination module 204 is used to determine the importance of faulty equipment to the nuclear reactor based on the nuclear reactor's structure tree, and to configure the weight value of the faulty equipment based on the importance. The health rating module 205 is used to calculate the health contribution value of the faulty equipment based on the fault impact value and weight value of the faulty equipment, and to sum the health contribution values ​​of all faulty equipment in the nuclear reactor to obtain the health rating of the nuclear reactor. The maintenance strategy determination module 206 is used to determine the health status of the nuclear reactor and the corresponding maintenance strategy based on the health score and health status assessment strategy.

[0058] Furthermore, the device also includes: The model building module is used to build a field digital twin model of the nuclear reactor, and provides operational data and fault information of each faulty device based on the field digital twin model.

[0059] Furthermore, the device also includes: The manual generation module is used to generate a maintenance manual, which includes at least one of the following: equipment operating principles, component structure, maintenance procedures, fault code explanations, maintenance steps, parts replacement methods, and safety precautions.

[0060] Furthermore, the device also includes: The case library module is used to record information on the fault diagnosis process and repair process of faulty equipment, forming a maintenance case library.

[0061] Furthermore, the influence value determination module 203 is specifically used for: Based on the operating characteristics of the equipment, determine the fault judgment strategy corresponding to each fault level; Determine the target fault determination strategy that the fault determination indicators of the faulty equipment meet, and use the fault level corresponding to the target fault determination strategy as the fault level of the faulty equipment; wherein, the fault determination indicators include at least one of the following: downtime, repair time, fault impact range, fault frequency, and maintenance cost.

[0062] Furthermore, the weight value determination module 204 is specifically used for: Obtain the failure rate of the lowest-level equipment in the nuclear reactor's structure tree, and deduce the failure rate of the upper-level equipment based on the hierarchical relationship of the structure tree; The importance of the faulty equipment to the nuclear reactor is evaluated based on the failure rate and key performance indicators of the faulty equipment. The weight value of the faulty equipment is configured based on its importance; the higher the importance of the faulty equipment, the greater its weight value.

[0063] Furthermore, the health score module 205 is specifically used for: Based on the fault impact value and weight value of the faulty equipment, the health contribution value of the faulty equipment is calculated according to the first formula; the first formula is:

[0064] in, Contribution value to health For weight values, This represents the impact value of the fault. t is the time-related degradation factor, k is the equipment aging coefficient, and t is time.

[0065] Furthermore, the maintenance strategy determination module 206 is specifically used for: Determine the target range for the health score; Based on the mapping relationship between numerical range and health status, the health status corresponding to the target numerical range is taken as the health status of the nuclear reactor.

[0066] The nuclear reactor maintenance decision-making device 200 in this application embodiment can be a computer device or a component within a computer device, such as an integrated circuit or a chip. The nuclear reactor maintenance decision-making device 200 provided in this application embodiment can achieve... Figure 1 The various processes implemented in the nuclear reactor maintenance decision-making method implementation example will not be described in detail here to avoid repetition.

[0067] This application also provides a computer device, such as... Figure 3 As shown, the computer device 300 includes a processor 301 and a memory 302. The memory 302 stores programs or instructions that can run on the processor 301. When the program or instructions are executed by the processor 301, they implement the various steps of the above-described nuclear reactor maintenance decision-making method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0068] The memory 302 can be used to store software programs and various data. The memory 302 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 302 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 302 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0069] Processor 301 may include one or more processing units; optionally, processor 301 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 301.

[0070] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described nuclear reactor maintenance decision-making method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0071] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0072] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A maintenance decision-making method for a nuclear reactor, characterized in that, include: Acquire nuclear reactor operating data and on-site environmental information, and use fault diagnosis strategies to perform fault diagnosis analysis on the acquired operating data and on-site environmental information to identify faulty equipment in the nuclear reactor; Based on the fault determination indicators, the fault level of the faulty equipment and the corresponding fault impact value are determined. Based on the nuclear reactor's structure tree, the importance of faulty equipment to the nuclear reactor is determined, and the weight value of the faulty equipment is configured based on the importance. Calculate the health contribution value of the faulty equipment based on its fault impact value and weight value. The health contribution values ​​of all faulty equipment in the nuclear reactor are summed to obtain the health score of the nuclear reactor; The health status of the nuclear reactor and the corresponding maintenance strategy are determined based on health scores and health status assessment strategies.

2. The method according to claim 1, characterized in that, After determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: Construct a field digital twin model of the nuclear reactor, and provide operational data and fault information for each faulty device based on the field digital twin model.

3. The method according to claim 1, characterized in that, After determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: Generate a maintenance manual, which includes at least one of the following: equipment operating principles, component structure, maintenance procedures, fault code explanations, maintenance steps, parts replacement methods, and safety precautions; After determining the maintenance strategy based on the health status of the nuclear reactor, the method further includes: Record information on the fault diagnosis and repair process of faulty equipment to form a maintenance case library.

4. The method according to claim 1, characterized in that, Based on fault diagnosis indicators, the fault level of the faulty equipment and the corresponding fault impact value are determined, including: Based on the operating characteristics of the equipment, determine the fault judgment strategy corresponding to each fault level; Determine the target fault determination strategy that the fault determination indicators of the faulty equipment meet, and use the fault level corresponding to the target fault determination strategy as the fault level of the faulty equipment; wherein, the fault determination indicators include at least one of the following: downtime, repair time, fault impact range, fault frequency, and maintenance cost.

5. The method according to claim 1, characterized in that, Based on the nuclear reactor's structure tree, the importance of faulty equipment to the nuclear reactor is determined, and weight values ​​for the faulty equipment are assigned based on this importance, including: Obtain the failure rate of the lowest-level equipment in the nuclear reactor's structure tree, and deduce the failure rate of the upper-level equipment based on the hierarchical relationship of the structure tree; The importance of the faulty equipment to the nuclear reactor is evaluated based on the failure rate and key performance indicators of the faulty equipment. The weight value of the faulty equipment is configured based on its importance; the higher the importance of the faulty equipment, the greater its weight value.

6. The method according to claim 1, characterized in that, Based on the failure impact value and weight value of the faulty equipment, calculate the health contribution value of the faulty equipment, including: Based on the fault impact value and weight value of the faulty equipment, the health contribution value of the faulty equipment is calculated according to the first formula; the first formula is: in, Contribution value to health For weight values, This represents the impact value of the fault. t is the time-related degradation factor, k is the equipment aging coefficient, and t is time.

7. The method according to claim 1, characterized in that, The health status of a nuclear reactor is determined based on health scoring and health status assessment strategies, including: Determine the target range for the health score; Based on the mapping relationship between numerical range and health status, the health status corresponding to the target numerical range is taken as the health status of the nuclear reactor.

8. A maintenance decision-making device for a nuclear reactor, characterized in that, include: The data acquisition module is used to acquire the nuclear reactor's operating data and on-site environmental information; The fault diagnosis module is used to perform fault diagnosis analysis on the acquired operating data and on-site environmental information using fault diagnosis strategies to identify faulty equipment in the nuclear reactor. The impact value determination module is used to determine the fault level of the faulty equipment and the corresponding fault impact value based on the fault judgment index. The weight value determination module is used to determine the importance of faulty equipment to the nuclear reactor based on the nuclear reactor's structure tree, and to configure the weight value of the faulty equipment based on the importance. The health rating module is used to calculate the health contribution value of the faulty equipment based on the fault impact value and weight value of the faulty equipment, and to sum the health contribution values ​​of all faulty equipment in the nuclear reactor to obtain the health rating of the nuclear reactor. The maintenance strategy determination module is used to determine the health status of the nuclear reactor and the corresponding maintenance strategy based on the health score and health status assessment strategy.

9. A computer device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that run on the processor, the program or instructions being executed by the processor to implement the steps of the maintenance decision method for a nuclear reactor as described in any one of claims 1 to 7.

10. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps of the maintenance decision-making method for a nuclear reactor as described in any one of claims 1 to 7.

Images