Operation and maintenance strategy generation system and method, electronic equipment, storage medium and product

Abstract

The invention discloses an operation and maintenance strategy generation system and method, electronic equipment, a storage medium and a product. The system comprises a data acquisition device, a data processing device, a data analysis device and an operation and maintenance management device, wherein the data acquisition device is used for acquiring nuclear power plant big data; the data processing equipment is used for processing nuclear power plant big data; the data analysis equipment is used for analyzing the processed data to obtain an analysis result, and the analysis result comprises nuclear power plant fault prediction information, nuclear power plant operation state prediction information and nuclear power plant operation and maintenance decision optimization information; the operation and maintenance management device is used for generating an operation and maintenance strategy according to the analysis result. The system analyzes the processed data to obtain the nuclear power station fault prediction information, the nuclear power station operation state prediction information and the nuclear power station operation decision optimization information, and the operation strategy is generated according to the information, so that the accuracy of the operation strategy can be effectively improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data processing technology, and in particular to an operation and maintenance strategy generation system, method, electronic device, storage medium, and product. Background Art

[0002] A nuclear power plant uses nuclear reactors to generate electricity. The heat released by nuclear fission reactions heats water to create steam, which drives generators to generate electricity. The operation of a nuclear power plant carries high risks and therefore requires highly sophisticated monitoring and management.

[0003] The data analysis process of the existing nuclear power plant operation and maintenance system is relatively simple, which leads to reduced accuracy of operation and maintenance decisions and a decline in the operation and maintenance quality of nuclear power plants. Summary of the Invention

[0004] The present invention provides an operation and maintenance strategy generation system, method, electronic device, storage medium and product to solve the problem that the data analysis process of the existing nuclear power plant operation and maintenance system is relatively simple, resulting in reduced accuracy of operation and maintenance decisions.

[0005] According to one aspect of the present invention, there is provided an operation and maintenance strategy generation system, comprising a data acquisition device, a data processing device, a data analysis device, and an operation and maintenance management device, wherein the data processing device is connected to the data acquisition device and the data analysis device respectively, and the data analysis device is also connected to the operation and maintenance management device;

[0006] The data acquisition equipment is used to obtain big data of nuclear power plants;

[0007] The data processing equipment is used to process the big data of the nuclear power plant;

[0008] The data analysis device is used to analyze the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information;

[0009] The operation and maintenance management device is used to generate an operation and maintenance strategy based on the analysis result.

[0010] According to another aspect of the present invention, a method for generating an operation and maintenance strategy is provided, comprising:

[0011] Obtaining big data from nuclear power plants;

[0012] Processing the nuclear power plant big data;

[0013] Analyzing the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information;

[0014] An operation and maintenance strategy is generated based on the analysis results.

[0015] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising: at least one processor;

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

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the operation and maintenance strategy generation method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the operation and maintenance strategy generation method described in any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the operation and maintenance strategy generation method according to any embodiment of the present invention is implemented.

[0020] The technical solution of the embodiment of the present invention obtains nuclear power plant fault prediction information, nuclear power plant operating status prediction information and nuclear power plant operation and maintenance decision optimization information by analyzing the processed data, thereby obtaining more comprehensive analysis results, solving the problem that the data analysis process of the existing nuclear power plant operation and maintenance system is relatively simple, resulting in reduced accuracy of operation and maintenance decisions, and achieving the beneficial effect of effectively improving the accuracy of operation and maintenance strategies.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of the structure of an operation and maintenance strategy generation system provided in Example 1 of the present invention;

[0024] Figure 2A schematic diagram of the structure of an operation and maintenance strategy generation system provided in the second embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of an operation and maintenance strategy generation system provided in the third embodiment of the present invention;

[0026] Figure 4 A flowchart of a method for generating an operation and maintenance strategy provided in the fourth embodiment of the present invention;

[0027] Figure 5 A schematic diagram of the structure of an electronic device generated by an operation and maintenance strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention. It should be understood that the various steps described in the method implementation mode of the present invention can be performed in different orders and / or in parallel. In addition, the method implementation mode may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0029] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] Example 1

[0034] Figure 1 This is a structural diagram of an operation and maintenance strategy generation system provided in Example 1 of the present invention. The operation and maintenance strategy generation system can be applied to the operation and maintenance of nuclear power plants, wherein the operation and maintenance strategy generation system can be implemented by software. The system is generally integrated on electronic equipment, and the electronic equipment may include computer equipment.

[0035] like Figure 1 As shown, an operation and maintenance strategy generation system provided by the first embodiment of the present invention includes a data acquisition device 110, a data processing device 120, a data analysis device 130, and an operation and maintenance management device 140. The data processing device 120 is connected to the data acquisition device 110 and the data analysis device 130 respectively, and the data analysis device 130 is also connected to the operation and maintenance management device 140.

[0036] Data acquisition equipment 110, used to obtain big data of nuclear power plants;

[0037] Data processing equipment 120, used for processing the nuclear power plant big data;

[0038] Data analysis equipment 130, used to analyze the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information;

[0039] The operation and maintenance management device 140 is configured to generate an operation and maintenance strategy based on the analysis result.

[0040] In this embodiment, the data acquisition device 110 can be used to acquire and store data from various sensor devices, monitoring devices, and external data source devices in the nuclear power plant.

[0041] In this embodiment, the data processing device 120 is connected to the data acquisition device 110 to obtain big data of the nuclear power plant and perform cleaning, filtering and standardization processing on the big data of the nuclear power plant.

[0042] In this embodiment, the data analysis device 130 is connected to the data processing device 120 to obtain processed data, analyze the processed data, and identify patterns, trends, and anomalies in the data.

[0043] Among them, the data analysis device 130 can be used to perform fault prediction analysis on the processed data to obtain nuclear power plant fault prediction information; the data analysis device 130 can also be used to predict the operating status of the nuclear power plant on the processed data to obtain nuclear power plant operating status prediction information; the data analysis device 130 can also be used to optimize the nuclear power plant operation and maintenance decision-making based on the processed data to obtain nuclear power plant operation and maintenance decision-making optimization information.

[0044] In this embodiment, the operation and maintenance management device 140 is connected to the data analysis device 130 to obtain analysis results and generate an operation and maintenance strategy based on the analysis results.

[0045] A first embodiment of the present invention provides an operation and maintenance strategy generation system. First, a data acquisition device acquires nuclear power plant big data. A data processing device then processes the nuclear power plant big data. A data analysis device then analyzes the processed data to obtain analysis results, including nuclear power plant failure prediction information, nuclear power plant operating status prediction information, and nuclear power plant operation and maintenance decision optimization information. Finally, an operation and maintenance management device generates an operation and maintenance strategy based on the analysis results. The system analyzes the processed data to obtain nuclear power plant failure prediction information, nuclear power plant operating status prediction information, and nuclear power plant operation and maintenance decision optimization information. Generating an operation and maintenance strategy based on this information can effectively improve the accuracy of the operation and maintenance strategy.

[0046] Example 2

[0047] Figure 2 This is a schematic diagram of the structure of an operation and maintenance strategy generation system provided by the second embodiment of the present invention. This second embodiment is optimized based on the above embodiments. For details not yet fully described in this embodiment, please refer to the first embodiment.

[0048] In this embodiment, the data acquisition device 110 includes a sensor data acquisition module 111, a monitoring data acquisition module 112, an external data acquisition module 113 and a storage module 114;

[0049] The sensor data acquisition module 111 is used to obtain sensor data collected by sensor equipment in the nuclear power plant;

[0050] The monitoring data acquisition module 112 is used to obtain monitoring data collected by monitoring equipment in the nuclear power plant;

[0051] The external data acquisition module 113 is used to acquire external data collected by an external data source device;

[0052] The storage module 114 is used to establish a central database and store the sensor data, the monitoring data and the external data in the central database.

[0053] The sensing device may be a sensor, and the sensing device may include a temperature sensor, a pressure sensor, a humidity sensor, a light sensor, a motion sensor, a proximity sensor, a gas sensor, and a sound sensor.

[0054] Among them, monitoring equipment may include cameras, recording equipment, video auxiliary equipment, audio monitoring equipment, environmental detection equipment, network and data monitoring equipment, and positioning and tracking equipment.

[0055] The external data collected by the external data source device may include meteorological data and power grid data.

[0056] Furthermore, the data analysis device 130 includes a fault prediction module 131 , an operation status prediction module 132 , and an operation and maintenance decision optimization module 133 ;

[0057] A fault prediction module 131 is configured to perform nuclear power plant fault prediction based on the analysis results and generate nuclear power plant fault prediction information;

[0058] An operating state prediction module 132 is configured to predict the operating state of the nuclear power plant based on the analysis results and generate nuclear power plant operating state prediction information;

[0059] The operation and maintenance decision optimization module 133 is used to optimize the operation and maintenance decision of the nuclear power plant according to the analysis results and generate nuclear power plant operation and maintenance decision optimization information.

[0060] It is understandable that during the operation of a nuclear power plant, equipment failure may lead to serious consequences, so accurate failure prediction is crucial to ensuring the safety of the nuclear power plant.

[0061] Furthermore, the fault prediction module 131 includes a prediction submodule 1311 and a generation submodule 1312. The prediction submodule 1311 is used to process the analysis results at different time scales through a multi-layer Bayesian network model to predict the failure probability of equipment in the nuclear power plant; the generation submodule 1312 is used to generate nuclear power plant failure prediction information based on the failure probability.

[0062] Among them, the Bayesian network is a commonly used probability model that predicts the probability of a specific event by constructing conditional dependencies between random variables.

[0063] In this embodiment, by introducing multiple time layers, the time-varying characteristics of sensor data, monitoring data, and external data can be more accurately captured. For complex nuclear power plant systems, data at different time scales, such as second-level vibration data, minute-level temperature data, and hour-level pressure data, have different implications for nuclear power plant failure prediction. Using a multi-layer Bayesian network model, data can be analyzed at different time scales, integrating data from different layers to improve prediction accuracy.

[0064] Furthermore, the corresponding formula of the prediction submodule is as follows:

[0065]

[0066] Among them, P(F i |D) represents the failure probability of the i-th device in the nuclear power plant, Represents the data set from the 1st level to the Lth level, α l Represents the weight coefficient of the first level, P(D 1,l ,D 2,l ,…,D n,l |F i ) represents the overall conditional probability when the i-th device fails, Z l represents the normalization constant, n represents the total number of conditional probabilities, P(F i ) represents the prior probability of the i-th device.

[0067] Among them, P(F i |D) can be understood as the probability of failure of the i-th device in the nuclear power plant after given different levels of data D; Represents a data set of all levels. For example, when the i-th device is a cooling pump, it is assumed that there are three levels: second-level data, minute-level data, and hour-level data. The first level contains the vibration data D of the cooling pump in the past few seconds. 1,1 and D 2,1 , the second level contains the temperature data D in the past few minutes 2,1 , the third level contains the pressure data D in the past few hours 1,3 ; α l It can be set based on experience or historical data; P(D 1,l ,D 2,l ,…,D n,l |F i ) is the product of the conditional probabilities of the various features of the i-th device when a fault occurs, that is, the possibility of observing data at a specific level, reflecting the typical characteristics of the data at each level when a fault occurs in the tested device.

[0068] in, It is used to normalize the probability of each level of data so that the sum of these probabilities is equal to 1, and n represents the total number of conditional probabilities; P(F i ) represents the prior probability of the i-th device, that is, the historical probability of the i-th device failing, which can be calculated using the following formula:

[0069]

[0070] In the above formula, T1 and T2 represent the number of failures and the total operating time, respectively. For example, the cooling pump has experienced three failures in the past 8760 hours, and the prior probability is approximately 0.00034.

[0071] It should be noted that when the i-th device is a device such as a communication device or a high-power device related to meteorological data or power grid data, a time hierarchy including data related to an external data source may also be introduced.

[0072] Furthermore, the prediction submodule 1311 also includes an analysis unit, which is used to analyze the overall conditional probability when the i-th device fails; the analysis unit is specifically used to: collect historical operation data of the i-th device; stratify the historical operation data according to the time scale to obtain data at each level, and the data at each level includes second-level data, minute-level data and hour-level data; analyze the distribution of the data at each level when a failure occurs; calculate the conditional probability of the data at each level when a failure occurs based on the distribution; calculate the product of the conditional probabilities of the data at each level when a failure occurs to obtain the overall conditional probability when the i-th device fails.

[0073] Among them, the overall conditional probability P(D 1,l ,D 2,l ,…,D n,l |F i ) needs to be obtained through historical data analysis. The specific steps are as follows:

[0074] Step 1: Collect historical operation data, including ten or more equipment failure records of the i-th equipment and data collected by the sensing equipment and monitoring equipment when each failure occurs.

[0075] For example, the i-th device is a cooling pump in a nuclear power plant. Every time the cooling pump fails, vibration, temperature, and pressure data are collected through sensing equipment and monitoring equipment.

[0076] Step 2: Data stratification and preprocessing: stratify historical operation data according to time scale.

[0077] Step 3: Statistical analysis to calculate the distribution of data at each level when the fault occurs.

[0078] The data at each level may include second-level data, minute-level data, and hour-level data. The second-level data may be calculated by analyzing vibration data to determine the probability of the vibration acceleration exceeding a vibration acceleration threshold within 10 seconds before a fault occurs. The minute-level data may be calculated by analyzing temperature data to determine the probability of the temperature exceeding a temperature threshold within 10 minutes before a fault occurs. The hour-level data may be calculated by analyzing pressure data to determine the probability of the pressure fluctuation amplitude exceeding a pressure fluctuation threshold within 3 hours before a fault occurs.

[0079] Step 4: Output the conditional probability. Based on the results of the statistical analysis, calculate the conditional probability of each data point at each level when a fault occurs.

[0080] For example, within 10 seconds before the fault occurs, the vibration acceleration of the i-th device exceeds the vibration acceleration threshold 80% of the time, that is, P(D 1,1 |F i )=0.8, which represents the conditional probability of the second-level data appearing when a fault occurs; within 10 minutes before the fault occurs, the temperature rise of the i-th device exceeds the temperature threshold 60% of the time, that is, P(D 1,2 |F i )=0.6, this value can represent the conditional probability of minute-level hierarchical data when a fault occurs; within 3 hours before the fault occurs, the pressure fluctuation amplitude of the i-th device exceeds the pressure fluctuation threshold 40% of the time, that is, P(D 1,3 |F i )=0.4, this value can represent the conditional probability of hourly level data occurring when a failure occurs.

[0081] Step 5: Calculate the overall conditional probability by multiplying the conditional probabilities of each feature of the ith device when the fault occurs to obtain the overall conditional probability of the ith device. For example, if the conditional probability that the vibration acceleration of the ith device exceeds the vibration acceleration threshold within 10 seconds before the fault occurs is P(D 1,1 |F i )=0.8, within 10 minutes before the fault occurs, the conditional probability that the temperature of the i-th device exceeds the temperature threshold is P(D 1,2 |F i )=0.6, within 3 hours before the failure occurs, the conditional probability that the pressure fluctuation amplitude of the i-th device exceeds the pressure fluctuation threshold is P(D 1,3 |F i )=0.4, then the overall conditional probability of the i-th device is P(D 1,l ,D 2,l ,…,D n,l |F i )=P(D 1,1 |Fi )×P(D 1,2 |F i )×P(D 1,3 |F i )=0.192.

[0082] Among them, when P(F i |D)≥p ref When the generation submodule 1312 is used to generate nuclear power plant failure prediction information that the nuclear power plant failure risk exceeds the standard and requires immediate inspection by operation and maintenance personnel, p ref Indicates the fault prediction threshold.

[0083] Furthermore, the operating status prediction module 132 is used to: input the analysis results into the trained deep learning neural network model, output the nuclear power plant operating status probability; and generate operating status prediction analysis information based on the nuclear power plant operating status probability.

[0084] Specifically, the operating status prediction module 132 includes a construction submodule, a calculation submodule, an update submodule, a prediction submodule, and a generation submodule.

[0085] Among them, the construction submodule is used to build a deep learning neural network model based on sensor data, monitoring data and external data; the calculation submodule is used to calculate the loss function during the model training process; the update submodule is used to update the learning rate and model parameters during the model training process; the construction submodule is also used to iterate according to the updated learning rate and model parameters during the training process until the loss function value converges to the minimum value; the prediction submodule is used to output the operating status probability according to the current new input data after the model training is completed; the generation submodule is used to generate corresponding operating status prediction and analysis information based on the operating status probability.

[0086] A deep learning neural network is a machine learning model that captures complex data features through multiple layers of nonlinear transformations. In nuclear power plant operation monitoring, this neural network is used to analyze large-scale, multi-dimensional data to discover underlying patterns and predict the future operating status of the system. Dynamic adaptive learning rate automatically adjusts the learning rate of each layer during deep learning neural network training according to the progress of training, allowing for more efficient model optimization.

[0087] Specifically, when the calculation submodule works, the following formula is satisfied:

[0088]

[0089] Among them, L lost Represents the loss function of the entire deep learning neural network, which represents the difference between the predicted value and the true value. The training goal of the neural network is to minimize the loss function, thereby improving the prediction accuracy of the model; βl Represents the loss weight of the lth layer. In the neural network structure, different layers have different effects on the final output, so different weights need to be set for each layer; Represents the gradient of the loss function of the lth layer; Represents the gradient norm of the loss function of the lth layer, using the conventional mathematical L2 norm, which is the square root of the sum of squares, Calculated by a computer program based on the loss function; Represents the sum of the gradient norms of all layers and is used for normalization.

[0090] Among them, y i The true label value of the i-th sample is generally a binary value. For example, the true label value indicates whether the corresponding equipment has substandard operating conditions under certain conditions. If so, the true label value is 1; if not, the true label value is 0. Assume that the trained model is used to predict the operating status of the cooling pump. First, extract the following samples from the data of the past year:

[0091] Sample 1: In January of the past year, the cooling pump operated normally under high-pressure conditions, and the operating status met the standards. The true label value y1 was 0. Sample 2: In May of the past year, the cooling pump operated substandardly under long-term high-temperature conditions. The true label value y2 was 1. Sample 3: In July of the past year, the cooling pump operated standard despite abnormal vibration conditions. The true label value y3 was 0.

[0092] Among them, Y i,l It represents the predicted output value of the i-th sample in the l-th layer, which is obtained by the deep learning neural network model through forward propagation calculation based on the input features of the i-th sample.

[0093] Specifically, when updating the submodule, the following formula is satisfied:

[0094]

[0095] in, represents the model parameters of the lth layer after the t+1th iteration. The model parameters may include the current, voltage, temperature, speed and pressure of the corresponding equipment in the nuclear power plant under different operating conditions; represents the learning rate of layer l at the tth iteration; represents the model parameters of the lth layer at the tth iteration; Represents the gradient of the loss function of the lth layer at the tth iteration. The loss function corresponding to the gradient is based on Model parameter implementation; represents the initial learning rate; λ represents the learning rate attenuation parameter; γ represents the attenuation nonlinearity parameter.

[0096] Specifically, the generation submodule performs the following steps to generate the nuclear power plant operation status prediction information:

[0097] Step 1: Data collection and preprocessing.

[0098] A large amount of real-time data is collected from various sensors on the generator set, including current, voltage, temperature, and speed. To improve the performance of the model, this data is first standardized to ensure that the distribution of data with different characteristics is consistent.

[0099] Step 2: Model construction.

[0100] Build a deep learning neural network with multiple hidden layers. The number of neurons and activation function in each layer are set based on the complexity of the data and the requirements of the task. Assume that three hidden layers are used, each corresponding to a different feature combination of current, voltage, temperature, and speed.

[0101] Step 3: Loss function setting.

[0102] During the model training process, a loss function is defined to measure the difference between the model prediction results and the actual fault status.

[0103] Step 4: Adaptive learning rate adjustment.

[0104] During model training, a larger initial learning rate is set at the beginning to facilitate rapid convergence. In the early stages of training, the model's parameters are updated with a large amplitude, which can quickly reduce the value of the loss function. As training progresses, the learning rate gradually decays, allowing the model to make more detailed adjustments as it approaches the optimal solution.

[0105] Step 5: Parameter update and model optimization.

[0106] In each iteration, the current gradient is calculated, the model parameters are adjusted according to the adaptive learning rate, and the iteration is repeated until the loss function value of the model converges to a stable minimum.

[0107] Step 6: Generate model prediction and operation status prediction analysis information.

[0108] After model training is complete, new data is input into the model, which then outputs the probability of the corresponding device's operating status meeting or failing the standard. Based on the probability values, the corresponding operating status prediction and analysis information is generated.

[0109] A second embodiment of the present invention provides an operation and maintenance strategy generation system that improves the accuracy and timeliness of the data analysis process through data cleaning, filtering, and standardization. The independent collection of sensor data, monitoring data, and external data facilitates improving the accuracy and stability of the data collection process, thereby improving the accuracy and stability of the system operation and maintenance plan. Nuclear power plant fault prediction is performed using sensor data, monitoring data, and external data to generate nuclear power plant fault prediction information, thereby improving the accuracy of the fault prediction information. Nuclear power plant operating status prediction is performed using sensor data, monitoring data, and external data to generate nuclear power plant operating status prediction information, thereby improving the accuracy of nuclear power plant operating status prediction information and thereby improving the accuracy of nuclear power plant operation and maintenance decision optimization information. Conventional operation and maintenance decision adjustment and information response adjustment functions are used to further enrich the system's operation and maintenance processes and modes, making the operation and maintenance process more accurate and complete. A multi-layer Bayesian network is used to calculate equipment failure probabilities based on sensor data, monitoring data, and external data, thereby improving the accuracy of nuclear power plant fault prediction information. The accuracy of nuclear power plant operating status prediction information is improved by improving the accuracy of loss functions and learning rate updates, thereby significantly improving the system's operation and maintenance quality for nuclear power plants.

[0110] Example 3

[0111] Figure 3 This is a schematic diagram of the structure of an operation and maintenance strategy generation system provided by the third embodiment of the present invention. This third embodiment is optimized based on the above embodiments. For details not yet fully described in this embodiment, please refer to the first and second embodiments.

[0112] In this embodiment, the operation and maintenance decision optimization module 133 includes a calculation submodule 1331, an allocation submodule 1332 and a generation submodule 1333. The calculation submodule 1331 is used to calculate the information entropy of each operation and maintenance project indicator of the nuclear power plant based on the analysis results; the allocation submodule 1332 is used to assign weights to each operation and maintenance project based on the information entropy; and the generation submodule 1333 is used to generate nuclear power plant operation and maintenance decision optimization information based on the weight allocation results.

[0113] Specifically, when the calculation submodule 1331 is working, the following formula is satisfied:

[0114]

[0115] In the above formula, μ ij represents the fuzzy membership of the i-th sample under the j-th operation and maintenance project indicator. The value of the fuzzy membership is between 0 and 1. The closer it is to 1, the closer the sample is to the ideal state. k1 represents the sensitivity parameter. The higher the sensitivity parameter, the more drastic the change of the fuzzy membership. i,jrepresents the actual value of the i-th sample under the j-th operation and maintenance project indicator, such as the actual maintenance cost or failure rate of the corresponding equipment in a nuclear power plant; c j H represents the fuzzy central value, that is, the ideal value of the j-th operation and maintenance project indicator. For example, the ideal value of maintenance cost is the historical lowest value of maintenance cost, and the ideal value of failure probability can be 0. j The information entropy of the jth operation and maintenance project indicator reflects the dispersion and uncertainty of the indicator. The higher the information entropy, the greater the volatility of the indicator and the more complex the impact on the operation and maintenance decision. k2 represents a constant, which is generally set to n represents the total number of samples.

[0116] Specifically, the allocation submodule 1332 satisfies the following formula:

[0117]

[0118] Among them, w j It represents the weight of the jth operation and maintenance project, which is used to determine the relative importance of the operation and maintenance project indicators in the operation and maintenance decision-making. The lower the information entropy, the more stable the indicator is and the greater its impact on the result. m represents the total number of operation and maintenance project indicators. When the operation and maintenance project indicators only consider failure rate, maintenance cost and downtime, the value of m is 3.

[0119] It should be noted that if the final weight distribution after comparing the weights shows that the failure rate is the most critical indicator, followed by maintenance costs and downtime, then the optimization information for the nuclear power plant operation and maintenance decision is: the operation and maintenance team can give priority to measures to reduce the failure rate and maintenance costs. For example, in the maintenance plan, more resources can be invested in preventing failures of key equipment, while trying to control costs and shorten downtime.

[0120] Furthermore, the system further includes an interactive device 150, which is connected to the operation and maintenance management device 140.

[0121] Interactive device 150, used for visually displaying the operation and maintenance strategy and the operating status of the nuclear power plant;

[0122] The interactive device 150 is also used to receive user instructions.

[0123] The interactive device 150 is used to provide a visual data display and operation interface, so that the operation and maintenance personnel can input user instructions on the operation interface. The operation and maintenance personnel can also view the operating status and operation and maintenance strategy of the nuclear power plant on the interactive device 150.

[0124] Furthermore, the operation and maintenance management device 140 includes a storage module 141, a first adjustment module 142, a second adjustment module 143, a third adjustment module 144 and a fourth adjustment module 145; the storage module 141 is used to store preset operation and maintenance decisions; the first adjustment module 142 is used to obtain user instructions from the interactive device and adjust the preset operation and maintenance decisions according to the user instructions; the second adjustment module 143 is used to adjust the preset operation and maintenance decisions according to the nuclear power plant fault prediction information; the third adjustment module 144 is used to adjust the preset operation and maintenance decisions according to the nuclear power plant operation status prediction information; the fourth adjustment module 145 is used to adjust the preset operation and maintenance decisions according to the nuclear power plant operation and maintenance decision optimization information.

[0125] A third embodiment of the present invention provides an operation and maintenance strategy generation system, in which the operation and maintenance decision optimization module 133 uses an information entropy calculation algorithm to calculate the information entropy of each operation and maintenance project indicator of the nuclear power plant based on sensor data, monitoring data and external data, which is conducive to improving the accuracy of the nuclear power plant operation and maintenance decision optimization information, thereby further improving the operation and maintenance quality of the nuclear power plant production system; enriching the operation and maintenance mode through automatic management of operation and maintenance decisions and human-computer interaction management is conducive to improving the accuracy of the system operation and maintenance plan, so that operation and maintenance personnel can view the operating status and operation and maintenance plan of the nuclear power plant in real time.

[0126] Example 4

[0127] Figure 4 This is a flow chart of a method for generating an operation and maintenance strategy provided in a fourth embodiment of the present invention. This method is applicable to the operation and maintenance of a nuclear power plant. This method can be executed by the operation and maintenance strategy generation system provided in any of the above embodiments. This system can be implemented by software. The method includes the following steps:

[0128] S110. Obtain big data of nuclear power plants.

[0129] Among them, nuclear power plant big data can include sensor data, monitoring data and external data.

[0130] In this embodiment, the sensing data may be collected by sensors in the nuclear power plant, the monitoring data may be collected by health equipment in the nuclear power plant, and the external data may be collected by external data source equipment.

[0131] In this embodiment, a central database may also be established to store the sensor data, monitoring data, and external data in the central database.

[0132] S120: Process the nuclear power plant big data.

[0133] Among them, sensor data, monitoring data and external data can be cleaned, filtered and standardized.

[0134] S130 , analyzing the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information.

[0135] Among them, the processed data can be used for fault prediction analysis to obtain nuclear power plant fault prediction information; it can also be used to predict the operating status of the nuclear power plant based on the processed data to obtain nuclear power plant operating status prediction information; it can also be used to optimize the operation and maintenance decision-making of the nuclear power plant based on the processed data to obtain nuclear power plant operation and maintenance decision-making optimization information.

[0136] S140: Generate an operation and maintenance strategy according to the analysis result.

[0137] Among them, the preset operation and maintenance strategy is optimized according to the analysis results to generate the final operation and maintenance strategy.

[0138] This embodiment provides a method for generating an operation and maintenance strategy. First, nuclear power plant big data is acquired; then, the big data is processed; the processed data is analyzed to obtain analysis results, including nuclear power plant failure prediction information, nuclear power plant operating status prediction information, and nuclear power plant operation and maintenance decision optimization information; and finally, an operation and maintenance strategy is generated based on the analysis results. This method can effectively improve the accuracy of the operation and maintenance strategy.

[0139] Furthermore, the processed data is analyzed to obtain analysis results, including: predicting nuclear power plant failures based on the analysis results to generate nuclear power plant failure prediction information; predicting the operating status of the nuclear power plant based on the analysis results to generate nuclear power plant operating status prediction information; and optimizing nuclear power plant operation and maintenance decisions based on the analysis results to generate nuclear power plant operation and maintenance decision optimization information.

[0140] Based on the above optimization, nuclear power plant failure prediction is performed according to the analysis results to generate nuclear power plant failure prediction information, including: processing the analysis results at different time scales through a multi-layer Bayesian network model to predict the failure probability of equipment in the nuclear power plant; and generating nuclear power plant failure prediction information according to the failure probability.

[0141] Based on the above technical solution, the corresponding formula of the Bayesian network model is as follows:

[0142]

[0143] Among them, P(F i |D) represents the failure probability of the i-th device in the nuclear power plant, Represents the data set from the 1st level to the Lth level, α l Represents the weight coefficient of the first level, P(D1,l ,D 2,l ,…,D n,l |F i ) represents the overall conditional probability when the i-th device fails, Z l represents the normalization constant, n represents the total number of conditional probabilities, P(F i ) represents the prior probability of the i-th device.

[0144] Furthermore, the analysis process of the overall conditional probability when the i-th device fails includes: collecting historical operating data of the i-th device; stratifying the historical operating data according to the time scale to obtain data at each level, and the data at each level includes second-level data, minute-level data and hour-level data; analyzing the distribution of the data at each level when a failure occurs; calculating the conditional probability of the data at each level when a failure occurs based on the distribution; calculating the product of the conditional probabilities of the data at each level when a failure occurs to obtain the overall conditional probability when the i-th device fails.

[0145] Furthermore, predicting the operating status of a nuclear power plant based on the analysis results and generating nuclear power plant operating status prediction information includes: inputting the analysis results into a trained deep learning neural network model to output the operating status probability of the nuclear power plant; and generating nuclear power plant operating status prediction information based on the operating status probability of the nuclear power plant.

[0146] Furthermore, the nuclear power plant operation and maintenance decision optimization is performed based on the analysis results to generate nuclear power plant operation and maintenance decision optimization information, including: calculating the information entropy of each operation and maintenance project indicator of the nuclear power plant based on the analysis results; allocating weights to each operation and maintenance project based on the information entropy; and generating nuclear power plant operation and maintenance decision optimization information based on the weight allocation results.

[0147] Furthermore, the method also includes visually displaying the operation and maintenance strategy and the operating status of the nuclear power plant; and receiving user instructions.

[0148] Furthermore, generating an operation and maintenance strategy based on the analysis results includes: obtaining a preset operation and maintenance strategy; obtaining a user instruction from an interactive device, and adjusting the preset operation and maintenance decision according to the user instruction; adjusting the preset operation and maintenance decision according to nuclear power plant fault prediction information; adjusting the preset operation and maintenance decision according to nuclear power plant operating status prediction information; and adjusting the preset operation and maintenance decision according to nuclear power plant operation and maintenance decision optimization information.

[0149] The above-mentioned operation and maintenance strategy generation device can execute the operation and maintenance strategy generation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0150] Example 5

[0151] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0152] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0153] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0154] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for generating an operation and maintenance strategy.

[0155] In some embodiments, an operation and maintenance strategy generation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps in the operation and maintenance strategy generation method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute an operation and maintenance strategy generation method in any other appropriate manner (for example, by means of firmware).

[0156] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] In some embodiments, the operation and maintenance strategy generation method can be implemented as a computer program, which is invisibly included in a computer program product. The computer program implements the operation and maintenance strategy generation method of the present invention when executed by a processor. The computer program product can be understood as a software product that mainly implements its solution through a computer program. The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device so that the functions / operations specified in the flowchart and / or block diagram are implemented when the computer program is executed by the processor. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as an independent software package and partially on a remote machine, or entirely on a remote machine or server.

[0158] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0159] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0160] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0161] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0162] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0163] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. An operation and maintenance strategy generation system, characterized in that: The system includes a data acquisition device, a data processing device, a data analysis device and an operation and maintenance management device, wherein the data processing device is connected to the data acquisition device and the data analysis device respectively, and the data analysis device is also connected to the operation and maintenance management device; The data acquisition equipment is used to obtain big data of nuclear power plants; The data processing equipment is used to process the big data of the nuclear power plant; The data analysis device is used to analyze the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information; The operation and maintenance management device is used to generate an operation and maintenance strategy based on the analysis result.

2. The system according to claim 1, wherein: The data acquisition device includes a sensing data acquisition module, a monitoring data acquisition module, an external data acquisition module and a storage module; The sensor data acquisition module is used to obtain sensor data collected by sensor equipment in the nuclear power plant; The monitoring data acquisition module is used to obtain monitoring data collected by monitoring equipment in the nuclear power plant; The external data acquisition module is used to acquire external data collected by an external data source device; The storage module is used to establish a central database and store the sensor data, the monitoring data and the external data in the central database.

3. The system according to claim 1, wherein: The data analysis device includes a fault prediction module, an operation status prediction module and an operation and maintenance decision optimization module; The fault prediction module is used to predict nuclear power plant faults based on the analysis results and generate nuclear power plant fault prediction information; The operation status prediction module is used to predict the operation status of the nuclear power plant according to the analysis results and generate nuclear power plant operation status prediction information; The operation and maintenance decision optimization module is used to optimize the operation and maintenance decision of the nuclear power plant according to the analysis results and generate nuclear power plant operation and maintenance decision optimization information.

4. The system according to claim 3, characterized in that The fault prediction module includes a prediction submodule and a generation submodule. The prediction submodule is used to process the analysis results at different time scales through a multi-layer Bayesian network model to predict the failure probability of equipment in the nuclear power plant; The generating submodule is used to generate nuclear power plant failure prediction information according to the failure probability.

5. The system according to claim 4, characterized in that The corresponding formula of the prediction submodule is as follows: Among them, P(F i |D) represents the failure probability of the i-th device in the nuclear power plant, Represents the data set from the 1st level to the Lth level, α l Represents the weight coefficient of the first level, P(D 1,l ,D 2,l ,…,D n,l |F i ) represents the overall conditional probability when the i-th device fails, Z l represents the normalization constant, n represents the total number of conditional probabilities, P(F i ) represents the prior probability of the i-th device.

6. The system according to claim 5, characterized in that The prediction submodule further includes an analysis unit, which is used to analyze the overall conditional probability of the i-th device failing; The analysis unit is specifically used to: collect historical operating data of the i-th device; stratify the historical operating data according to the time scale to obtain data at each level, and the data at each level includes second-level data, minute-level data and hour-level data; analyze the distribution of the data at each level when a fault occurs; calculate the conditional probability of the data at each level occurring when a fault occurs based on the distribution; calculate the product of the conditional probabilities of the data at each level occurring when a fault occurs to obtain the overall conditional probability of the i-th device failing.

7. The system according to claim 3, wherein: The operating status prediction module is used to: input the analysis results into a trained deep learning neural network model, output the nuclear power plant operating status probability; and generate nuclear power plant operating status prediction information based on the nuclear power plant operating status probability.

8. The system according to claim 3, wherein: The operation and maintenance decision optimization module includes a calculation submodule, an allocation submodule and a generation submodule. The calculation submodule is used to calculate the information entropy of each operation and maintenance project indicator of the nuclear power plant according to the analysis results; The allocation submodule is used to allocate weights to each operation and maintenance project according to the information entropy; The generation submodule is used to generate nuclear power plant operation and maintenance decision optimization information based on the weight distribution result.

9. The system according to claim 1, wherein: The system further includes an interactive device, which is connected to the operation and maintenance management device. The interactive device is used to visually display the operation and maintenance strategy and the operating status of the nuclear power plant; The interactive device is also used to receive user instructions.

10. The system according to claim 1, wherein: The operation and maintenance management device includes a storage module, a first adjustment module, a second adjustment module, a third adjustment module and a fourth adjustment module; The storage module is used to store preset operation and maintenance decisions; The first adjustment module is configured to obtain a user instruction from an interactive device and adjust the preset operation and maintenance decision according to the user instruction; The second adjustment module is used to adjust the preset operation and maintenance decision according to the nuclear power plant fault prediction information; The third adjustment module is used to adjust the preset operation and maintenance decision according to the nuclear power plant operation status prediction information; The fourth adjustment module is used to adjust the preset operation and maintenance decision according to the nuclear power plant operation and maintenance decision optimization information.

11. A method for generating an operation and maintenance strategy, characterized in that: The method comprises: Obtaining big data from nuclear power plants; Processing the nuclear power plant big data; Analyzing the processed data to obtain analysis results, wherein the analysis results include nuclear power plant failure prediction information, nuclear power plant operation status prediction information, and nuclear power plant operation and maintenance decision optimization information; An operation and maintenance strategy is generated based on the analysis results.

12. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the operation and maintenance strategy generation method described in claim 11.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the operation and maintenance strategy generation method according to claim 11 when executed.

14. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the operation and maintenance strategy generating method according to claim 11.

Images