Pumped storage equipment maintenance strategy evaluation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a pumped storage equipment maintenance strategy evaluation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that the pumped storage equipment to be overhauled is overhauled according to an overhauling strategy, and multiple pieces of index data after the pumped storage equipment to be overhauled is overhauled are obtained; screening out key index data from the multiple pieces of index data; performing feature extraction processing on the key index data to obtain feature vectors corresponding to the key index data; respectively inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model; screening out a target maintenance strategy evaluation model from each maintenance strategy evaluation model; and carrying out fusion processing on the strategy evaluation result of the maintenance strategy output by each target maintenance strategy evaluation model to obtain a target strategy evaluation result of the maintenance strategy. By adopting the method, the maintenance strategy evaluation accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for evaluating maintenance strategy of pumped storage equipment. Background Art

[0002] In order to maintain pumped storage equipment and ensure its stable operation, it is necessary to conduct regular maintenance on pumped storage equipment through maintenance strategies and evaluate the actual effect of the implementation of maintenance strategies.

[0003] In traditional technology, when evaluating the actual effect of the implementation of maintenance strategies, it is generally done through manual evaluation; however, the manual evaluation method is prone to subjectivity, resulting in a low evaluation accuracy of the maintenance strategy of pumped storage equipment. Summary of the invention

[0004] Based on this, it is necessary to provide a pumped-storage equipment maintenance strategy evaluation method, device, computer equipment, computer-readable storage medium and computer program product that can improve the evaluation accuracy of pumped-storage equipment maintenance strategy in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for evaluating a maintenance strategy for a pumped storage equipment, comprising:

[0006] According to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data of the pumped-storage equipment to be repaired after the repair;

[0007] Filtering out key indicator data from the multiple indicator data;

[0008] Performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data;

[0009] Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, obtaining a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result;

[0010] From each of the maintenance strategy evaluation models, select a target maintenance strategy evaluation model whose output strategy evaluation result of the maintenance strategy corresponds to a predicted probability greater than a preset probability;

[0011] According to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0012] In one embodiment, the step of filtering out key indicator data from the plurality of indicator data includes:

[0013] Input each indicator data into a pre-trained first importance prediction model to obtain the first importance corresponding to each indicator data;

[0014] Input each indicator data into a pre-trained second importance prediction model to obtain the second importance corresponding to each indicator data;

[0015] The first importance and the second importance corresponding to each indicator data are respectively fused to obtain the target importance corresponding to each indicator data;

[0016] From each of the indicator data, the indicator data whose corresponding target importance is greater than the preset importance is screened out as the key indicator data.

[0017] In one embodiment, the step of performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data includes:

[0018] Identify the data type of the key indicator data;

[0019] According to the data type of the key indicator data, query the corresponding relationship between the data type and the feature extraction model to obtain the feature extraction model corresponding to the key indicator data;

[0020] Inputting the key indicator data into a corresponding feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the key indicator data;

[0021] Performing feature extraction processing on the first feature vector again to obtain a second feature vector corresponding to the key indicator data;

[0022] The first feature vector and the second feature vector are fused to obtain a feature vector of the key indicator data.

[0023] In one embodiment, the feature vectors are respectively input into a plurality of pre-trained maintenance strategy evaluation models to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result, including:

[0024] Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, and obtaining the predicted probability of the maintenance strategy under various preset evaluation results output by each maintenance strategy evaluation model;

[0025] Correcting the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results to obtain a corrected predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results;

[0026] From the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, the preset evaluation result with the largest corrected prediction probability is screened out as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model.

[0027] In one embodiment, each pre-trained maintenance strategy evaluation model is trained in the following manner:

[0028] According to the sample maintenance strategy of the sample pumped-storage equipment, the sample pumped-storage equipment is maintained to obtain a plurality of sample indicator data after the maintenance of the sample pumped-storage equipment;

[0029] Filtering out key sample indicator data from the plurality of sample indicator data;

[0030] Performing feature extraction processing on the key sample indicator data to obtain a sample feature vector corresponding to the key sample indicator data;

[0031] Inputting the sample feature vector into the maintenance strategy evaluation model to be trained to obtain a prediction strategy evaluation result of the sample maintenance strategy;

[0032] The actual strategy evaluation result of the sample maintenance strategy is obtained, and according to the difference between the predicted strategy evaluation result and the actual strategy evaluation result of the sample maintenance strategy, the maintenance strategy evaluation model to be trained is iteratively trained to obtain the pre-trained maintenance strategy evaluation model.

[0033] In one embodiment, after fusing the strategy evaluation results output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy, the method further includes:

[0034] According to the target strategy evaluation result, query the corresponding relationship between the strategy evaluation result and the strategy evaluation level to obtain the strategy evaluation level corresponding to the target strategy evaluation result;

[0035] Obtaining a policy update instruction corresponding to the policy evaluation level;

[0036] According to the strategy update instruction, the maintenance strategy is updated to obtain an updated maintenance strategy.

[0037] In a second aspect, the present application also provides a pumped storage equipment maintenance strategy evaluation device, comprising:

[0038] A data acquisition module, used to perform maintenance on the pumped-storage equipment to be maintained according to the maintenance strategy of the pumped-storage equipment to be maintained, and obtain a plurality of index data of the pumped-storage equipment to be maintained after maintenance;

[0039] A data screening module, used to screen out key indicator data from the plurality of indicator data;

[0040] A feature extraction module is used to perform feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data;

[0041] A strategy evaluation module, used to input the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result;

[0042] A model screening module, used to screen out, from each of the maintenance strategy evaluation models, a target maintenance strategy evaluation model whose predicted probability corresponding to the strategy evaluation result of the maintenance strategy outputted is greater than a preset probability;

[0043] The result determination module is used to fuse the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy.

[0044] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0045] According to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data of the pumped-storage equipment to be repaired after the repair;

[0046] Filtering out key indicator data from the multiple indicator data;

[0047] Performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data;

[0048] Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, obtaining a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result;

[0049] From each of the maintenance strategy evaluation models, select a target maintenance strategy evaluation model whose output strategy evaluation result of the maintenance strategy corresponds to a predicted probability greater than a preset probability;

[0050] According to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0052] According to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data of the pumped-storage equipment to be repaired after the repair;

[0053] Filtering out key indicator data from the multiple indicator data;

[0054] Performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data;

[0055] Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, obtaining a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result;

[0056] From each of the maintenance strategy evaluation models, select a target maintenance strategy evaluation model whose output strategy evaluation result of the maintenance strategy corresponds to a predicted probability greater than a preset probability;

[0057] According to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0058] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0059] According to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data of the pumped-storage equipment to be repaired after the repair;

[0060] Filtering out key indicator data from the multiple indicator data;

[0061] Performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data;

[0062] Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, obtaining a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result;

[0063] From each of the maintenance strategy evaluation models, select a target maintenance strategy evaluation model whose output strategy evaluation result of the maintenance strategy corresponds to a predicted probability greater than a preset probability;

[0064] According to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0065] The above-mentioned pumped-storage equipment maintenance strategy evaluation method, device, computer equipment, computer-readable storage medium and computer program product first perform maintenance on the pumped-storage equipment to be maintained according to the maintenance strategy of the pumped-storage equipment to be maintained, and obtain multiple indicator data of the pumped-storage equipment to be maintained after maintenance, then screen out key indicator data from the multiple indicator data, and perform feature extraction processing on the key indicator data to obtain feature vectors corresponding to the key indicator data, and then input the feature vectors into multiple pre-trained maintenance strategy evaluation models respectively to obtain the strategy evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, and the prediction probability corresponding to the strategy evaluation results, and from each maintenance strategy evaluation model, screen out a target maintenance strategy evaluation model whose prediction probability corresponding to the strategy evaluation result of the output maintenance strategy is greater than the preset probability, and finally, according to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation result of the maintenance strategy. In this way, the key indicator data of the pumped-storage equipment to be maintained after maintenance and multiple pre-trained maintenance strategy evaluation models are comprehensively considered, and the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused according to the model weight of each target maintenance strategy evaluation model. This can make the final target strategy evaluation result more accurate, thereby improving the evaluation accuracy of the maintenance strategy of the pumped-storage equipment, and avoiding the defect of low evaluation accuracy of the maintenance strategy of the pumped-storage equipment due to manual evaluation of the maintenance strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of a flow chart of a method for evaluating a maintenance strategy for pumped storage equipment in one embodiment;

[0068] Figure 2 A flowchart of the steps of screening out key indicator data in one embodiment;

[0069] Figure 3 A schematic flow chart of a method for evaluating a maintenance strategy for pumped storage equipment in another embodiment;

[0070] Figure 4 It is a structural block diagram of a pumped storage equipment maintenance strategy evaluation device in one embodiment;

[0071] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0074] Figure 1 is a flow chart of a method for evaluating a maintenance strategy for a pumped storage device according to an exemplary embodiment. Figure 1As shown, the pumped storage equipment maintenance strategy evaluation method is applied to the server; it is understandable that the method can also be applied to the terminal, and can also be applied to the system including the terminal and the server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but not limited to various personal computers, laptops, smart phones and tablets; the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. In this exemplary embodiment, the method includes the following steps S101 to S106. Among them:

[0075] Step S101, according to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data after the repair of the pumped-storage equipment to be repaired.

[0076] Among them, the pumped-storage equipment to be repaired refers to the pumped-storage equipment that needs to be repaired.

[0077] Among them, the maintenance strategy refers to the strategy for maintaining the pumped storage equipment to be overhauled, which specifically includes maintenance type, maintenance items, maintenance time, maintenance cycle, maintenance requirements, etc.

[0078] Among them, the index data after the maintenance of the pumped storage equipment to be repaired refers to the index data related to the pumped storage equipment to be repaired, which is collected after the maintenance of the pumped storage equipment to be repaired using the maintenance strategy of the pumped storage equipment to be repaired, and is used to measure the actual effect of the implementation of the maintenance strategy, including reliability indicators, maintenance costs, equipment status, accident events, etc. Reliability indicators include equivalent availability coefficient, forced outage rate, unit start-up success rate, unplanned outage time, etc.; maintenance costs include asset maintenance fees of 10,000 yuan, average maintenance fees of a single unit for many years, etc.; equipment status includes operating status, performance indicators, health adjustment information, etc.; accident events include accident event level, number of accident events, etc.

[0079] Exemplarily, the server generates a maintenance instruction for the pumped-storage equipment to be repaired according to the maintenance strategy of the pumped-storage equipment to be repaired, controls the maintenance equipment to repair the pumped-storage equipment to be repaired according to the maintenance instruction of the pumped-storage equipment to be repaired, and collects multiple indicator data of the pumped-storage equipment to be repaired after the maintenance.

[0080] For example, the server sends a maintenance instruction of the pumped-storage equipment to be repaired to the maintenance equipment. The maintenance equipment repairs the pumped-storage equipment according to the maintenance instruction, and after the maintenance of the pumped-storage equipment is completed, collects multiple indicator data of the pumped-storage equipment after maintenance, and sends the multiple indicator data to the server.

[0081] Step S102: Filter out key indicator data from multiple indicator data.

[0082] Among them, key indicator data refers to indicator data whose corresponding importance is greater than a preset importance, specifically referring to some important indicator data.

[0083] Exemplarily, the server inputs each indicator data into a pre-trained importance prediction model (such as a neural network model, a deep learning model, etc.) to obtain the importance corresponding to each indicator data; from multiple indicator data, the server selects the indicator data whose corresponding importance is greater than the preset importance as the key indicator data.

[0084] Step S103: perform feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data.

[0085] Among them, the feature vector is used to represent the characteristic information of key indicator data.

[0086] Exemplarily, the server preprocesses the key indicator data to obtain preprocessed key indicator data, and inputs the preprocessed key indicator data into a pre-trained feature extraction model for feature extraction processing to obtain a feature vector as a feature vector corresponding to the key indicator data.

[0087] Step S104, respectively inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result.

[0088] Among them, the maintenance strategy evaluation model is a model used to output the strategy evaluation results of the maintenance strategy and its predicted probability, such as a large language model, a neural network model, a deep learning model, etc.

[0089] Among them, different pre-trained maintenance strategy evaluation models are obtained through different model training. For example, maintenance strategy evaluation model A is obtained through large language model training, maintenance strategy evaluation model B is obtained through neural network model training, and maintenance strategy evaluation model C is obtained through deep learning model training.

[0090] Among them, the strategy evaluation result refers to the predicted evaluation result of the maintenance strategy, such as evaluation score, evaluation level, etc.

[0091] Among them, the predicted probability is used to measure the possibility corresponding to the strategy evaluation result, such as 0.7, 0.8, etc.

[0092] Exemplarily, the server inputs the feature vectors into multiple pre-trained maintenance strategy evaluation models respectively, performs predictive processing on the feature vectors through each maintenance strategy evaluation model, and obtains the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; respectively, from the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, the preset evaluation result with the largest predicted probability is screened out as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and the predicted probability corresponding to the preset evaluation result with the largest predicted probability is used as the predicted probability corresponding to the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model.

[0093] For example, assuming that the predicted probabilities of the maintenance strategies output by the maintenance strategy evaluation model under the preset evaluation results a, b, and c are 0.5, 0.3, and 0.2 respectively, then the strategy evaluation result of the maintenance strategy output by the maintenance strategy evaluation model is the preset evaluation result a, and the predicted probability corresponding to the strategy evaluation result is 0.5.

[0094] Step S105 , selecting a target maintenance strategy evaluation model whose output maintenance strategy evaluation result corresponds to a predicted probability greater than a preset probability from each maintenance strategy evaluation model.

[0095] The preset probability refers to a pre-set probability value, such as 0.5, 0.6, etc.

[0096] Among them, the target maintenance strategy evaluation model refers to a maintenance strategy evaluation model in which the predicted probability corresponding to the strategy evaluation result of the output maintenance strategy is greater than the preset probability.

[0097] Exemplarily, the server selects, from each maintenance strategy evaluation model, a maintenance strategy evaluation model whose output strategy evaluation result of the maintenance strategy corresponds to a predicted probability greater than a preset probability, as the target maintenance strategy evaluation model.

[0098] For example, assuming that the predicted probability corresponding to the strategy evaluation result a of the maintenance strategy output by the maintenance strategy evaluation model A is 0.9, the predicted probability corresponding to the strategy evaluation result b of the maintenance strategy output by the maintenance strategy evaluation model B is 0.8, the predicted probability corresponding to the strategy evaluation result b of the maintenance strategy output by the maintenance strategy evaluation model C is 0.5, the predicted probability corresponding to the strategy evaluation result a of the maintenance strategy output by the maintenance strategy evaluation model D is 0.7, and the preset probability is 0.6, then the screened target maintenance strategy evaluation models are maintenance strategy evaluation model A, maintenance strategy evaluation model B and maintenance strategy evaluation model D.

[0099] Step S106, according to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0100] Among them, the model weight is used to measure the importance of the strategy evaluation result of the maintenance strategy output by the target maintenance strategy evaluation model, such as 0.7, 0.6, etc., which is specifically determined according to the prediction accuracy of the target maintenance strategy evaluation model.

[0101] The fusion processing refers to the weighted summation processing.

[0102] Among them, the target strategy evaluation result refers to the final strategy evaluation result, such as evaluation score, evaluation level, etc., which is used to measure the actual effect of maintenance strategy implementation, so as to facilitate the subsequent iterative improvement of maintenance strategy. For example, the actual effect of maintenance strategy implementation is evaluated by reliability index, maintenance cost, equipment status, etc., reliability improvement is carried out, and maintenance strategy is iteratively improved.

[0103] Exemplarily, the server queries the correspondence between the prediction accuracy and the model weight according to the prediction accuracy of each target maintenance strategy evaluation model, and obtains the model weight of each target maintenance strategy evaluation model; then, according to the model weight of each target maintenance strategy evaluation model, the server fuses the policy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model to obtain a fused evaluation result as the target strategy evaluation result of the maintenance strategy.

[0104] For example, assuming that the target maintenance strategy evaluation models are maintenance strategy evaluation model A, maintenance strategy evaluation model B and maintenance strategy evaluation model D, and the corresponding model weights are A1, B1, and D1 respectively, then the target strategy evaluation result of the maintenance strategy = the strategy evaluation result of the maintenance strategy output by maintenance strategy evaluation model A × A1 + the strategy evaluation result of the maintenance strategy output by maintenance strategy evaluation model B × B1 + the strategy evaluation result of the maintenance strategy output by maintenance strategy evaluation model D × D1.

[0105] In the above-mentioned pumped-storage equipment maintenance strategy evaluation method, the pumped-storage equipment to be repaired is first repaired according to the maintenance strategy of the pumped-storage equipment to be repaired, and a plurality of indicator data of the pumped-storage equipment to be repaired after the repair is obtained. Then, the key indicator data are screened out from the plurality of indicator data, and feature extraction processing is performed on the key indicator data to obtain feature vectors corresponding to the key indicator data. Then, the feature vectors are respectively input into a plurality of pre-trained maintenance strategy evaluation models to obtain the strategy evaluation results of the maintenance strategies output by each maintenance strategy evaluation model, and the prediction probability corresponding to the strategy evaluation results are obtained. Then, from each maintenance strategy evaluation model, a target maintenance strategy evaluation model whose prediction probability corresponding to the strategy evaluation results of the output maintenance strategies is greater than the preset probability is screened out. Finally, according to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategies output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategies. In this way, the key indicator data of the pumped-storage equipment to be maintained after maintenance and multiple pre-trained maintenance strategy evaluation models are comprehensively considered, and the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused according to the model weight of each target maintenance strategy evaluation model. This can make the final target strategy evaluation result more accurate, thereby improving the evaluation accuracy of the maintenance strategy of the pumped-storage equipment, and avoiding the defect of low evaluation accuracy of the maintenance strategy of the pumped-storage equipment due to manual evaluation of the maintenance strategy.

[0106] In an exemplary embodiment, Figure 2 As shown, the above step S102, screening out key indicator data from multiple indicator data, specifically includes the following steps S201 to S204. Among them:

[0107] Step S201 , input each indicator data into a pre-trained first importance prediction model to obtain the first importance corresponding to each indicator data.

[0108] Step S202 , input each indicator data into a pre-trained second importance prediction model to obtain the second importance corresponding to each indicator data.

[0109] Step S203 , fusing the first importance and the second importance corresponding to each indicator data respectively to obtain the target importance corresponding to each indicator data.

[0110] Step S204: Filter out, from each indicator data, the indicator data whose corresponding target importance is greater than the preset importance as the key indicator data.

[0111] Among them, the first importance, the second importance and the target importance are all used to measure the importance of the indicator data. The preset importance is a pre-set importance, such as 0.6.

[0112] Among them, the first importance prediction model is used to output the first importance corresponding to the indicator data, and can specifically be a neural network model, a deep learning model, etc. The second importance prediction model is used to output the second importance corresponding to the indicator data, and can specifically be a neural network model, a deep learning model, etc. It should be noted that the first importance prediction model and the second importance prediction model refer to different importance prediction models, for example, the first importance prediction model is a neural network model, and the second importance prediction model is a deep learning model.

[0113] Among them, key indicator data refers to indicator data whose corresponding target importance is greater than the preset importance.

[0114] Exemplarily, the server inputs each indicator data into a pre-trained first importance prediction model for importance prediction to obtain the first importance corresponding to each indicator data; inputs each indicator data into a pre-trained second importance prediction model for importance prediction to obtain the second importance corresponding to each indicator data; then fuses the first importance and the second importance corresponding to each indicator data to obtain the fused importance corresponding to each indicator data as the target importance corresponding to each indicator data, such as target importance = first importance + second importance, or target importance = first importance × weight of first importance + second importance × weight of second importance; finally, from each indicator data, filter out the indicator data whose corresponding target importance is greater than the preset importance as the key indicator data.

[0115] In this embodiment, key indicator data are screened out from multiple indicator data, which is conducive to accurately predicting the strategy evaluation results of the maintenance strategy based on the key indicator data, avoiding the influence of redundant data on the strategy evaluation results, thereby improving the evaluation accuracy of the pumped storage equipment maintenance strategy.

[0116] In an exemplary embodiment, the above step S103 performs feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data, which specifically includes the following contents: identifying the data type of the key indicator data; according to the data type of the key indicator data, querying the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the key indicator data; inputting the key indicator data into the corresponding feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the key indicator data; performing feature extraction processing on the first feature vector again to obtain a second feature vector corresponding to the key indicator data; fusing the first feature vector and the second feature vector to obtain the feature vector of the key indicator data.

[0117] Among them, different key indicator data correspond to different data types.

[0118] Among them, the feature extraction model can refer to a convolutional neural network model, a deep learning model, etc.

[0119] Among them, the first eigenvector refers to the eigenvector corresponding to the shallow features of the key indicator data; the second eigenvector refers to the eigenvector corresponding to the deep features of the key indicator data.

[0120] The characteristic vector of the key indicator data is obtained by fusing the first characteristic vector and the second characteristic vector.

[0121] Exemplarily, the server identifies the data type of the key indicator data according to the data type identification instruction; according to the data type of the key indicator data, queries the correspondence between the data type and the feature extraction model, obtains the feature extraction model corresponding to the data type of the key indicator data, and uses it as the feature extraction model corresponding to the key indicator data; then, the key indicator data is input into the corresponding feature extraction model for feature extraction processing, and a first feature vector corresponding to the key indicator data is obtained; the first feature vector is subjected to feature extraction processing again through the feature extraction model, and a second feature vector corresponding to the key indicator data is obtained; finally, the first feature vector and the second feature vector are fused to obtain a fused feature vector, which is used as the feature vector of the key indicator data.

[0122] In this embodiment, the feature extraction model corresponding to the key indicator data is first determined, and then the key indicator data is input into the corresponding feature extraction model for multiple feature extraction processes, which is beneficial to improving the accuracy of determining the feature vector of the key indicator data.

[0123] In an exemplary embodiment, the above step S104, respectively inputs the feature vector into a plurality of pre-trained maintenance strategy evaluation models to obtain the strategy evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, and the prediction probability corresponding to the strategy evaluation result, specifically includes the following contents: respectively inputs the feature vector into a plurality of pre-trained maintenance strategy evaluation models to obtain the prediction probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; corrects the prediction probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results to obtain the corrected prediction probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; respectively, from the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, screens out the preset evaluation result with the largest corrected prediction probability as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model.

[0124] Among them, the preset evaluation result may refer to the preset evaluation score a, the preset evaluation score b, the preset evaluation score c, etc., or may refer to the preset evaluation level X1, the preset evaluation level X2, the preset evaluation level X3, the preset evaluation level X4, etc.

[0125] Among them, each maintenance strategy evaluation model can output the predicted probability of the maintenance strategy under various preset evaluation results, such as (0.1, 0.2, 0.3, 0.4), which respectively represent the predicted probability of the maintenance strategy under the preset evaluation level X1, the preset evaluation level X2, the preset evaluation level X3, and the preset evaluation level X4.

[0126] Among them, the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results is corrected, mainly to adjust the predicted probability to avoid the output predicted probability deviating too much from the actual situation, such as adjusting the predicted probability (0.01, 0.02, 0.97) to (0.1, 0.1, 0.8).

[0127] Exemplarily, the server inputs the feature vectors into multiple pre-trained maintenance strategy evaluation models respectively, and performs predictive processing on the feature vectors through each maintenance strategy evaluation model to obtain the predicted probabilities of the maintenance strategies output by each maintenance strategy evaluation model under various preset evaluation results; then, the predicted probabilities of the maintenance strategies output by each maintenance strategy evaluation model under various preset evaluation results are corrected through a pre-trained probability correction model (such as a deep learning model) to obtain the corrected predicted probabilities of the maintenance strategies output by each maintenance strategy evaluation model under various preset evaluation results; finally, the preset evaluation results with the largest corrected predicted probabilities are screened out from the various preset evaluation results of the maintenance strategies output by each maintenance strategy evaluation model as the strategy evaluation results of the maintenance strategies output by each maintenance strategy evaluation model, and the corrected predicted probabilities corresponding to the preset evaluation results with the largest corrected predicted probabilities are used as the predicted probabilities corresponding to the strategy evaluation results of the maintenance strategies output by each maintenance strategy evaluation model.

[0128] For example, assuming that the predicted probabilities of the maintenance strategy output by a maintenance strategy evaluation model under the preset evaluation results a, b, and c are 0.01, 0.02, and 0.97 respectively. After correction, the predicted probabilities of the maintenance strategy output by the maintenance strategy evaluation model under the preset evaluation results a, b, and c are 0.1, 0.1, and 0.8 respectively. Then the strategy evaluation result of the maintenance strategy output by the maintenance strategy evaluation model is the preset evaluation result c, and the predicted probability corresponding to the strategy evaluation result (i.e., the preset evaluation result c) is 0.8.

[0129] In this embodiment, each maintenance strategy evaluation model outputs the predicted probability of the maintenance strategy under various preset evaluation results, and the predicted probability is corrected. Based on the corrected predicted probability, the strategy evaluation result and predicted probability of the maintenance strategy output by each maintenance strategy evaluation model are determined, which is beneficial to improving the accuracy of the strategy evaluation results and predicted probability of the maintenance strategy output by each maintenance strategy evaluation model, and further improves the accuracy of the target strategy evaluation result finally obtained.

[0130] In an exemplary embodiment, the pumped-storage equipment maintenance strategy evaluation method provided by the present application also includes a training step of a maintenance strategy evaluation model, which specifically includes the following contents: according to the sample maintenance strategy of the sample pumped-storage equipment, the sample pumped-storage equipment is maintained to obtain a plurality of sample indicator data of the sample pumped-storage equipment after maintenance; from the plurality of sample indicator data, key sample indicator data are screened out; feature extraction processing is performed on the key sample indicator data to obtain a sample feature vector corresponding to the key sample indicator data; the sample feature vector is input into the maintenance strategy evaluation model to be trained to obtain a predicted strategy evaluation result of the sample maintenance strategy; the actual strategy evaluation result of the sample maintenance strategy is obtained, and according to the difference between the predicted strategy evaluation result and the actual strategy evaluation result of the sample maintenance strategy, the maintenance strategy evaluation model to be trained is iteratively trained to obtain a pre-trained maintenance strategy evaluation model.

[0131] Among them, the maintenance strategy evaluation model to be trained can refer to a large language model, a neural network model, a deep learning model, etc.

[0132] Among them, each pre-trained maintenance strategy evaluation model is trained separately.

[0133] Exemplarily, the server generates a sample maintenance instruction for the sample pumped-storage equipment according to the sample maintenance strategy of the sample pumped-storage equipment, and controls the maintenance equipment to perform maintenance on the sample pumped-storage equipment according to the sample maintenance instruction of the sample pumped-storage equipment, and collects a plurality of sample indicator data after the maintenance of the sample pumped-storage equipment; then, each sample indicator data is respectively input into a pre-trained importance prediction model to obtain the importance corresponding to each sample indicator data; from the plurality of sample indicator data, the sample indicator data whose corresponding importance is greater than the preset importance is screened out as the key sample indicator data; then, the key sample indicator data is pre-processed to obtain the pre-processed key sample indicator data, and the pre-processed key sample indicator data is input into the pre-trained importance prediction model. Feature extraction processing is performed in the feature extraction model to obtain a feature vector as the sample feature vector corresponding to the key sample indicator data; then, the sample feature vector is input into the maintenance strategy evaluation model to be trained to obtain the predicted strategy evaluation result of the sample maintenance strategy; finally, the actual strategy evaluation result of the sample maintenance strategy is obtained, and the loss value is calculated according to the difference between the predicted strategy evaluation result and the actual strategy evaluation result of the sample maintenance strategy, and according to the loss value, the maintenance strategy evaluation model to be trained is iteratively trained until the loss value obtained according to the predicted strategy evaluation result output by the trained maintenance strategy evaluation model is less than the preset threshold, then the training is stopped, and the trained maintenance strategy evaluation model is used as the pre-trained maintenance strategy evaluation model.

[0134] In this embodiment, by iteratively training the maintenance strategy evaluation model to be trained, the accuracy of the strategy evaluation results output by the maintenance strategy evaluation model can be improved, thereby improving the accuracy of the final target strategy evaluation results, and further improving the evaluation accuracy of the pumped-storage equipment maintenance strategy.

[0135] In an exemplary embodiment, the above-mentioned step S106, after fusing the strategy evaluation results output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy, also includes the following contents: according to the target strategy evaluation result, querying the correspondence between the strategy evaluation result and the strategy evaluation level to obtain the strategy evaluation level corresponding to the target strategy evaluation result; obtaining the strategy update instruction corresponding to the strategy evaluation level; according to the strategy update instruction, updating the maintenance strategy to obtain the updated maintenance strategy.

[0136] Among them, the strategy evaluation level can refer to high, medium, low, or can also refer to the first level, second level, third level, fourth level, etc.

[0137] Among them, different strategy evaluation levels correspond to different strategy update instructions.

[0138] Among them, the strategy update instruction is mainly used to update the maintenance strategy, such as iteratively improving the maintenance strategy to update the maintenance type, maintenance item, maintenance time, maintenance cycle, maintenance requirements, etc. in the maintenance strategy.

[0139] Exemplarily, the server queries the correspondence between the policy evaluation result and the policy evaluation level based on the target policy evaluation result, and obtains the policy evaluation level corresponding to the target policy evaluation result; then, based on the policy evaluation level, the server queries the correspondence between the policy evaluation level and the policy update instruction, and obtains the policy update instruction corresponding to the policy evaluation level; finally, based on the policy update instruction, the server performs a series of update processing on the maintenance policy to obtain the updated maintenance strategy.

[0140] For example, the server improves reliability from design improvement, manufacturing improvement, maintenance improvement and other aspects according to the maintenance evaluation results (such as the target strategy evaluation results), and improves the maintenance strategy by optimizing the maintenance process and decision-making methods, including the continuous optimization of maintenance types, maintenance items, maintenance cycles and maintenance requirements.

[0141] In this embodiment, the corresponding strategy update instruction is determined according to the strategy evaluation level corresponding to the target strategy evaluation result, and the maintenance strategy is updated according to the strategy update instruction, which is conducive to achieving the purpose of updating the maintenance strategy, making the updated maintenance strategy more in line with the corresponding pumped storage equipment, thereby improving the implementation effect of the maintenance strategy.

[0142] In an exemplary embodiment, Figure 3 As shown, another method for evaluating the maintenance strategy of pumped storage equipment is provided, which is described by taking the method applied to a server as an example, and includes the following steps S301 to S312. Among them:

[0143] Step S301, according to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of indicator data after the repair of the pumped-storage equipment to be repaired.

[0144] Step S302, input each indicator data into the pre-trained first importance prediction model respectively to obtain the first importance corresponding to each indicator data; input each indicator data into the pre-trained second importance prediction model respectively to obtain the second importance corresponding to each indicator data.

[0145] Step S303, respectively fuse the first importance and the second importance corresponding to each indicator data to obtain the target importance corresponding to each indicator data; from each indicator data, filter out the indicator data whose corresponding target importance is greater than the preset importance as the key indicator data.

[0146] Step S304, identifying the data type of the key indicator data; according to the data type of the key indicator data, querying the corresponding relationship between the data type and the feature extraction model, and obtaining the feature extraction model corresponding to the key indicator data.

[0147] Step S305, inputting the key indicator data into the corresponding feature extraction model to perform feature extraction processing to obtain a first feature vector corresponding to the key indicator data; performing feature extraction processing on the first feature vector again to obtain a second feature vector corresponding to the key indicator data.

[0148] Step S306: fusing the first eigenvector and the second eigenvector to obtain a eigenvector of the key indicator data.

[0149] Step S307, respectively inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models to obtain the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results.

[0150] Step S308, correcting the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results, and obtaining the corrected predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results.

[0151] Step S309, respectively, from the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, select the preset evaluation result with the largest corrected prediction probability as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and obtain the prediction probability corresponding to the strategy evaluation result.

[0152] Step S310, from each maintenance strategy evaluation model, select a target maintenance strategy evaluation model whose output maintenance strategy evaluation result corresponds to a predicted probability greater than a preset probability.

[0153] Step S311, according to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

[0154] Step S312, based on the target policy evaluation result, query the correspondence between the policy evaluation result and the policy evaluation level to obtain the policy evaluation level corresponding to the target policy evaluation result; obtain the policy update instruction corresponding to the policy evaluation level; according to the policy update instruction, update the maintenance strategy to obtain the updated maintenance strategy.

[0155] In the above-mentioned pumped-storage equipment maintenance strategy evaluation method, the key indicator data of the pumped-storage equipment to be maintained after maintenance and multiple pre-trained maintenance strategy evaluation models are comprehensively considered, and the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused according to the model weight of each target maintenance strategy evaluation model. This can make the final target strategy evaluation result more accurate, thereby improving the evaluation accuracy of the pumped-storage equipment maintenance strategy, and at the same time avoiding the defect of low evaluation accuracy of the pumped-storage equipment maintenance strategy due to manual evaluation of the maintenance strategy.

[0156] In an exemplary embodiment, in order to more clearly illustrate the pumped storage equipment maintenance strategy evaluation method provided by the embodiment of the present application, the pumped storage equipment maintenance strategy evaluation method is specifically described below with a specific embodiment. In an exemplary embodiment, the present application also proposes another pumped storage equipment maintenance strategy evaluation method, which uses reliability indicators to evaluate the actual effect of the maintenance strategy implementation and iteratively improves the maintenance strategy, specifically including the following contents:

[0157] (1) Perform maintenance on the pumped storage equipment to be maintained according to the maintenance strategy, and obtain multiple indicator data of the pumped storage equipment after maintenance, including reliability indicators, accident events, maintenance costs, and equipment status; reliability indicators include equivalent availability coefficient, forced outage rate, unit startup success rate, and unplanned outage time; accident events include accident event level and accident event number; maintenance costs include asset maintenance fees of 10,000 yuan and average maintenance fees for a single unit over many years; equipment status includes operating status, performance indicators, and health adjustment. For example, generate maintenance evaluation tasks according to user needs, and automatically calculate unit reliability data and key indicator data after a certain maintenance according to the maintenance evaluation algorithm.

[0158] (2) Perform feature extraction on the indicator data to obtain indicator features.

[0159] (3) The indicator data is input into multiple maintenance strategy evaluation models to obtain the maintenance strategy evaluation results and corresponding prediction probabilities output by each maintenance strategy evaluation model.

[0160] (4) From each maintenance strategy evaluation model, select a target maintenance strategy evaluation model whose predicted probability is greater than a preset probability.

[0161] (5) According to the model weight of each target maintenance strategy evaluation model, the maintenance strategy evaluation results output by each target maintenance strategy evaluation model are comprehensively processed to obtain the target evaluation results of the maintenance strategy.

[0162] (6) According to the target evaluation results of the maintenance strategy, the maintenance strategy is improved in terms of reliability and iteratively improved. For example, according to the maintenance evaluation results, reliability improvements are made in terms of design improvement, manufacturing improvement, maintenance improvement, etc., and the maintenance strategy is improved by optimizing the maintenance process and decision-making methods, including the continuous optimization of maintenance types, maintenance items, maintenance cycles, and requirements.

[0163] The above-mentioned embodiment is conducive to improving the evaluation accuracy of the maintenance strategy of the pumped-storage equipment, while avoiding the defect of low evaluation accuracy of the maintenance strategy of the pumped-storage equipment due to manual evaluation of the maintenance strategy.

[0164] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0165] Based on the same inventive concept, the embodiment of the present application also provides a pumped-storage equipment maintenance strategy evaluation device for implementing the above-mentioned pumped-storage equipment maintenance strategy evaluation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the pumped-storage equipment maintenance strategy evaluation device provided below can refer to the limitations of the pumped-storage equipment maintenance strategy evaluation method above, and will not be repeated here.

[0166] In an exemplary embodiment, Figure 4 As shown, a pumped storage equipment maintenance strategy evaluation device is provided, including: a data acquisition module 410, a data screening module 420, a data screening module 430, a strategy evaluation module 440, a model screening module 450 and a result determination module 460, wherein:

[0167] The data acquisition module 410 is used to perform maintenance on the pumped-storage equipment to be maintained according to the maintenance strategy of the pumped-storage equipment to be maintained, and obtain a plurality of indicator data of the pumped-storage equipment to be maintained after maintenance.

[0168] The data screening module 420 is used to screen out key indicator data from multiple indicator data.

[0169] The feature extraction module 430 is used to perform feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data.

[0170] The strategy evaluation module 440 is used to input the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, and obtain the strategy evaluation results of the maintenance strategies output by each maintenance strategy evaluation model, and the prediction probability corresponding to the strategy evaluation results.

[0171] The model screening module 450 is used to screen out, from each maintenance strategy evaluation model, a target maintenance strategy evaluation model whose output maintenance strategy evaluation result corresponds to a predicted probability greater than a preset probability.

[0172] The result determination module 460 is used to fuse the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy.

[0173] In an exemplary embodiment, the data screening module 420 is also used to input each indicator data into a pre-trained first importance prediction model to obtain the first importance corresponding to each indicator data; input each indicator data into a pre-trained second importance prediction model to obtain the second importance corresponding to each indicator data; fuse the first importance and the second importance corresponding to each indicator data to obtain the target importance corresponding to each indicator data; and screen out the indicator data whose corresponding target importance is greater than the preset importance from each indicator data as the key indicator data.

[0174] In an exemplary embodiment, the feature extraction module 430 is also used to identify the data type of the key indicator data; based on the data type of the key indicator data, query the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the key indicator data; input the key indicator data into the corresponding feature extraction model for feature extraction processing to obtain the first feature vector corresponding to the key indicator data; perform feature extraction processing on the first feature vector again to obtain the second feature vector corresponding to the key indicator data; and fuse the first feature vector and the second feature vector to obtain the feature vector of the key indicator data.

[0175] In an exemplary embodiment, the strategy evaluation module 440 is also used to input the feature vectors into multiple pre-trained maintenance strategy evaluation models, respectively, to obtain the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; to correct the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results, to obtain the corrected predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; and to screen out the preset evaluation result with the largest corrected predicted probability from the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model.

[0176] In an exemplary embodiment, the pumped-storage equipment maintenance strategy evaluation device also includes a model training device, which is used to perform maintenance on the sample pumped-storage equipment according to the sample maintenance strategy of the sample pumped-storage equipment, and obtain multiple sample indicator data of the sample pumped-storage equipment after maintenance; screen out key sample indicator data from the multiple sample indicator data; perform feature extraction processing on the key sample indicator data to obtain sample feature vectors corresponding to the key sample indicator data; input the sample feature vector into the maintenance strategy evaluation model to be trained to obtain a predicted strategy evaluation result of the sample maintenance strategy; obtain the actual strategy evaluation result of the sample maintenance strategy, and iteratively train the maintenance strategy evaluation model to be trained based on the difference between the predicted strategy evaluation result and the actual strategy evaluation result of the sample maintenance strategy to obtain a pre-trained maintenance strategy evaluation model.

[0177] In an exemplary embodiment, the pumped-storage equipment maintenance strategy evaluation device also includes a strategy update module, which is used to query the correspondence between the strategy evaluation result and the strategy evaluation level according to the target strategy evaluation result, and obtain the strategy evaluation level corresponding to the target strategy evaluation result; obtain the strategy update instruction corresponding to the strategy evaluation level; according to the strategy update instruction, update the maintenance strategy to obtain the updated maintenance strategy.

[0178] Each module in the above pumped storage equipment maintenance strategy evaluation device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0179] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store index data, key index data and other data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for evaluating the maintenance strategy of pumped storage equipment is implemented.

[0180] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0182] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0183] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0184] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0185] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0186] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating maintenance strategy of pumped storage equipment, characterized in that: The method comprises: According to the maintenance strategy of the pumped-storage equipment to be repaired, the pumped-storage equipment to be repaired is repaired to obtain a plurality of index data of the pumped-storage equipment to be repaired after the repair; Filtering out key indicator data from the multiple indicator data; Performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data; Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, obtaining a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result; From each of the maintenance strategy evaluation models, select a target maintenance strategy evaluation model whose output strategy evaluation result corresponds to a predicted probability greater than a preset probability; According to the model weight of each target maintenance strategy evaluation model, the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model are fused to obtain the target strategy evaluation results of the maintenance strategy.

2. The method according to claim 1, characterized in that The step of screening out key indicator data from the plurality of indicator data includes: Input each indicator data into a pre-trained first importance prediction model to obtain the first importance corresponding to each indicator data; Input each indicator data into a pre-trained second importance prediction model to obtain the second importance corresponding to each indicator data; The first importance and the second importance corresponding to each indicator data are respectively fused to obtain the target importance corresponding to each indicator data; From each of the indicator data, the indicator data whose corresponding target importance is greater than the preset importance is screened out as the key indicator data.

3. The method according to claim 1, characterized in that The performing feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data includes: Identify the data type of the key indicator data; According to the data type of the key indicator data, query the corresponding relationship between the data type and the feature extraction model to obtain the feature extraction model corresponding to the key indicator data; Inputting the key indicator data into a corresponding feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the key indicator data; Performing feature extraction processing on the first feature vector again to obtain a second feature vector corresponding to the key indicator data; The first feature vector and the second feature vector are fused to obtain a feature vector of the key indicator data.

4. The method according to claim 1, characterized in that: The step of respectively inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result, comprises: Inputting the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, and obtaining the predicted probability of the maintenance strategy under various preset evaluation results output by each maintenance strategy evaluation model; Correcting the predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results to obtain a corrected predicted probability of the maintenance strategy output by each maintenance strategy evaluation model under various preset evaluation results; From the various preset evaluation results of the maintenance strategy output by each maintenance strategy evaluation model, the preset evaluation result with the largest corrected prediction probability is screened out as the strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model.

5. The method according to claim 1, characterized in that Each pre-trained maintenance strategy evaluation model is trained in the following manner: According to the sample maintenance strategy of the sample pumped-storage equipment, the sample pumped-storage equipment is maintained to obtain a plurality of sample indicator data after the maintenance of the sample pumped-storage equipment; Filtering out key sample indicator data from the plurality of sample indicator data; Performing feature extraction processing on the key sample indicator data to obtain a sample feature vector corresponding to the key sample indicator data; Inputting the sample feature vector into the maintenance strategy evaluation model to be trained to obtain a prediction strategy evaluation result of the sample maintenance strategy; The actual strategy evaluation result of the sample maintenance strategy is obtained, and according to the difference between the predicted strategy evaluation result and the actual strategy evaluation result of the sample maintenance strategy, the maintenance strategy evaluation model to be trained is iteratively trained to obtain the pre-trained maintenance strategy evaluation model.

6. The method according to any one of claims 1 to 5, characterized in that: After fusing the strategy evaluation results output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy, the method further includes: According to the target strategy evaluation result, query the corresponding relationship between the strategy evaluation result and the strategy evaluation level to obtain the strategy evaluation level corresponding to the target strategy evaluation result; Obtaining a policy update instruction corresponding to the policy evaluation level; According to the strategy update instruction, the maintenance strategy is updated to obtain an updated maintenance strategy.

7. A pumped storage equipment maintenance strategy evaluation device, characterized in that: The device comprises: A data acquisition module, used to perform maintenance on the pumped-storage equipment to be maintained according to the maintenance strategy of the pumped-storage equipment to be maintained, and obtain a plurality of index data of the pumped-storage equipment to be maintained after maintenance; A data screening module, used to screen out key indicator data from the multiple indicator data; A feature extraction module is used to perform feature extraction processing on the key indicator data to obtain a feature vector corresponding to the key indicator data; A strategy evaluation module, used to input the feature vectors into a plurality of pre-trained maintenance strategy evaluation models respectively, to obtain a strategy evaluation result of the maintenance strategy output by each maintenance strategy evaluation model, and a prediction probability corresponding to the strategy evaluation result; A model screening module, used to screen out, from each of the maintenance strategy evaluation models, a target maintenance strategy evaluation model whose predicted probability corresponding to the strategy evaluation result of the maintenance strategy outputted is greater than a preset probability; The result determination module is used to fuse the strategy evaluation results of the maintenance strategy output by each target maintenance strategy evaluation model according to the model weight of each target maintenance strategy evaluation model to obtain the target strategy evaluation result of the maintenance strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images