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

Abstract

The invention relates to a pumped storage equipment maintenance strategy generation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: constructing an initial maintenance item list according to an equipment maintenance manual of pumped storage equipment; inputting current equipment data of the pumped storage equipment into the equipment state analysis model to obtain a current equipment state of the pumped storage equipment, and updating the initial maintenance item list according to the current equipment state and historical maintenance data of the pumped storage equipment to obtain a candidate maintenance item list; inputting the current equipment data and the current equipment state of the pumped storage equipment into the equipment fault prediction model to obtain fault information of the pumped storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; and generating a maintenance strategy of the pumped storage equipment according to the target maintenance item list. By adopting the method, the determination accuracy of the maintenance strategy can be improved.

Description

Technical Field

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

[0002] In the field of power grid technology, in order to maintain pumped storage equipment and ensure its normal operation, it is necessary to perform regular maintenance on the pumped storage equipment through relevant maintenance strategies.

[0003] In traditional technology, when determining the maintenance strategy of pumped-storage equipment, the corresponding maintenance strategy is generally formulated based on manual experience; however, when formulating the maintenance strategy of pumped-storage equipment, relying solely on manual experience can easily lead to limitations in the formulated maintenance strategy, resulting in a low accuracy rate in determining the maintenance strategy. Summary of the invention

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

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

[0006] Obtain equipment maintenance manuals for pumped storage equipment;

[0007] Constructing an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual;

[0008] Inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and updating the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list;

[0009] Inputting the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information;

[0010] A maintenance strategy for the pumped-storage equipment is generated based on the target maintenance item list.

[0011] In one of the embodiments, the pre-trained device state analysis model includes a plurality of sub-device state analysis models;

[0012] The step of inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment state analysis model to obtain the current equipment state of the pumped-storage equipment comprises:

[0013] Performing feature extraction processing on current equipment data of the pumped-storage equipment to obtain a target feature vector;

[0014] Inputting the target feature vector into the multiple sub-device state analysis models respectively, obtaining the device state of the pumped-storage device output by each sub-device state analysis model, and the state prediction probability corresponding to the device state;

[0015] Filtering out, from each of the sub-device state analysis models, a target sub-device state analysis model whose outputted state prediction probability corresponding to the device state of the pumped-storage device is greater than a first preset probability;

[0016] From the equipment states of the pumped-storage equipment output by each target sub-equipment state analysis model, the equipment state with the largest number of occurrences is screened out as the current equipment state of the pumped-storage equipment.

[0017] In one embodiment, the step of performing feature extraction processing on the current equipment data of the pumped-storage equipment to obtain a target feature vector includes:

[0018] Inputting the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model to obtain importance prediction probabilities of the current equipment data at various preset importances;

[0019] From the preset importances, selecting the preset importance with the largest importance prediction probability as the importance of the current device data;

[0020] Filtering out the device data whose importance is greater than a preset importance from the current device data as key device data;

[0021] Inputting the key equipment data into a plurality of pre-trained feature extraction models to obtain a plurality of feature vectors of the key equipment data;

[0022] The multiple feature vectors of the key equipment data are fused to obtain a fused feature vector as the target feature vector.

[0023] In one embodiment, the initial maintenance item list is updated according to the current equipment state and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list, including:

[0024] Inputting the current equipment status, the historical maintenance data of the pumped-storage equipment and the initial maintenance item list into a pre-trained maintenance item prediction model to obtain a predicted maintenance probability of each maintenance item in the initial maintenance item list;

[0025] From the various maintenance items, determine a maintenance item whose predicted maintenance probability is greater than a second preset probability as a target maintenance item;

[0026] The maintenance items other than the target maintenance items in the initial maintenance item list are deleted to obtain the candidate maintenance item list.

[0027] In one of the embodiments, the pre-trained equipment failure prediction model includes a first equipment failure prediction model and a second equipment failure prediction model;

[0028] The step of inputting the current equipment data and the current equipment state of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain the fault information of the pumped-storage equipment includes:

[0029] Performing feature extraction processing on the current device data and the current device state to obtain a feature vector corresponding to the current device data and a feature vector corresponding to the current device state;

[0030] Performing concatenation processing on the feature vector corresponding to the current device data and the feature vector corresponding to the current device state to obtain a concatenated feature vector;

[0031] Inputting the spliced ​​feature vector into the first equipment fault prediction model to obtain current fault information of the pumped-storage equipment, and inputting the spliced ​​feature vector into the second equipment fault prediction model to obtain future fault information of the pumped-storage equipment;

[0032] The current fault information and the future fault information are fused to obtain the fault information of the pumped storage equipment.

[0033] In one embodiment, the candidate maintenance item list is updated again according to the fault information to obtain a target maintenance item list, including:

[0034] According to the current fault information of the pumped-storage equipment, query the corresponding relationship between the current fault information and the maintenance item to obtain the first maintenance item corresponding to the current fault information;

[0035] According to the future fault information of the pumped-storage equipment, query the corresponding relationship between the future fault information and the maintenance item to obtain the second maintenance item corresponding to the future fault information;

[0036] In the candidate maintenance item list, the first maintenance item and the second maintenance item are added to obtain the target maintenance item list.

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

[0038] An information acquisition module, used to obtain equipment maintenance manuals for pumped storage equipment;

[0039] A list building module, used to build an initial maintenance item list of the pumped storage equipment according to the equipment maintenance manual;

[0040] A first updating module is used to input the current equipment data of the pumped-storage equipment into a pre-trained equipment state analysis model to obtain the current equipment state of the pumped-storage equipment, and update the initial maintenance item list according to the current equipment state and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list;

[0041] A second updating module is used to input the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and update the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information;

[0042] A strategy generation module is used to generate a maintenance strategy for the pumped-storage equipment according to the target maintenance item list.

[0043] 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:

[0044] Obtain equipment maintenance manuals for pumped storage equipment;

[0045] Constructing an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual;

[0046] Inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and updating the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list;

[0047] Inputting the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information;

[0048] A maintenance strategy for the pumped-storage equipment is generated based on the target maintenance item list.

[0049] 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:

[0050] Obtain equipment maintenance manuals for pumped storage equipment;

[0051] Constructing an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual;

[0052] Inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and updating the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list;

[0053] Inputting the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information;

[0054] A maintenance strategy for the pumped-storage equipment is generated based on the target maintenance item list.

[0055] 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:

[0056] Obtain equipment maintenance manuals for pumped storage equipment;

[0057] Constructing an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual;

[0058] Inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and updating the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list;

[0059] Inputting the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information;

[0060] A maintenance strategy for the pumped-storage equipment is generated based on the target maintenance item list.

[0061] The above-mentioned pumped-storage equipment maintenance strategy generation method, device, computer equipment, computer-readable storage medium and computer program product first obtain the equipment maintenance manual of the pumped-storage equipment, and build an initial maintenance item list of the pumped-storage equipment based on the equipment maintenance manual, then input the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, update the initial maintenance item list based on the current equipment status and the historical maintenance data of the pumped-storage equipment, and obtain a candidate maintenance item list, then input the current equipment data and the current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain the fault information of the pumped-storage equipment, and update the candidate maintenance item list again based on the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information, and finally, based on the target maintenance item list, generate a maintenance strategy for the pumped-storage equipment. In this way, when generating the maintenance strategy of pumped-storage equipment, the equipment maintenance manual of the pumped-storage equipment, the current equipment status, historical maintenance data, current fault information and future fault information are comprehensively considered, and this is used to determine the target maintenance project list, which is conducive to improving the accuracy of determining the target maintenance project list, thereby making the maintenance strategy generated based on the target maintenance project list more accurate, thereby improving the accuracy of determining the maintenance strategy, and at the same time avoiding the limitations of the maintenance strategy formulated based on manual experience, resulting in the defect of low accuracy in determining the maintenance strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] 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.

[0063] Figure 1 A schematic diagram of a flow chart of a method for generating a maintenance strategy for pumped storage equipment in one embodiment;

[0064] Figure 2A flowchart of steps for inputting current equipment data of a pumped-storage equipment into a pre-trained equipment state analysis model to obtain the current equipment state of the pumped-storage equipment in one embodiment;

[0065] Figure 3 A schematic flow chart of a method for generating a maintenance strategy for pumped storage equipment in another embodiment;

[0066] Figure 4 A flow chart of a method for determining a maintenance strategy for a pumped storage device in one embodiment;

[0067] Figure 5 It is a structural block diagram of a device for generating a maintenance strategy for pumped storage equipment in one embodiment;

[0068] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0069] 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.

[0070] 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.

[0071] Figure 1 is a flow chart of a method for generating a maintenance strategy for a pumped storage device according to an exemplary embodiment. Figure 1 As shown, the method for generating maintenance strategy for pumped storage equipment is applied to a server; it is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablet computers; the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. In this exemplary embodiment, the method includes the following steps S101 to S105. Among them:

[0072] Step S101, obtaining the equipment maintenance manual of the pumped storage equipment.

[0073] Among them, the equipment maintenance manual refers to a one-type-one-book. One-type-one-book refers to an independent data book or manual compiled for pumped storage equipment. This data book or manual usually contains detailed parameters, operating instructions, maintenance suggestions, troubleshooting methods and other related information of this type of pumped storage equipment, aiming to help staff better understand and use the pumped storage equipment.

[0074] Exemplarily, the server obtains the equipment maintenance manual of the pumped-storage equipment from a local database or from the network.

[0075] Step S102: construct an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual.

[0076] Among them, the initial maintenance item list includes multiple maintenance items, as well as the maintenance type, maintenance time, maintenance cycle, maintenance requirements, etc. of each maintenance item.

[0077] Exemplarily, the server determines the maintenance items corresponding to the pumped-storage equipment according to the equipment maintenance manual, and constructs an initial maintenance item list of the pumped-storage equipment according to the maintenance items corresponding to the pumped-storage equipment.

[0078] Step S103, input the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and update the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list.

[0079] Among them, the current equipment data refers to basic parameters, motor generator parameters, reversible pump turbine parameters and other key parameters. Basic parameters include total installed capacity, annual power generation, maximum load, rated frequency, maximum voltage level, etc.; motor generator parameters include motor generator type, ventilation cooling method, etc.; reversible pump turbine parameters include head, flow, speed, efficiency, power, impeller diameter, etc.; other key parameters include available capacity of power system, power station unit starting method, response time, life, etc.

[0080] Among them, the pre-trained equipment status analysis model refers to a network model used to output the current equipment status of the pumped-storage equipment, such as a neural network model, a deep learning model, a large model, etc.

[0081] Among them, historical maintenance data is used to characterize the historical maintenance status of pumped storage equipment, such as historical maintenance time, historical maintenance items, etc.

[0082] Among them, according to the current equipment status and the historical maintenance data of the pumped storage equipment, it can be determined which maintenance items in the initial maintenance item list need to be retained and which maintenance items need to be deleted, thereby obtaining a candidate maintenance item list.

[0083] The candidate maintenance item list includes maintenance items that need to be retained (ie, candidate maintenance items), as well as the maintenance type, maintenance time, maintenance cycle, maintenance requirements, etc. of each maintenance item that needs to be retained.

[0084] Exemplarily, the server obtains the current equipment data and historical maintenance data of the pumped-storage equipment from a local database, performs feature extraction processing on the current equipment data of the pumped-storage equipment to obtain a feature vector of the current equipment data, and inputs the feature vector of the current equipment data into a pre-trained equipment state analysis model, performs state prediction processing on the feature vector through the equipment state analysis model to obtain a predicted probability of the pumped-storage equipment under each preset equipment state, and selects the preset equipment state with the largest predicted probability from each preset equipment state as the current equipment state of the pumped-storage equipment; then, based on the current equipment state and the historical maintenance data of the pumped-storage equipment, from the initial maintenance item list, selects maintenance items that match the current equipment state and the historical maintenance data of the pumped-storage equipment as candidate maintenance items, and finally obtains a candidate maintenance item list based on the candidate maintenance items.

[0085] Furthermore, the pre-trained equipment state analysis model is trained in the following manner: the server obtains the current sample equipment data of the sample pumped-storage equipment, and inputs the current sample equipment data of the sample pumped-storage equipment into the equipment state analysis model to be trained to obtain the predicted equipment state of the sample pumped-storage equipment; the actual equipment state of the sample pumped-storage equipment is obtained, and according to the difference between the predicted equipment state and the actual equipment state of the sample pumped-storage equipment, the equipment state analysis model to be trained is iteratively trained to obtain the trained equipment state analysis model as the pre-trained equipment state analysis model.

[0086] Step S104, input the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and update the candidate maintenance item list again based on the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information.

[0087] Among them, the pre-trained equipment fault prediction model refers to a network model used to output fault information of pumped storage equipment, such as a neural network model, a deep learning model, a large model, etc.

[0088] The current fault information refers to the fault information currently existing in the pumped storage equipment.

[0089] Among them, future fault information refers to the fault information that may occur in the future of the pumped storage equipment.

[0090] Among them, according to the fault information, the maintenance items that need to be added can be determined and added to the candidate maintenance item list, so as to obtain the target maintenance item list. The newly added maintenance items correspond to the fault information. For example, if the fault information is A, then a maintenance item a is added.

[0091] Among them, the target maintenance project list includes newly added maintenance projects and a list of candidate maintenance projects.

[0092] Exemplarily, the server performs feature extraction processing on the current equipment data and the current equipment status of the pumped-storage equipment to obtain a feature vector corresponding to the current equipment data and the current equipment status, and inputs the feature vector corresponding to the current equipment data and the current equipment status into a pre-trained equipment fault prediction model, performs fault prediction processing on the feature vector through the pre-trained equipment fault prediction model to obtain current fault information and future fault information of the pumped-storage equipment, combines the current fault information and future fault information of the pumped-storage equipment to obtain the fault information of the pumped-storage equipment; finally, queries the correspondence between the fault information and the maintenance items, obtains the maintenance items corresponding to the fault information of the pumped-storage equipment as new maintenance items, and adds the new maintenance items to the candidate maintenance item list to obtain a target maintenance item list for the pumped-storage equipment.

[0093] Furthermore, the pre-trained equipment fault prediction model is trained in the following manner: the server obtains the current sample equipment data and the current sample equipment status of the sample pumped-storage equipment, and inputs the current sample equipment data and the current sample equipment status of the sample pumped-storage equipment into the equipment fault prediction model to be trained, so as to obtain the predicted fault information of the sample pumped-storage equipment; the actual fault information of the sample pumped-storage equipment is obtained, and according to the difference between the predicted fault information and the actual fault information of the sample pumped-storage equipment, the equipment fault prediction model to be trained is iteratively trained to obtain the trained equipment fault prediction model as the pre-trained equipment fault prediction model.

[0094] Step S105: generating a maintenance strategy for the pumped storage equipment according to the target maintenance item list.

[0095] Among them, maintenance strategy refers to the strategy for maintaining pumped storage equipment, specifically the list of target maintenance items.

[0096] Exemplarily, the server confirms the obtained target maintenance item list as the maintenance strategy for the pumped-storage equipment.

[0097] In the above-mentioned method for generating a maintenance strategy for pumped-storage equipment, the equipment maintenance manual of the pumped-storage equipment is first obtained, and based on the equipment maintenance manual, an initial maintenance item list of the pumped-storage equipment is constructed, and then the current equipment data of the pumped-storage equipment is input into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and the initial maintenance item list is updated based on the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list, and then the current equipment data and the current equipment status of the pumped-storage equipment are input into a pre-trained equipment fault prediction model to obtain the fault information of the pumped-storage equipment, and based on the fault information, the candidate maintenance item list is updated again to obtain a target maintenance item list; the fault information includes current fault information and future fault information, and finally, based on the target maintenance item list, a maintenance strategy for the pumped-storage equipment is generated. In this way, when generating the maintenance strategy of pumped-storage equipment, the equipment maintenance manual of the pumped-storage equipment, the current equipment status, historical maintenance data, current fault information and future fault information are comprehensively considered, and this is used to determine the target maintenance project list, which is conducive to improving the accuracy of determining the target maintenance project list, thereby making the maintenance strategy generated based on the target maintenance project list more accurate, thereby improving the accuracy of determining the maintenance strategy, and at the same time avoiding the limitations of the maintenance strategy formulated based on manual experience, resulting in the defect of low accuracy in determining the maintenance strategy.

[0098] In an exemplary embodiment, Figure 2 As shown, the pre-trained device state analysis model includes multiple sub-device state analysis models; then, the above step S103, inputting the current device data of the pumped storage device into the pre-trained device state analysis model to obtain the current device state of the pumped storage device, includes the following steps S201 to S204. Among them:

[0099] Step S201, performing feature extraction processing on current equipment data of the pumped storage equipment to obtain a target feature vector.

[0100] Step S202 , respectively inputting the target feature vector into a plurality of sub-device state analysis models to obtain the device state of the pumped-storage device output by each sub-device state analysis model and the state prediction probability corresponding to the device state.

[0101] Step S203 , selecting a target sub-device state analysis model whose output state prediction probability corresponding to the device state of the pumped-storage device is greater than a first preset probability from each sub-device state analysis model.

[0102] Step S204 , selecting the device state with the most occurrences from the device states of the pumped-storage equipment output by each target sub-device state analysis model as the current device state of the pumped-storage equipment.

[0103] The sub-device state analysis model refers to a network model used to output the device state of the pumped storage equipment, such as a neural network model, a deep learning model, etc. The model structures of different sub-device state analysis models are different.

[0104] The target feature vector refers to the feature vector corresponding to the current device data of the pumped storage device.

[0105] Exemplarily, the server determines a feature extraction model corresponding to the current device data of the pumped-storage device, and performs feature extraction processing on the current device data of the pumped-storage device through the feature extraction model to obtain a target feature vector; then, the target feature vector is respectively input into a plurality of sub-device state analysis models to obtain the state prediction probability of the pumped-storage device under each preset device state output by each sub-device state analysis model; for each sub-device state analysis model, the preset device state with the largest state prediction probability is screened out from each preset device state as the device state of the pumped-storage device output by each sub-device state analysis model, and the state prediction probability corresponding to the preset device state with the largest state prediction probability is used as the device state of the pumped-storage device output by each sub-device state analysis model. The state prediction probability corresponding to the equipment state of the pumped-storage equipment outputted by the target sub-equipment state analysis model is obtained; then, from each sub-equipment state analysis model, a sub-equipment state analysis model whose state prediction probability corresponding to the equipment state of the pumped-storage equipment outputted is greater than a first preset probability is selected as the target sub-equipment state analysis model; finally, from the equipment state of the pumped-storage equipment outputted by each target sub-equipment state analysis model, the equipment state with the largest number of occurrences is selected as the current equipment state of the pumped-storage equipment; for example, assuming that the equipment states of the pumped-storage equipment outputted by the target sub-equipment state analysis models M1, M2, M3, and M4 are S1, S2, S1, and S3 respectively, then the equipment state S1 has the largest number of occurrences, and the equipment state S1 is used as the current equipment state of the pumped-storage equipment.

[0106] In this embodiment, the device state of the pumped-storage equipment output by each sub-device state analysis model and the state prediction probability corresponding to the device state are first obtained, and then from each sub-device state analysis model, a target sub-device state analysis model whose state prediction probability corresponding to the device state of the pumped-storage equipment output is greater than a first preset probability is screened out, and finally, from the device state of the pumped-storage equipment output by each target sub-device state analysis model, the device state with the largest number of occurrences is screened out as the current device state of the pumped-storage equipment, which is beneficial to improving the accuracy of determining the current device state of the pumped-storage equipment.

[0107] In an exemplary embodiment, the above step S201 performs feature extraction processing on the current equipment data of the pumped-storage equipment to obtain a target feature vector, which specifically includes the following contents: inputting the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model to obtain the importance prediction probability of the current equipment data at each preset importance; from each preset importance, screening out the preset importance with the largest importance prediction probability as the importance of the current equipment data; from the current equipment data, screening out equipment data with an importance greater than the preset importance as key equipment data; inputting the key equipment data into multiple pre-trained feature extraction models to obtain multiple feature vectors of the key equipment data; fusing the multiple feature vectors of the key equipment data to obtain a fused feature vector as the target feature vector.

[0108] The pre-trained importance prediction model refers to a network model used to output the importance of current device data, such as an attention mechanism model.

[0109] Among them, the model structures of different pre-trained feature extraction models are different.

[0110] Exemplarily, the server inputs the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model, performs importance prediction processing on the current equipment data through the pre-trained importance prediction model, and obtains the importance prediction probability of the current equipment data at each preset importance; then, from each preset importance, screens out the preset importance with the largest importance prediction probability as the importance of the current equipment data; then, from the current equipment data, screens out the equipment data with an importance greater than the preset importance as the key equipment data; finally, inputs the key equipment data into multiple pre-trained feature extraction models, performs feature extraction processing on the key equipment data through each pre-trained feature extraction model, obtains the feature vectors of the key equipment data output by each pre-trained feature extraction model, as multiple feature vectors of the key equipment data, and fuses the multiple feature vectors of the key equipment data to obtain the fused feature vector as the target feature vector.

[0111] In this embodiment, the importance of the current device data is determined through a pre-trained importance prediction model, and then the key device data is screened out from the current device data based on the importance of the current device data. Finally, the key device data is input into multiple pre-trained feature extraction models to obtain multiple feature vectors of the key device data, which are then fused to obtain the target feature vector, which is beneficial to improving the accuracy of determining the target feature vector.

[0112] In an exemplary embodiment, the above step S103 updates the initial maintenance project list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance project list, which specifically includes the following contents: the current equipment status, the historical maintenance data of the pumped-storage equipment and the initial maintenance project list are input into a pre-trained maintenance project prediction model to obtain a predicted maintenance probability of each maintenance project in the initial maintenance project list; from each maintenance project, a maintenance project with a predicted maintenance probability greater than a second preset probability is determined as a target maintenance project; and maintenance projects other than the target maintenance project in the initial maintenance project list are deleted to obtain a candidate maintenance project list.

[0113] Among them, the pre-trained maintenance project prediction model refers to a network model used to output the predicted maintenance probability of a maintenance project, such as a neural network model, a deep learning model, etc.

[0114] Among them, the predicted maintenance probability of the maintenance item is used to characterize the maintenance necessity of the maintenance item.

[0115] The target maintenance items refer to the maintenance items in the initial maintenance item list whose predicted maintenance probability is greater than the second preset probability, and are used to indicate maintenance items that need to be retained.

[0116] Exemplarily, the server inputs the current equipment status, historical maintenance data of the pumped-storage equipment, and the initial maintenance project list into a pre-trained maintenance project prediction model, performs feature extraction processing on the current equipment status and historical maintenance data through the pre-trained maintenance project prediction model, obtains a feature vector corresponding to the current equipment status and historical maintenance data, and performs maintenance prediction processing on the feature vector to obtain a predicted maintenance probability for each maintenance item in the initial maintenance project list; then, from each maintenance item, a maintenance item having a predicted maintenance probability greater than a second preset probability is determined as a target maintenance item; finally, maintenance items other than the target maintenance item in the initial maintenance item list are deleted to obtain a processed maintenance item list as a candidate maintenance item list.

[0117] In this embodiment, the initial maintenance item list is updated according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list, which can make the determined candidate maintenance item list more accurate, thereby improving the accuracy of determining the candidate maintenance item list.

[0118] In an exemplary embodiment, the pre-trained equipment fault prediction model includes a first equipment fault prediction model and a second equipment fault prediction model; then, the above step S104, inputting the current equipment data and the current equipment state of the pumped-storage equipment into the pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, specifically includes the following contents: performing feature extraction processing on the current equipment data and the current equipment state to obtain a feature vector corresponding to the current equipment data and a feature vector corresponding to the current equipment state; performing splicing processing on the feature vector corresponding to the current equipment data and the feature vector corresponding to the current equipment state to obtain a spliced ​​feature vector; inputting the spliced ​​feature vector into the first equipment fault prediction model to obtain current fault information of the pumped-storage equipment, and inputting the spliced ​​feature vector into the second equipment fault prediction model to obtain future fault information of the pumped-storage equipment; fusing the current fault information and the future fault information to obtain fault information of the pumped-storage equipment.

[0119] Among them, the first equipment fault prediction model refers to a network model used to output the current fault information of the pumped-storage equipment, such as a neural network model, a deep learning model, etc.

[0120] Among them, the second equipment fault prediction model refers to a network model used to output future fault information of pumped-storage equipment, such as a neural network model, a deep learning model, etc.

[0121] Exemplarily, the server performs feature extraction processing on the current device data and the current device state through a feature extraction model to obtain a feature vector corresponding to the current device data and a feature vector corresponding to the current device state; then, the feature vector corresponding to the current device data and the feature vector corresponding to the current device state are spliced ​​to obtain a spliced ​​feature vector; then, the spliced ​​feature vector is input into the first device fault prediction model, and the spliced ​​feature vector is processed for fault prediction through the first device fault prediction model to obtain the probability of the pumped-storage device under each first preset fault information, and the first preset fault information with the highest probability is used as the current fault information of the pumped-storage device; at the same time, the spliced ​​feature vector is input into the second device fault prediction model, and the spliced ​​feature vector is processed for fault prediction through the second device fault prediction model to obtain the probability of the pumped-storage device under each second preset fault information, and the second preset fault information with the highest probability is used as the future fault information of the pumped-storage device; finally, the current fault information and the future fault information are combined to obtain the fault information of the pumped-storage device.

[0122] In this embodiment, the current fault information of the pumped-storage equipment is predicted through the first equipment fault prediction model, and the future fault information of the pumped-storage equipment is predicted through the second equipment fault prediction model, and the current fault information and the future fault information are fused to obtain the fault information of the pumped-storage equipment, which is beneficial to improving the accuracy of determining the fault information of the pumped-storage equipment.

[0123] In an exemplary embodiment, the above step S104, based on the fault information, updates the candidate maintenance item list again to obtain a target maintenance item list, which specifically includes the following contents: based on the current fault information of the pumped-storage equipment, query the correspondence between the current fault information and the maintenance item to obtain the first maintenance item corresponding to the current fault information; based on the future fault information of the pumped-storage equipment, query the correspondence between the future fault information and the maintenance item to obtain the second maintenance item corresponding to the future fault information; in the candidate maintenance item list, add the first maintenance item and the second maintenance item to obtain the target maintenance item list.

[0124] The corresponding relationship between the current fault information and the maintenance items is used to indicate that different current fault information corresponds to different maintenance items.

[0125] The corresponding relationship between the future fault information and the maintenance items is used to indicate that different future fault information corresponds to different maintenance items.

[0126] Among them, the target maintenance project list includes the first maintenance project, the second maintenance project and the candidate maintenance project list.

[0127] Exemplarily, the server first obtains the correspondence between current fault information and maintenance items, as well as the correspondence between future fault information and maintenance items from the local database; then, based on the current fault information of the pumped-storage equipment, the server queries the correspondence between the current fault information and the maintenance items, and obtains the maintenance item corresponding to the current fault information of the pumped-storage equipment as the first maintenance item; at the same time, based on the future fault information of the pumped-storage equipment, the server queries the correspondence between future fault information and maintenance items, and obtains the maintenance item corresponding to the future fault information of the pumped-storage equipment as the second maintenance item; finally, the first maintenance item and the second maintenance item are added to the candidate maintenance item list to obtain a processed candidate maintenance item list, which is the target maintenance item list, that is, the target maintenance item list includes the first maintenance item, the second maintenance item and the candidate maintenance item list.

[0128] In this embodiment, the candidate maintenance project list is updated again based on the current fault information and future fault information of the pumped-storage equipment to obtain the target maintenance project list, which can make the final target maintenance project list more accurate, thereby improving the accuracy of determining the target maintenance project list.

[0129] In an exemplary embodiment, Figure 3 As shown, another method for generating a maintenance strategy for 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:

[0130] Step S301, obtaining the equipment maintenance manual of the pumped storage equipment.

[0131] Step S302: construct an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual.

[0132] Step S303, input the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model to obtain the importance prediction probability of the current equipment data at each preset importance; from each preset importance, select the preset importance with the largest importance prediction probability as the importance of the current equipment data.

[0133] Step S304, screening out device data whose importance is greater than a preset importance from the current device data as key device data; inputting the key device data into a plurality of pre-trained feature extraction models to obtain a plurality of feature vectors of the key device data.

[0134] Step S305 , fusing multiple feature vectors of key equipment data to obtain a fused feature vector as a target feature vector.

[0135] Step S306, input the current equipment status, historical maintenance data of the pumped storage equipment and the initial maintenance item list into the pre-trained maintenance item prediction model to obtain the predicted maintenance probability of each maintenance item in the initial maintenance item list.

[0136] Step S307, from various maintenance items, determine the maintenance items with predicted maintenance probability greater than the second preset probability as the target maintenance items; delete the maintenance items except the target maintenance items in the initial maintenance item list to obtain a candidate maintenance item list.

[0137] Step S308, perform feature extraction processing on the current device data and the current device state to obtain a feature vector corresponding to the current device data and a feature vector corresponding to the current device state; perform splicing processing on the feature vector corresponding to the current device data and the feature vector corresponding to the current device state to obtain a spliced ​​feature vector.

[0138] Step S309, input the spliced ​​feature vector into the first equipment fault prediction model to obtain the current fault information of the pumped-storage equipment, and input the spliced ​​feature vector into the second equipment fault prediction model to obtain the future fault information of the pumped-storage equipment; fuse the current fault information and the future fault information to obtain the fault information of the pumped-storage equipment.

[0139] Step S310, based on the current fault information of the pumped-storage equipment, query the correspondence between the current fault information and the maintenance items to obtain the first maintenance item corresponding to the current fault information; based on the future fault information of the pumped-storage equipment, query the correspondence between the future fault information and the maintenance items to obtain the second maintenance item corresponding to the future fault information.

[0140] Step S311, adding the first maintenance item and the second maintenance item to the candidate maintenance item list to obtain a target maintenance item list.

[0141] Step S312: Generate a maintenance strategy for the pumped storage equipment based on the target maintenance item list.

[0142] In the above-mentioned method for generating a maintenance strategy for pumped-storage equipment, when generating a maintenance strategy for the pumped-storage equipment, the equipment maintenance manual of the pumped-storage equipment, the current equipment status, historical maintenance data, current fault information and future fault information are comprehensively considered, and the target maintenance item list is determined based on this, which is beneficial to improving the accuracy of determining the target maintenance item list, thereby making the maintenance strategy generated based on the target maintenance item list more accurate, thereby improving the accuracy of determining the maintenance strategy, and at the same time avoiding the defects of the low accuracy of determining the maintenance strategy caused by the limitations of the maintenance strategy formulated based on manual experience.

[0143] In an exemplary embodiment, in order to more clearly illustrate the pumped storage equipment maintenance strategy generation method provided in the embodiment of the present application, the pumped storage equipment maintenance strategy generation method is specifically described below with a specific embodiment. In an exemplary embodiment, Figure 4 As shown, the present application also proposes a method for determining a maintenance strategy for pumped storage equipment, which analyzes and automatically calculates a maintenance plan based on the standard maintenance test configuration of the pumped storage equipment and the equipment status evaluation results, and generates a maintenance plan item list; specifically, it includes the following contents:

[0144] (1) Maintenance project plan for newly built pumped storage equipment.

[0145] (2) Obtain the historical maintenance data of the pumped-storage equipment from the power grid management platform, and summarize the maintenance project information of the pumped-storage equipment based on the historical maintenance data of the pumped-storage equipment and one type and one book.

[0146] (3) Obtain the health evaluation results and importance evaluation results of pumped storage equipment, and determine the control level of pumped storage equipment according to the equipment risk matrix based on the health evaluation results and importance evaluation results of pumped storage equipment; the control level of pumped storage equipment is divided into "level I, level II, level III and level IV" from high to low. According to the RCM (Reliability Centered Maintenance) maintenance strategy library and control level, determine the maintenance decision results of pumped storage equipment. The maintenance decision results should include single maintenance items, maintenance time, and maintenance cycle; adjust the regular maintenance plan according to the maintenance decision results. Among them, the maintenance strategy differentiation principles of different control levels are as follows: (a) Level I control equipment: shorten the maintenance cycle and carry out maintenance in a timely manner (within 1 year). (b) Level II and III control equipment: carry out maintenance according to the maintenance cycle determined by RCM analysis, that is, the benchmark cycle. (c) Level IV control equipment: for equipment with normal status evaluation, the maintenance cycle can be appropriately extended according to the equipment failure law, and the extension time shall not exceed its benchmark cycle.

[0147] For example, based on historical maintenance conditions and equipment status evaluation results, the strategy analysis algorithm is executed: (1) Periodic maintenance items, maintenance when the time is due: For items with "Maintenance Strategy" = "Periodic Maintenance", maintenance is performed when the time is due; (2) Status maintenance items, healthy equipment is exempt from maintenance: For items with "Maintenance Strategy" = "Status Maintenance", whether maintenance is performed is determined based on the equipment status evaluation results, but it must not exceed the maximum cycle. (3) Defect elimination and technical transformation countermeasures, additional maintenance as needed: Manual or third-party systems supplement equipment defect elimination, technical transformation or function optimization maintenance items.

[0148] Among them, maintenance strategy formulation can also include the following steps: ① Based on component nodes, users configure standard maintenance lists; ② Users associate one or more completed equipment status evaluation tasks, complete maintenance strategy analysis tasks according to system guidance and calculations, and intelligently output maintenance plans; among them, evaluation standards, evaluation tasks, and maintenance strategies are linked to components; ③ (grid management platform) links defects, countermeasures and other information to complete maintenance plan formulation, automatically generate plan forms, etc.

[0149] (4) Add a new maintenance project list based on the projects that require new maintenance plans, such as fault elimination, countermeasures, and technical improvements, and support importing from the power grid management platform.

[0150] (5) Generate a maintenance item list for the pumped storage equipment based on the increased maintenance plan.

[0151] The above-mentioned embodiments are conducive to improving the accuracy of determining equipment maintenance strategies, while avoiding the defect that the maintenance strategies formulated based on manual experience have limitations, resulting in a low accuracy of determining maintenance strategies.

[0152] 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.

[0153] Based on the same inventive concept, the embodiment of the present application also provides a pumped-storage equipment maintenance strategy generation device for implementing the above-mentioned pumped-storage equipment maintenance strategy generation 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 generation device provided below can refer to the above-mentioned limitations on the pumped-storage equipment maintenance strategy generation method, which will not be repeated here.

[0154] In an exemplary embodiment, Figure 5 As shown, a pumped storage equipment maintenance strategy generation device is provided, comprising: an information acquisition module 510, a list construction module 520, a first update module 530, a second update module 540 and a strategy generation module 550, wherein:

[0155] The information acquisition module 510 is used to obtain the equipment maintenance manual of the pumped storage equipment.

[0156] The list building module 520 is used to build an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual.

[0157] The first update module 530 is used to input the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and update the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list.

[0158] The second update module 540 is used to input the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and based on the fault information, update the candidate maintenance item list again to obtain a target maintenance item list; the fault information includes current fault information and future fault information.

[0159] The strategy generation module 550 is used to generate a maintenance strategy for the pumped storage equipment according to the target maintenance item list.

[0160] In an exemplary embodiment, the pre-trained device state analysis model includes a plurality of sub-device state analysis models;

[0161] The first update module 530 is also used to perform feature extraction processing on the current equipment data of the pumped-storage equipment to obtain a target feature vector; input the target feature vector into a plurality of sub-equipment state analysis models respectively to obtain the equipment state of the pumped-storage equipment output by each sub-equipment state analysis model, and the state prediction probability corresponding to the equipment state; from each sub-equipment state analysis model, select a target sub-equipment state analysis model whose state prediction probability corresponding to the equipment state of the output pumped-storage equipment is greater than a first preset probability; from the equipment state of the pumped-storage equipment output by each target sub-equipment state analysis model, select the equipment state with the largest number of occurrences as the current equipment state of the pumped-storage equipment.

[0162] In an exemplary embodiment, the first update module 530 is also used to input the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model to obtain the importance prediction probability of the current equipment data at each preset importance; from each preset importance, screen out the preset importance with the largest importance prediction probability as the importance of the current equipment data; from the current equipment data, screen out equipment data with an importance greater than the preset importance as key equipment data; input the key equipment data into multiple pre-trained feature extraction models to obtain multiple feature vectors of the key equipment data; and fuse the multiple feature vectors of the key equipment data to obtain a fused feature vector as the target feature vector.

[0163] In an exemplary embodiment, the first update module 530 is also used to input the current equipment status, historical maintenance data of the pumped-storage equipment and the initial maintenance project list into a pre-trained maintenance project prediction model to obtain the predicted maintenance probability of each maintenance project in the initial maintenance project list; from each maintenance project, determine the maintenance project with a predicted maintenance probability greater than a second preset probability as the target maintenance project; delete the maintenance projects in the initial maintenance project list except the target maintenance project to obtain a candidate maintenance project list.

[0164] In an exemplary embodiment, the pre-trained equipment failure prediction model includes a first equipment failure prediction model and a second equipment failure prediction model;

[0165] The second update module 540 is also used to perform feature extraction processing on the current device data and the current device state to obtain a feature vector corresponding to the current device data and a feature vector corresponding to the current device state; to perform splicing processing on the feature vector corresponding to the current device data and the feature vector corresponding to the current device state to obtain a spliced ​​feature vector; to input the spliced ​​feature vector into the first device fault prediction model to obtain current fault information of the pumped-storage equipment, and to input the spliced ​​feature vector into the second device fault prediction model to obtain future fault information of the pumped-storage equipment; and to fuse the current fault information and the future fault information to obtain fault information of the pumped-storage equipment.

[0166] In an exemplary embodiment, the second update module 540 is also used to query the correspondence between the current fault information and the maintenance items based on the current fault information of the pumped-storage equipment, and obtain the first maintenance item corresponding to the current fault information; query the correspondence between the future fault information and the maintenance items based on the future fault information of the pumped-storage equipment, and obtain the second maintenance item corresponding to the future fault information; add the first maintenance item and the second maintenance item to the list of candidate maintenance items to obtain a list of target maintenance items.

[0167] Each module in the above-mentioned pumped storage equipment maintenance strategy generation device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules 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 of the above modules.

[0168] 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 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as equipment maintenance manuals and maintenance strategies. 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 generating a maintenance strategy for pumped storage equipment is implemented.

[0169] Those skilled in the art will understand that Figure 6 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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 generating a maintenance strategy for a pumped storage equipment, characterized in that: The method comprises: Obtain equipment maintenance manuals for pumped storage equipment; Constructing an initial maintenance item list for the pumped storage equipment according to the equipment maintenance manual; Inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment status analysis model to obtain the current equipment status of the pumped-storage equipment, and updating the initial maintenance item list according to the current equipment status and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list; Inputting the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and updating the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information; A maintenance strategy for the pumped-storage equipment is generated based on the target maintenance item list.

2. The method according to claim 1, characterized in that The pre-trained device state analysis model includes a plurality of sub-device state analysis models; The step of inputting the current equipment data of the pumped-storage equipment into a pre-trained equipment state analysis model to obtain the current equipment state of the pumped-storage equipment comprises: Performing feature extraction processing on current equipment data of the pumped-storage equipment to obtain a target feature vector; Inputting the target feature vector into the multiple sub-device state analysis models respectively, obtaining the device state of the pumped-storage device output by each sub-device state analysis model, and the state prediction probability corresponding to the device state; Filtering out, from each of the sub-device state analysis models, a target sub-device state analysis model whose outputted state prediction probability corresponding to the device state of the pumped-storage device is greater than a first preset probability; From the equipment states of the pumped-storage equipment output by each target sub-equipment state analysis model, the equipment state with the largest number of occurrences is screened out as the current equipment state of the pumped-storage equipment.

3. The method according to claim 2, characterized in that The step of performing feature extraction processing on the current equipment data of the pumped storage equipment to obtain a target feature vector includes: Inputting the current equipment data of the pumped-storage equipment into a pre-trained importance prediction model to obtain importance prediction probabilities of the current equipment data at various preset importances; From the preset importances, selecting the preset importance with the largest importance prediction probability as the importance of the current device data; Filtering out the device data whose importance is greater than a preset importance from the current device data as key device data; Inputting the key equipment data into a plurality of pre-trained feature extraction models to obtain a plurality of feature vectors of the key equipment data; The multiple feature vectors of the key equipment data are fused to obtain a fused feature vector as the target feature vector.

4. The method according to claim 1, characterized in that The initial maintenance item list is updated according to the current equipment state and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list, including: Inputting the current equipment status, the historical maintenance data of the pumped-storage equipment and the initial maintenance item list into a pre-trained maintenance item prediction model to obtain a predicted maintenance probability of each maintenance item in the initial maintenance item list; From the various maintenance items, determine a maintenance item whose predicted maintenance probability is greater than a second preset probability as a target maintenance item; The maintenance items other than the target maintenance items in the initial maintenance item list are deleted to obtain the candidate maintenance item list.

5. The method according to claim 1, characterized in that The pre-trained equipment failure prediction model includes a first equipment failure prediction model and a second equipment failure prediction model; The step of inputting the current equipment data and the current equipment state of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain the fault information of the pumped-storage equipment includes: Performing feature extraction processing on the current device data and the current device state to obtain a feature vector corresponding to the current device data and a feature vector corresponding to the current device state; Performing concatenation processing on the feature vector corresponding to the current device data and the feature vector corresponding to the current device state to obtain a concatenated feature vector; Inputting the spliced ​​feature vector into the first equipment fault prediction model to obtain current fault information of the pumped-storage equipment, and inputting the spliced ​​feature vector into the second equipment fault prediction model to obtain future fault information of the pumped-storage equipment; The current fault information and the future fault information are fused to obtain the fault information of the pumped storage equipment.

6. The method according to any one of claims 1 to 5, characterized in that: The candidate maintenance item list is updated again according to the fault information to obtain a target maintenance item list, including: According to the current fault information of the pumped-storage equipment, query the corresponding relationship between the current fault information and the maintenance item to obtain the first maintenance item corresponding to the current fault information; According to the future fault information of the pumped-storage equipment, query the corresponding relationship between the future fault information and the maintenance item to obtain the second maintenance item corresponding to the future fault information; In the candidate maintenance item list, the first maintenance item and the second maintenance item are added to obtain the target maintenance item list.

7. A pumped storage equipment maintenance strategy generation device, characterized in that: The device comprises: An information acquisition module, used to obtain equipment maintenance manuals for pumped storage equipment; A list building module, used to build an initial maintenance item list of the pumped storage equipment according to the equipment maintenance manual; A first updating module is used to input the current equipment data of the pumped-storage equipment into a pre-trained equipment state analysis model to obtain the current equipment state of the pumped-storage equipment, and update the initial maintenance item list according to the current equipment state and the historical maintenance data of the pumped-storage equipment to obtain a candidate maintenance item list; A second updating module is used to input the current equipment data and current equipment status of the pumped-storage equipment into a pre-trained equipment fault prediction model to obtain fault information of the pumped-storage equipment, and update the candidate maintenance item list again according to the fault information to obtain a target maintenance item list; the fault information includes current fault information and future fault information; A strategy generation module is used to generate a maintenance strategy for the pumped-storage equipment according to the target maintenance item list.

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