Power equipment operation and maintenance method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a power equipment operation and maintenance method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring equipment data of to-be-analyzed power equipment; performing feature extraction processing on the equipment data to obtain feature vectors corresponding to the equipment data, and performing splicing processing on the feature vectors to obtain target feature vectors; according to the application scene identifier of the to-be-analyzed power equipment, determining a target equipment state prediction model corresponding to the to-be-analyzed power equipment from a plurality of equipment state prediction models, and inputting the target feature vector into the target equipment state prediction model to obtain a target equipment state prediction result corresponding to the to-be-analyzed power equipment; determining a target equipment operation and maintenance scheme corresponding to the to-be-analyzed power equipment according to the target equipment state prediction result; and performing operation and maintenance processing on the to-be-analyzed power equipment according to the target equipment operation and maintenance scheme. By adopting the method, the operation and maintenance accuracy of the power equipment 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 operating and maintaining power equipment. Background Art

[0002] At present, in order to ensure the safe and stable operation of the power system, it is crucial to operate and maintain power equipment.

[0003] In traditional technology, when operating and maintaining power equipment, manual experience is generally used; however, this method has subjective factors and is prone to errors, resulting in low accuracy in the operation and maintenance of power equipment. Summary of the invention

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

[0005] In a first aspect, the present application provides a method for operating and maintaining an electric power device, comprising:

[0006] Acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed;

[0007] Performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector;

[0008] According to the application scenario identifier of the power equipment to be analyzed, a target device state prediction model corresponding to the power equipment to be analyzed is determined from multiple device state prediction models, and the target feature vector is input into the target device state prediction model to obtain a target device state prediction result corresponding to the power equipment to be analyzed;

[0009] Determine the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result;

[0010] According to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained.

[0011] In one embodiment, determining the target device operation and maintenance solution corresponding to the power device to be analyzed according to the target device state prediction result includes:

[0012] Determining the associated power equipment corresponding to the power equipment to be analyzed;

[0013] Obtaining a device status prediction result corresponding to the associated power device;

[0014] According to the target device state prediction result and the device state prediction result corresponding to the associated power device, a target device operation and maintenance plan corresponding to the power device to be analyzed is determined.

[0015] In one embodiment, determining the associated power equipment corresponding to the power equipment to be analyzed includes:

[0016] Determining a plurality of candidate power devices corresponding to the power device to be analyzed;

[0017] Determining the degree of association between each of the candidate power devices and the power device to be analyzed;

[0018] From the candidate power devices, the candidate power devices whose correlation degree is greater than a preset correlation degree are screened out as the associated power devices.

[0019] In one embodiment, determining the target device operation and maintenance solution corresponding to the power device to be analyzed according to the target device state prediction result and the device state prediction result corresponding to the associated power device includes:

[0020] Determine the target operation and maintenance priority of the power equipment to be analyzed according to the target equipment state prediction result and the equipment state prediction result corresponding to the associated power equipment;

[0021] According to the target operation and maintenance priority, the corresponding relationship between the operation and maintenance priority and the equipment operation and maintenance plan is queried to obtain the equipment operation and maintenance plan corresponding to the target operation and maintenance priority as the target equipment operation and maintenance plan.

[0022] In one embodiment, the performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data includes:

[0023] Preprocessing the device data to obtain preprocessed device data;

[0024] Identifying a data type corresponding to the preprocessed device data;

[0025] According to the data type, query the corresponding relationship between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the preprocessed device data;

[0026] The target feature extraction model is used to perform feature extraction processing on the preprocessed device data to obtain a feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

[0027] In one embodiment, the target feature vector is input into the target device state prediction model to obtain the target device state prediction result corresponding to the power device to be analyzed, including:

[0028] Inputting the target feature vector into the target device state prediction model to obtain a plurality of device state prediction results corresponding to the power device to be analyzed, and a prediction probability corresponding to each of the device state prediction results;

[0029] From the device state prediction results, the device state prediction result with the largest prediction probability is screened out as the target device state prediction result.

[0030] In a second aspect, the present application also provides an electric power equipment operation and maintenance device, comprising:

[0031] A data acquisition module, used to acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed;

[0032] A feature extraction module is used to perform feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and perform splicing processing on the feature vector to obtain a target feature vector;

[0033] A result prediction module is used to determine a target device state prediction model corresponding to the power device to be analyzed from multiple device state prediction models according to the application scenario identifier of the power device to be analyzed, and input the target feature vector into the target device state prediction model to obtain a target device state prediction result corresponding to the power device to be analyzed;

[0034] A solution determination module, used to determine the target equipment operation and maintenance solution corresponding to the power equipment to be analyzed according to the target equipment state prediction result;

[0035] The equipment operation and maintenance module is used to perform operation and maintenance processing on the power equipment to be analyzed according to the target equipment operation and maintenance plan.

[0036] 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:

[0037] Acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed;

[0038] Performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector;

[0039] According to the application scenario identifier of the power equipment to be analyzed, a target device state prediction model corresponding to the power equipment to be analyzed is determined from multiple device state prediction models, and the target feature vector is input into the target device state prediction model to obtain a target device state prediction result corresponding to the power equipment to be analyzed;

[0040] Determine the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result;

[0041] According to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained.

[0042] 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:

[0043] Acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed;

[0044] Performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector;

[0045] According to the application scenario identifier of the power equipment to be analyzed, a target device state prediction model corresponding to the power equipment to be analyzed is determined from multiple device state prediction models, and the target feature vector is input into the target device state prediction model to obtain a target device state prediction result corresponding to the power equipment to be analyzed;

[0046] Determine the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result;

[0047] According to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained.

[0048] 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:

[0049] Acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed;

[0050] Performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector;

[0051] According to the application scenario identifier of the power equipment to be analyzed, a target device state prediction model corresponding to the power equipment to be analyzed is determined from multiple device state prediction models, and the target feature vector is input into the target device state prediction model to obtain a target device state prediction result corresponding to the power equipment to be analyzed;

[0052] Determine the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result;

[0053] According to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained.

[0054] The above-mentioned power equipment operation and maintenance method, device, computer equipment, storage medium and computer program product first obtain the operating data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed as the equipment data of the power equipment to be analyzed, then perform feature extraction processing on the equipment data to obtain the feature vector corresponding to the equipment data, and perform splicing processing on the feature vector to obtain the target feature vector. Then, according to the application scenario identifier of the power equipment to be analyzed, the target equipment state prediction model corresponding to the power equipment to be analyzed is determined from multiple equipment state prediction models, and the target feature vector is input into the target equipment state prediction model to obtain the target equipment state prediction result corresponding to the power equipment to be analyzed. Then, according to the target equipment state prediction result, the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed is determined. Finally, according to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained. In this way, when performing operation and maintenance on power equipment, multi-source data related to the power equipment to be analyzed is obtained, and after a series of processing, the data is input into the model for data analysis, and a personalized operation and maintenance plan is formulated based on the obtained target equipment status prediction results, so that accurate maintenance and management can be carried out according to the specific situation of the equipment, which is conducive to improving the operation and maintenance accuracy of the power equipment; moreover, the entire process does not require human intervention, avoiding the defects of low operation and maintenance accuracy of power equipment due to subjective factors and prone to errors in the form of manual experience, thereby further improving the operation and maintenance accuracy of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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.

[0056] Figure 1 A schematic diagram of a flow chart of a power equipment operation and maintenance method in one embodiment;

[0057] Figure 2 A flowchart of steps for determining a target equipment operation and maintenance solution corresponding to the power equipment to be analyzed in one embodiment;

[0058] Figure 3 A schematic diagram of a flow chart of a power equipment operation and maintenance method in another embodiment;

[0059] Figure 4 A structural block diagram of an electric power equipment operation and maintenance device in one embodiment;

[0060] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] 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.

[0062] 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.

[0063] In an exemplary embodiment, Figure 1 As shown, a method for operation and maintenance of electric power equipment is provided. This embodiment uses the method applied to a server as an example for illustration; it can be understood 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 implemented with an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0064] Step S101, obtaining equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environment data of the power equipment to be analyzed.

[0065] Among them, the power equipment to be analyzed refers to the power equipment that needs operation and maintenance, including generators, transformers, etc.

[0066] Among them, equipment data refers to data associated with the power equipment to be analyzed, including operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed.

[0067] The operating data is used to represent various parameters and indicators generated by the power equipment to be analyzed under normal operating conditions, such as voltage data, current data, etc.

[0068] Among them, fault data is used to represent relevant data of the power equipment to be analyzed when a fault occurs, such as fault type, fault location, etc.

[0069] The maintenance data is used to represent relevant data corresponding to the maintenance history of the power equipment to be analyzed, such as maintenance time, maintenance personnel, etc.

[0070] Among them, usage data is used to indicate the usage of the power equipment to be analyzed, such as the equipment commissioning time, usage time, etc.

[0071] Among them, environmental data is used to represent the external environmental conditions of the power equipment, such as temperature, humidity, etc.

[0072] Exemplarily, in response to an equipment analysis instruction for the power equipment to be analyzed, the server collects operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed through various sensors installed on the power equipment to be analyzed, and combines these data to obtain the equipment data of the power equipment to be analyzed.

[0073] Step S102, performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector.

[0074] Among them, the feature vector is used to represent the characterization vector corresponding to the device data.

[0075] The target feature vector refers to a feature vector obtained by concatenating feature vectors corresponding to device data.

[0076] Exemplarily, the server inputs the device data into the feature extraction model, performs feature extraction processing on the device data through the feature extraction model, and obtains a feature vector corresponding to the device data; then, the server splices the feature vector according to a preset splicing order to obtain a target feature vector.

[0077] Step S103, according to the application scenario identifier of the power equipment to be analyzed, determine the target device state prediction model corresponding to the power equipment to be analyzed from multiple device state prediction models, and input the target feature vector into the target device state prediction model to obtain the target device state prediction result corresponding to the power equipment to be analyzed.

[0078] The application scenario identifier refers to identification information corresponding to the application scenario in which the power equipment to be analyzed is located.

[0079] Among them, the equipment status prediction model refers to a network model that can obtain the equipment status prediction results of the power equipment, such as a weighted average model, a hierarchical analysis model, and a fuzzy comprehensive evaluation model.

[0080] The target device state prediction model refers to the device state prediction model corresponding to the power equipment to be analyzed.

[0081] Among them, the target equipment status prediction result is used to represent the level information corresponding to the health evaluation status of the power equipment to be analyzed, such as "excellent", "good", "medium", "poor", etc.

[0082] Exemplarily, the server obtains the location information of the power equipment to be analyzed, and determines the application scenario identifier of the power equipment to be analyzed based on the location information of the power equipment to be analyzed; then, the server determines the device state prediction model corresponding to the application scenario identifier from multiple device state prediction models based on the application scenario identifier of the power equipment to be analyzed, as the target device state prediction model corresponding to the power equipment to be analyzed; then, the server inputs the target feature vector into the target device state prediction model, and obtains the device state prediction result corresponding to the target feature vector, as the target device state prediction result corresponding to the power equipment to be analyzed.

[0083] Step S104: determining a target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result.

[0084] Among them, the target equipment operation and maintenance plan refers to the equipment operation and maintenance plan for the power equipment to be analyzed, such as arranging a routine inspection every quarter.

[0085] Exemplarily, the server determines, based on the target device state prediction result, an equipment operation and maintenance plan corresponding to the target device state prediction result as the target device operation and maintenance plan corresponding to the power equipment to be analyzed.

[0086] Step S105: performing operation and maintenance processing on the power equipment to be analyzed according to the operation and maintenance plan of the target equipment.

[0087] Exemplarily, the server generates equipment operation and maintenance instructions corresponding to the target equipment operation and maintenance plan according to the target equipment operation and maintenance plan as the target equipment operation and maintenance instructions corresponding to the power equipment to be analyzed; then, the server performs operation and maintenance processing on the power equipment to be analyzed according to the target equipment operation and maintenance instructions.

[0088] In the above-mentioned power equipment operation and maintenance method, the operating data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed are first obtained as the equipment data of the power equipment to be analyzed, and then the equipment data is subjected to feature extraction processing to obtain the feature vector corresponding to the equipment data, and the feature vector is spliced ​​to obtain the target feature vector. Then, according to the application scenario identifier of the power equipment to be analyzed, the target equipment state prediction model corresponding to the power equipment to be analyzed is determined from multiple equipment state prediction models, and the target feature vector is input into the target equipment state prediction model to obtain the target equipment state prediction result corresponding to the power equipment to be analyzed. Then, according to the target equipment state prediction result, the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed is determined. Finally, according to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained. In this way, when performing operation and maintenance on power equipment, multi-source data related to the power equipment to be analyzed is obtained, and after a series of processing, the data is input into the model for data analysis, and a personalized operation and maintenance plan is formulated based on the obtained target equipment status prediction results, so that accurate maintenance and management can be carried out according to the specific situation of the equipment, which is conducive to improving the operation and maintenance accuracy of the power equipment; moreover, the entire process does not require human intervention, avoiding the defects of low operation and maintenance accuracy of power equipment due to subjective factors and prone to errors in the form of manual experience, thereby further improving the operation and maintenance accuracy of power equipment.

[0089] In an exemplary embodiment, Figure 2 As shown, the above step S104, according to the target device state prediction result, determines the target device operation and maintenance plan corresponding to the power equipment to be analyzed, which specifically includes the following steps:

[0090] Step S201: determining the associated power equipment corresponding to the power equipment to be analyzed.

[0091] Step S202, obtaining the device status prediction result corresponding to the associated power equipment.

[0092] Step S203, determining a target device operation and maintenance solution corresponding to the power equipment to be analyzed according to the target device state prediction result and the device state prediction result corresponding to the associated power equipment.

[0093] The associated power equipment refers to power equipment that has a certain degree of correlation with the power equipment to be analyzed.

[0094] Among them, the equipment status prediction result corresponding to the associated power equipment is used to characterize the level information corresponding to the health evaluation status of the associated power equipment, such as "excellent", "good", "medium", "poor", etc.

[0095] Exemplarily, the server determines the associated power equipment corresponding to the power equipment to be analyzed through grey correlation analysis; then, the server collects equipment data of the associated power equipment through various sensors installed on the associated power equipment; then, the server obtains multiple historical equipment data of the associated power equipment, and the historical equipment status prediction results corresponding to each historical equipment data; then, the server determines the similarity between each historical equipment data and the equipment data of the associated power equipment; then, the server filters out the historical equipment data with a similarity greater than a preset similarity from each historical equipment data, and uses the historical equipment status prediction results corresponding to the historical equipment data as the equipment status prediction results corresponding to the associated power equipment; then, the server determines the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed based on the target equipment status prediction results and the equipment status prediction results corresponding to the associated power equipment.

[0096] In this embodiment, by determining the associated power equipment of the power equipment to be analyzed and obtaining its equipment status prediction results, it is possible to evaluate the operating status of the equipment to be analyzed from a broader perspective; moreover, the target equipment status prediction results and the equipment status prediction results corresponding to the associated power equipment are combined to determine the target equipment operation and maintenance plan, thereby realizing the integration of multi-dimensional information, which is conducive to improving the accuracy of determining the target equipment operation and maintenance plan.

[0097] In an exemplary embodiment, the above step S201, determining the associated power equipment corresponding to the power equipment to be analyzed, specifically includes the following contents: determining multiple candidate power equipment corresponding to the power equipment to be analyzed; determining the correlation between each candidate power equipment and the power equipment to be analyzed; and screening out, from each candidate power equipment, the candidate power equipment having a correlation greater than a preset correlation as the associated power equipment.

[0098] The candidate power equipment refers to power equipment to be selected, for example, power equipment in the same power system as the power equipment to be analyzed.

[0099] The correlation degree is used to indicate the proximity between each candidate power device and the power device to be analyzed.

[0100] The preset correlation refers to a preset correlation threshold value, which is used to judge the correlation between each candidate power device and the power device to be analyzed, such as 0.8. It should be noted that the preset correlation may be determined according to the circumstances.

[0101] Exemplarily, the server determines the power system to which the power equipment to be analyzed belongs, and from the power system, determines the power equipment in the same power system as the power equipment to be analyzed as multiple candidate power equipment corresponding to the power equipment to be analyzed; then, the server uses the grey correlation analysis method, takes the equipment data of the power equipment to be analyzed as a reference sequence, and takes the equipment data of each candidate power equipment as a comparison sequence, and determines the correlation between each candidate power equipment and the power equipment to be analyzed based on the reference sequence and the comparison sequence; then, the server screens out candidate power equipment with a correlation greater than a preset correlation from each candidate power equipment, and uses these candidate power equipment as associated power equipment.

[0102] For example, the server may determine the correlation between each candidate power device and the power device to be analyzed by the following formula:

[0103] , formula (1)

[0104] in, is the reference sequence, is a comparison sequence, is the resolution factor (usually taken as 0.5).

[0105] In this embodiment, by determining the correlation between each candidate power device and the power device to be analyzed, devices with a correlation greater than a preset correlation are screened out from the candidate devices as associated power devices, so that the closeness of the relationship between different devices can be accurately evaluated in a quantitative manner, and then the focus can be accurately placed on the key devices that are truly closely related to the device to be analyzed, which facilitates subsequent data processing.

[0106] In an exemplary embodiment, the above step S203 determines the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed based on the target equipment state prediction results and the equipment state prediction results corresponding to the associated power equipment, and specifically includes the following contents: determining the target operation and maintenance priority corresponding to the power equipment to be analyzed based on the target equipment state prediction results and the equipment state prediction results corresponding to the associated power equipment; based on the target operation and maintenance priority, querying the correspondence between the operation and maintenance priority and the equipment operation and maintenance plan, and obtaining the equipment operation and maintenance plan corresponding to the target operation and maintenance priority as the target equipment operation and maintenance plan.

[0107] Among them, the target operation and maintenance priority refers to the operation and maintenance priority corresponding to the power equipment to be analyzed, such as highest, higher, slightly higher, and lowest.

[0108] It should be noted that the target operation and maintenance priority corresponding to the power equipment to be analyzed is determined comprehensively by the target equipment state prediction result corresponding to the power equipment to be analyzed and the equipment state prediction result corresponding to the associated power equipment. For example, when the target equipment state prediction result corresponding to the power equipment to be analyzed and the equipment state prediction result corresponding to the associated power equipment are both "excellent", the target operation and maintenance priority corresponding to the power equipment to be analyzed is the lowest; when the target equipment state prediction result corresponding to the power equipment to be analyzed is "excellent" and the equipment state prediction result corresponding to the associated power equipment is "good", the corresponding operation and maintenance priority is slightly higher; when the target equipment state prediction result corresponding to the power equipment to be analyzed is "excellent" and the equipment state prediction result corresponding to the associated power equipment is "medium", the corresponding operation and maintenance priority is relatively high; when the target equipment state prediction result corresponding to the power equipment to be analyzed is "excellent" and the equipment state prediction result corresponding to the associated power equipment is "poor", the corresponding operation and maintenance priority is the highest.

[0109] Among them, the corresponding relationship between the operation and maintenance priority and the equipment operation and maintenance plan is used to represent the association information between the operation and maintenance priority and the equipment operation and maintenance plan. For example, when the operation and maintenance priority is the lowest, the corresponding equipment operation and maintenance plan is to arrange a routine inspection once a quarter; when the operation and maintenance priority is slightly higher, the corresponding equipment operation and maintenance plan is to arrange a routine inspection once a month, and focus on monitoring some key indicators; when the operation and maintenance priority is relatively high, the corresponding equipment operation and maintenance plan is to arrange a routine inspection every two weeks, and arrange preventive maintenance measures to replace or repair key components of the equipment in advance; when the operation and maintenance priority is the highest, the corresponding equipment operation and maintenance plan is to immediately stop the equipment from running, and conduct a comprehensive overhaul, and prioritize the allocation of resources for maintenance to ensure that the equipment can resume normal operation as soon as possible.

[0110] Exemplarily, the server inputs the target device status prediction result and the device status prediction result corresponding to the associated power equipment into the operation and maintenance priority prediction model to obtain multiple predicted operation and maintenance priorities corresponding to the power equipment to be analyzed, and the prediction probability corresponding to each predicted operation and maintenance priority; then, the server filters out the predicted operation and maintenance priority with the largest prediction probability from each predicted operation and maintenance priority as the target operation and maintenance priority corresponding to the power equipment to be analyzed; then, the server queries the correspondence between the operation and maintenance priority and the equipment operation and maintenance plan based on the target operation and maintenance priority, obtains the equipment operation and maintenance plan corresponding to the target operation and maintenance priority, and uses the equipment operation and maintenance plan as the target equipment operation and maintenance plan.

[0111] In this embodiment, the target operation and maintenance priority of the power equipment to be analyzed is determined by combining the target device status prediction results and the device status prediction results corresponding to the associated power equipment, which fully considers the mutual influence between the equipment and the overall operating status of the system, and avoids the defect of low accuracy in determining the target equipment operation and maintenance plan due to certain limitations based on the failure history or experience judgment of a single device.

[0112] In an exemplary embodiment, the above step S102, performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, specifically includes the following contents: preprocessing the device data to obtain preprocessed device data; identifying the data type corresponding to the preprocessed device data; according to the data type, querying the correspondence between the data type and the feature extraction model to obtain a target feature extraction model corresponding to the preprocessed device data; performing feature extraction processing on the preprocessed device data through the target feature extraction model to obtain a feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

[0113] Preprocessing the device data refers to performing preprocessing operations such as denoising and normalization on the device data.

[0114] The preprocessed device data is the preprocessed device data.

[0115] Among them, the data types corresponding to the preprocessed device data include numerical type and time series type.

[0116] The correspondence between the data type and the feature extraction model is used to represent the association information between the data type and the feature extraction model. For example, data type A corresponds to feature extraction model a, data type B corresponds to feature extraction model b, and data type C corresponds to feature extraction model c.

[0117] The target feature extraction model refers to a feature extraction model corresponding to the data type of the preprocessed device data.

[0118] Exemplarily, the server performs denoising on the device data to obtain denoised device data; then, the server performs normalization on the denoised device data to obtain preprocessed device data; then, the server identifies the data type corresponding to the preprocessed device data; then, the server queries the correspondence between the data type and the feature extraction model based on the data type of the preprocessed device data, and obtains the feature extraction model corresponding to the data type of the preprocessed device data as the target feature extraction model corresponding to the preprocessed device data; then, the server performs feature extraction on the preprocessed device data through the target feature extraction model, and obtains the feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

[0119] In this embodiment, through the correspondence between the data type and the feature extraction model, the feature extraction model corresponding to the data type of the preprocessed device data can be determined, so that a special feature extraction model can be matched according to different data types, thereby improving the accuracy and adaptability of feature extraction, which is conducive to improving the accuracy of determining the feature vector corresponding to the device data.

[0120] In an exemplary embodiment, the above step S103, inputs the target feature vector into the target device state prediction model to obtain the target device state prediction result corresponding to the power equipment to be analyzed, specifically including the following contents: inputs the target feature vector into the target device state prediction model to obtain multiple device state prediction results corresponding to the power equipment to be analyzed, and the prediction probability corresponding to each device state prediction result; from each device state prediction result, screens out the device state prediction result with the largest prediction probability as the target device state prediction result.

[0121] The prediction probability is used to indicate the possibility that the target device state prediction model determines that the device state prediction result is correct.

[0122] Exemplarily, the server obtains the prediction accuracy of the target device state prediction model; when the prediction accuracy of the target device state prediction model is greater than the preset accuracy, the server inputs the target feature vector into the target device state prediction model to obtain multiple device state prediction results corresponding to the power equipment to be analyzed, and the prediction probability corresponding to each device state prediction result; then, the server filters out the device state prediction result with the largest prediction probability from each device state prediction result, and uses the device state prediction result as the target device state prediction result.

[0123] In this embodiment, a plurality of device state prediction results and corresponding prediction probabilities are outputted through the target device state prediction model, thereby being able to provide more comprehensive information; moreover, the result with the largest prediction probability is screened out from the plurality of prediction results as the target device state prediction result, which can focus on the most likely state, and is conducive to improving the accuracy of the target device state prediction result.

[0124] In an exemplary embodiment, Figure 3 As shown, another power equipment operation and maintenance method is provided, which is described by taking the method applied to a server as an example, and includes the following steps:

[0125] Step S301, obtaining equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environment data of the power equipment to be analyzed.

[0126] Step S302, preprocessing the device data to obtain preprocessed device data; identifying the data type corresponding to the preprocessed device data; and querying the correspondence between the data type and the feature extraction model according to the data type to obtain the target feature extraction model corresponding to the preprocessed device data.

[0127] Step S303 , performing feature extraction processing on the preprocessed device data through the target feature extraction model, and obtaining a feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

[0128] Step S304, concatenating the feature vectors to obtain a target feature vector.

[0129] Step S305 , determining a target device state prediction model corresponding to the power device to be analyzed from a plurality of device state prediction models according to the application scenario identifier of the power device to be analyzed.

[0130] Step S306: input the target feature vector into the target device state prediction model to obtain a plurality of device state prediction results corresponding to the power equipment to be analyzed, and a prediction probability corresponding to each device state prediction result.

[0131] Step S307: Filter out the device state prediction result with the highest prediction probability from the device state prediction results as the target device state prediction result.

[0132] Step S308, determine multiple candidate power devices corresponding to the power device to be analyzed; determine the correlation between each candidate power device and the power device to be analyzed; and select candidate power devices with a correlation greater than a preset correlation from each candidate power device as associated power devices.

[0133] Step S309, obtaining the device status prediction result corresponding to the associated power equipment.

[0134] Step S310, determining the target operation and maintenance priority corresponding to the power equipment to be analyzed according to the target equipment state prediction result and the equipment state prediction result corresponding to the associated power equipment.

[0135] Step S311, according to the target operation and maintenance priority, query the corresponding relationship between the operation and maintenance priority and the equipment operation and maintenance plan, and obtain the equipment operation and maintenance plan corresponding to the target operation and maintenance priority as the target equipment operation and maintenance plan.

[0136] Step S312: performing operation and maintenance processing on the power equipment to be analyzed according to the operation and maintenance plan of the target equipment.

[0137] In the above-mentioned power equipment operation and maintenance method, when the power equipment is operated and maintained, multi-source data related to the power equipment to be analyzed is obtained, and after a series of processing, the data is input into the model for data analysis, and a personalized operation and maintenance plan is formulated according to the obtained target equipment status prediction results, so that accurate maintenance and management can be carried out according to the specific situation of the equipment, which is conducive to improving the operation and maintenance accuracy of the power equipment; moreover, the whole process does not require human intervention, avoiding the subjective factors and prone to errors in the way of manual experience, resulting in low operation and maintenance accuracy of the power equipment, thereby further improving the operation and maintenance accuracy of the power equipment.

[0138] In an exemplary embodiment, in order to more clearly illustrate the power equipment operation and maintenance method provided by the embodiment of the present application, the power equipment operation and maintenance method is specifically described below with a specific embodiment. In one embodiment, the present application also provides an equipment health evaluation model based on a single device dimension. When performing operation and maintenance processing on the power equipment, the equipment data of the power equipment is first obtained, and then the corresponding equipment health evaluation model of the power equipment is determined from multiple equipment health evaluation models according to the application scenario of the power equipment. Then, the equipment data is input into the equipment health evaluation model to obtain the health evaluation result of the power equipment. Then, according to the health evaluation result of the power equipment, the operation and maintenance priority of the power equipment is determined. Finally, according to the operation and maintenance priority of the power equipment, the corresponding operation and maintenance plan of the power equipment is generated. Specifically including the following contents:

[0139] In the equipment health evaluation model design plan, the equipment holographic data will be obtained, and the threshold analysis of the equipment status will be carried out. Combined with the analysis of related equipment, a state-only evaluation model will be finally formed to diagnose the equipment status and formulate differentiated equipment operation and maintenance strategies.

[0140] 1. Data collection and preprocessing:

[0141] Through sensors, high-definition video cameras, infrared cameras, voiceprint recognition equipment and other monitoring equipment, the online operation data of the equipment is collected in real time by integrating various inspection equipment data and live test data. According to the goal of establishing the equipment health evaluation model, key evaluation indicators are selected. Screening can be considered from dimensions such as equipment operation status data, equipment failure data, equipment maintenance data, equipment usage data, and equipment environment data. Some examples of selected evaluation indicators are as follows:

[0142] Failure rate: Count the number of equipment failures and equipment operating time over a period of time, and calculate the average failure rate of the equipment.

[0143] Maintenance time: Statistics on the maintenance time and operation time of equipment within a period of time, and calculate the average maintenance time ratio of the equipment.

[0144] Utilization rate: the ratio of equipment operating time to production time.

[0145] Availability rate: the proportion of time that equipment is in normal operating state to the total operating time.

[0146] Availability rate: The probability that the equipment can be started normally when needed.

[0147] Overhaul completion rate: the completion status of equipment overhaul tasks.

[0148] Repair cost rate: the proportion of equipment maintenance costs to total costs.

[0149] Effective operating efficiency: the efficiency of the equipment during its effective operating time.

[0150] The collected data is preprocessed by cleaning, denoising, normalization and other operations to ensure the accuracy and consistency of the data.

[0151] 2. Data aggregation monitoring:

[0152] Through robot / drone patrols to obtain inspection data, etc., and through holographic monitoring technology, all-round, non-stop intelligent inspection of equipment can be achieved, replacing traditional power outage tests, and multi-dimensional spectral intelligent inspection technology, voiceprint recognition technology and other means can be used to collect remote monitoring data of equipment.

[0153] 3. Establish a device health evaluation model based on a single device:

[0154] The health assessment model to be constructed is selected based on the relevant scenario conditions of power equipment. Specifically, the total score can be calculated for each model according to the following selection conditions. The higher the total score, the more suitable the model is in the current scenario, as shown in Table 1:

[0155] Table 1. Health assessment model selection criteria

[0156]

[0157] The selection criteria are explained as follows:

[0158] Data integrity: refers to whether the data covers a comprehensive scope and no important information is missing.

[0159] Data accuracy: reflects the accuracy of the data, with fewer errors or deviations.

[0160] Data size: measures the amount of data.

[0161] Data fuzziness: refers to the uncertainty and unclearness of data.

[0162] Evaluation accuracy requirements: expectations for the accuracy and detail of evaluation results.

[0163] Equipment complexity: describes the complexity of the structure, function, etc. of power equipment.

[0164] Clarity of association and impact: refers to the clarity and specificity of the associations and impacts between devices.

[0165] For the analysis of the clarity of correlation impact, the following method can be used to perform correlation device analysis to identify the correlation impact between devices.

[0166] (1) Frequent itemset mining:

[0167] Frequent itemsets refer to the collection of items that appear simultaneously in a data set. Common frequent itemset mining algorithms include the Apriori algorithm and the FP-Growth algorithm. The relevant key metric formulas are as follows:

[0168] Support: Support (A) = , formula (2)

[0169] Confidence: Confidence (A=>B) = , formula (3)

[0170] (2) Association rule mining:

[0171] Association rules refer to the conditional relationship between item sets. For example, "A->B" means that when item set A appears, item set B may also appear. Lift is used to measure whether the degree of association between A and B in the association rule "A=>B" is stronger than the degree of their random appearance. The relevant lift formula is as follows:

[0172] Lift (A=>B) = , formula (4)

[0173] (3) Grey correlation analysis:

[0174] Grey relational analysis is an analytical method used to deal with uncertain data. It evaluates the correlation between different factors by calculating the correlation degree of sequence data.

[0175] , formula (1)

[0176] in, is the reference sequence, is a comparison sequence, is the resolution factor (usually taken as 0.5).

[0177] The following are the relevant formulas for weighted average method, analytic hierarchy process and fuzzy comprehensive evaluation method:

[0178] (1) Weighted average method:

[0179] Multiply the score of each evaluation indicator by the corresponding weight, and then sum them up to get the final score. The formula is as follows.

[0180] Comprehensive score = , formula (5)

[0181] in, is the weight of the ith indicator, is the score of the ith indicator.

[0182] According to the recommended evaluation indicators, the actual operation cases of model scoring are as follows, as shown in Table 2:

[0183] Table 2 Evaluation index data of equipment

[0184]

[0185] According to the above description of the current situation, combined with the weighted average method to calculate:

[0186] The comprehensive score of device A = 0.01×20%+0.05×15%+0.9×15%+0.95×15%+0.9×10%+100%×10%+0.2×10%+0.944×5%≈0.623.

[0187] The comprehensive score of device B = 0.0056×20%+0.044×15%+0.889×15%+0.944×15%+0.875×10%+0×10%+0.1875×10%+0.9375×5%≈0.584.

[0188] The weighted average calculation shows that the health status of device A is acceptable.

[0189] (2) Analytic Hierarchy Process (AHP)

[0190] The analytic hierarchy process is a decision-making method that decomposes complex problems into multiple levels and determines the relative importance of each factor through pairwise comparison. It decomposes the problem into the goal level, the criterion level, and the solution level. By constructing a judgment matrix, the relative weights of the factors at each level are calculated, and the overall ranking of the solutions is finally obtained.

[0191] According to the recommended evaluation indicators, the actual operation case of model scoring is as follows:

[0192] A hierarchical model is established, including the target layer: equipment health status assessment; the criterion layer: failure rate, maintenance time, utilization rate, intact rate, start-up rate, overhaul completion rate, repair cost rate, and effective operation efficiency; the solution layer: equipment to be evaluated.

[0193] Constructing a judgment matrix involves comparing each factor in the criterion layer in pairs, assigning corresponding scale values ​​(usually using a 1-9 scale method) according to the degree of importance, and constructing a judgment matrix. For example, if the failure rate is considered to be slightly more important than the maintenance time, the comparison value of the failure rate to the maintenance time is assigned to 3, and vice versa, the comparison value of the maintenance time to the failure rate is 1 / 3.

[0194] The following are the meanings of the 1-9 scale, as shown in Table 3:

[0195] Table 3 Meaning of 1-9 scaling method

[0196]

[0197] According to the above scaling method, the judgment matrix (taking the criterion layer as an example) is constructed, as shown in Table 4:

[0198] Table 4 Judgment matrix

[0199]

[0200] Calculate the weight vector, including calculating the eigenvector and maximum eigenvalue of the judgment matrix, normalize the eigenvector, and obtain the weight of each factor. According to the above matrix, the weight of each indicator is calculated: failure rate: 0.31, maintenance time: 0.19, utilization rate: 0.09, intact rate: 0.05, start-up rate: 0.09, overhaul completion rate: 0.05, repair cost rate: 0.14, effective operation efficiency: 0.08.

[0201] The consistency test includes calculating the consistency index CI (Consistency Index) and the consistency ratio CR (Consistency Ratio) to determine whether the consistency of the matrix is ​​acceptable. If CR < 0.1, the consistency is acceptable, otherwise the judgment matrix needs to be readjusted.

[0202] Consistency Index (CI): CI= , formula (6)

[0203] Consistency Ratio (CR): CR= , formula (7)

[0204] When the value of CR is less than or equal to 0.1, the judgment matrix is ​​considered to have good consistency, otherwise the judgment matrix needs to be modified; the value of RI (Random Consistency Index) depends on the size of the judgment matrix (that is, the order of the matrix n), which can be found from a pre-prepared table. The value of RI is the average consistency index calculated from a large number of randomly generated judgment matrices.

[0205] According to the case, n=8, find the average random consistency index RI, for n=8, the value of RI is about 1.41.

[0206] Since the maximum eigenvalue is calculated The process is relatively complicated and is usually completed with the help of mathematical software (such as MATLAB, Python related libraries). Assume that the maximum eigenvalue of the judgment matrix of the above case is obtained by calculation ,but:

[0207]

[0208] Calculating the device score includes collecting specific data on each criterion layer indicator for each device, multiplying the data with the corresponding weight and summing them to obtain the health evaluation score of the device.

[0209] Assuming that the indicator data of equipment X are: failure rate: 0.02, maintenance time: 0.08, utilization rate: 0.85, intact rate: 0.92, start-up rate: 0.90, overhaul completion rate: 100%, repair cost rate: 0.15, effective operation efficiency: 0.88, the health score of equipment X = 0.02×0.31+0.08×0.19+0.85×0.09+0.92×0.05+0.90×0.09+1×0.05+0.15×0.14+0.88×0.08≈0.58 The higher the score, the better the health of the equipment.

[0210] The fuzzy comprehensive evaluation method includes dividing each evaluation index into different levels and using fuzzy mathematical methods for comprehensive evaluation.

[0211] Comprehensive evaluation score = , formula (8)

[0212] in, is the weight of the ith indicator, is the membership degree of the i-th indicator.

[0213] According to the recommended evaluation indicators, the actual operation case of model scoring is as follows:

[0214] Determine the evaluation factor set: U = {failure rate, maintenance time, utilization rate, intact rate, startability rate, overhaul completion rate, repair cost rate, effective operation efficiency}.

[0215] Determine the evaluation level set: V = {excellent, good, fair, poor}.

[0216] Determine the weight of each factor:

[0217] Assume that the weight vector determined by expert scoring or other methods is: A = (0.15, 0.1, 0.15, 0.15, 0.1, 0.1, 0.1, 0.15)

[0218] Determine the membership matrix:

[0219] Assume that a certain device is evaluated, and the specific data of its various indicators are as follows:

[0220] Failure rate: 0.02 times / hour, maintenance time: 0.05, utilization rate: 0.8, intact rate: 0.9, start-up rate: 0.85, overhaul completion rate: 80%, repair cost rate: 0.12, effective operation efficiency: 0.85.

[0221] According to the pre-set standards, the membership of each indicator to each evaluation level is determined. For example, a failure rate less than 0.01 is set as excellent, 0.01-0.03 is good, 0.03-0.05 is medium, and greater than 0.05 is poor. Then the membership of the equipment failure rate to excellent, good, medium, and poor is 0, 0.5, 0.5, and 0 respectively.

[0222] In this way, the membership matrix R is obtained:

[0223] , formula (9)

[0224] Conduct fuzzy comprehensive evaluation:

[0225] , formula (10)

[0226] , formula (11)

[0227] Regarding the evaluation results, according to the maximum membership principle (the evaluation level corresponding to the element with the maximum value is selected as the final evaluation result), the health evaluation result of the equipment is "good".

[0228] The above model algorithms enable devices with different health evaluation results to have corresponding differentiated operation and maintenance priority plans.

[0229] In the above embodiment, when the power equipment is operated and maintained, the multi-source data associated with the power equipment to be analyzed is obtained, and a series of processing is performed and then input into the model for data analysis, and a personalized operation and maintenance plan is formulated according to the obtained target equipment state prediction result, so that accurate maintenance and management can be carried out according to the specific situation of the equipment, which is conducive to improving the operation and maintenance accuracy of the power equipment; moreover, the whole process does not require manual intervention, avoiding the defects of subjective factors and easy errors in the way of manual experience, resulting in low operation and maintenance accuracy of the power equipment, and further improving the operation and maintenance accuracy of the power equipment. At the same time, in view of the problem of indicator construction, this embodiment constructs a multi-dimensional equipment health status indicator system, which widely covers key elements such as data integrity, equipment complexity and clarity of associated impacts, so as to achieve a comprehensive and in-depth reflection of the health status of the equipment. In view of the problem of indicator weight, this embodiment adopts an advanced weight allocation strategy to implement a rigorous scientific quantitative evaluation of each evaluation model. By comprehensively calculating the weights of each model and quantifying the scores, the high-scoring model is given priority as a health evaluation model for accurately calculating the health status of the equipment. In view of the problem of equipment correlation, this embodiment uses advanced technical means such as frequent item set mining, association rule mining and grey correlation analysis to deeply analyze the associated equipment and effectively identify the complex mutual influence relationship between equipment. Based on the core goal of the equipment health evaluation model, key evaluation indicators are carefully selected, and a sample list of evaluation indicator selection is provided, which provides a strong reference for model construction.

[0230] 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.

[0231] Based on the same inventive concept, the embodiment of the present application also provides an electric power equipment operation and maintenance device for implementing the electric power equipment operation and maintenance method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the electric power equipment operation and maintenance device provided below can refer to the limitations of the electric power equipment operation and maintenance method above, and will not be repeated here.

[0232] In an exemplary embodiment, Figure 4 As shown, a power equipment operation and maintenance device is provided, including: a data acquisition module 401, a feature extraction module 402, a result prediction module 403, a solution determination module 404 and an equipment operation and maintenance module 405, wherein:

[0233] The data acquisition module 401 is used to acquire the equipment data of the power equipment to be analyzed; the equipment data at least includes the operation data, fault data, maintenance data, usage data and environment data of the power equipment to be analyzed.

[0234] The feature extraction module 402 is used to perform feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and perform splicing processing on the feature vector to obtain a target feature vector.

[0235] The result prediction module 403 is used to determine the target device state prediction model corresponding to the power equipment to be analyzed from multiple device state prediction models according to the application scenario identifier of the power equipment to be analyzed, and input the target feature vector into the target device state prediction model to obtain the target device state prediction result corresponding to the power equipment to be analyzed.

[0236] The solution determination module 404 is used to determine the target equipment operation and maintenance solution corresponding to the power equipment to be analyzed according to the target equipment state prediction result.

[0237] The equipment operation and maintenance module 405 is used to perform operation and maintenance processing on the power equipment to be analyzed according to the target equipment operation and maintenance plan.

[0238] In an exemplary embodiment, the solution determination module 404 is also used to determine the associated power equipment corresponding to the power equipment to be analyzed; obtain the equipment status prediction results corresponding to the associated power equipment; and determine the target equipment operation and maintenance solution corresponding to the power equipment to be analyzed based on the target equipment status prediction results and the equipment status prediction results corresponding to the associated power equipment.

[0239] In an exemplary embodiment, the scheme determination module 404 is also used to determine multiple candidate power devices corresponding to the power device to be analyzed; determine the correlation between each candidate power device and the power device to be analyzed; and screen out candidate power devices with a correlation greater than a preset correlation from each candidate power device as associated power devices.

[0240] In an exemplary embodiment, the solution determination module 404 is also used to determine the target operation and maintenance priority corresponding to the power equipment to be analyzed based on the target equipment status prediction results and the equipment status prediction results corresponding to the associated power equipment; according to the target operation and maintenance priority, query the correspondence between the operation and maintenance priority and the equipment operation and maintenance solution, and obtain the equipment operation and maintenance solution corresponding to the target operation and maintenance priority as the target equipment operation and maintenance solution.

[0241] In an exemplary embodiment, the feature extraction module 402 is also used to preprocess the device data to obtain preprocessed device data; identify the data type corresponding to the preprocessed device data; query the correspondence between the data type and the feature extraction model according to the data type to obtain the target feature extraction model corresponding to the preprocessed device data; perform feature extraction processing on the preprocessed device data through the target feature extraction model to obtain a feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

[0242] In an exemplary embodiment, the result prediction module 403 is also used to input the target feature vector into the target device state prediction model to obtain multiple device state prediction results corresponding to the power equipment to be analyzed, and the prediction probability corresponding to each device state prediction result; from each device state prediction result, the device state prediction result with the largest prediction probability is screened out as the target device state prediction result.

[0243] Each module in the above-mentioned power equipment operation and maintenance 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 the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0244] 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 5 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. Among them, 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. Among them, 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 operating data, fault data, etc. 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 operating and maintaining power equipment is implemented.

[0245] Those skilled in the art will understand that Figure 5The 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] Those skilled 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 this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive 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, etc., but are not limited to this.

[0250] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0251] 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 understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations 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 operating and maintaining electric power equipment, characterized in that: The method comprises: Acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed; Performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and performing splicing processing on the feature vector to obtain a target feature vector; According to the application scenario identifier of the power equipment to be analyzed, a target device state prediction model corresponding to the power equipment to be analyzed is determined from multiple device state prediction models, and the target feature vector is input into the target device state prediction model to obtain a target device state prediction result corresponding to the power equipment to be analyzed; Determine the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result; According to the target equipment operation and maintenance plan, the power equipment to be analyzed is operated and maintained.

2. The method according to claim 1, characterized in that Determining the target equipment operation and maintenance plan corresponding to the power equipment to be analyzed according to the target equipment state prediction result includes: Determining the associated power equipment corresponding to the power equipment to be analyzed; Obtaining a device status prediction result corresponding to the associated power device; According to the target device state prediction result and the device state prediction result corresponding to the associated power device, a target device operation and maintenance plan corresponding to the power device to be analyzed is determined.

3. The method according to claim 2, characterized in that The determining of the associated power equipment corresponding to the power equipment to be analyzed includes: Determining a plurality of candidate power devices corresponding to the power device to be analyzed; Determining the degree of association between each of the candidate power devices and the power device to be analyzed; From the candidate power devices, the candidate power devices whose correlation degree is greater than a preset correlation degree are screened out as the associated power devices.

4. The method according to claim 2, characterized in that: Determining the target device operation and maintenance solution corresponding to the power device to be analyzed according to the target device state prediction result and the device state prediction result corresponding to the associated power device includes: Determine the target operation and maintenance priority of the power equipment to be analyzed according to the target equipment state prediction result and the equipment state prediction result corresponding to the associated power equipment; According to the target operation and maintenance priority, the corresponding relationship between the operation and maintenance priority and the equipment operation and maintenance plan is queried to obtain the equipment operation and maintenance plan corresponding to the target operation and maintenance priority as the target equipment operation and maintenance plan.

5. The method according to claim 1, characterized in that The performing feature extraction processing on the device data to obtain a feature vector corresponding to the device data includes: Preprocessing the device data to obtain preprocessed device data; Identifying a data type corresponding to the preprocessed device data; According to the data type, query the corresponding relationship between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the preprocessed device data; The target feature extraction model is used to perform feature extraction processing on the preprocessed device data to obtain a feature vector corresponding to the preprocessed device data as the feature vector corresponding to the device data.

6. The method according to any one of claims 1 to 5, characterized in that Inputting the target feature vector into the target device state prediction model to obtain a target device state prediction result corresponding to the power device to be analyzed includes: Inputting the target feature vector into the target device state prediction model to obtain a plurality of device state prediction results corresponding to the power device to be analyzed, and a prediction probability corresponding to each of the device state prediction results; From the device state prediction results, the device state prediction result with the largest prediction probability is screened out as the target device state prediction result.

7. An electric power equipment operation and maintenance device, characterized in that: The device comprises: A data acquisition module, used to acquire equipment data of the power equipment to be analyzed; the equipment data at least includes operation data, fault data, maintenance data, usage data and environmental data of the power equipment to be analyzed; A feature extraction module is used to perform feature extraction processing on the device data to obtain a feature vector corresponding to the device data, and perform splicing processing on the feature vector to obtain a target feature vector; A result prediction module is used to determine a target device state prediction model corresponding to the power device to be analyzed from multiple device state prediction models according to the application scenario identifier of the power device to be analyzed, and input the target feature vector into the target device state prediction model to obtain a target device state prediction result corresponding to the power device to be analyzed; A solution determination module, used to determine the target equipment operation and maintenance solution corresponding to the power equipment to be analyzed according to the target equipment state prediction result; The equipment operation and maintenance module is used to perform operation and maintenance processing on the power equipment to be analyzed according to the target equipment operation and maintenance plan.

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