Converter station device operation and maintenance method based on spatial computing, computer device, and program product

Abstract

The present application relates to a converter station device operation and maintenance method and apparatus based on spatial computing, a computer device, a storage medium, and a computer program product. The method comprises: acquiring device information, target position information, and environment information of a device to be analyzed in a converter station to be analyzed; respectively preprocessing the device information, the target position information, and the environment information to obtain preprocessed device information, preprocessed position information, and preprocessed environment information; performing feature extraction processing and fusion processing on the preprocessed device information, the preprocessed position information, and the preprocessed environment information to obtain a fused feature vector corresponding to said device; inputting the fused feature vector into a pre-trained device operation and maintenance instruction prediction model to obtain a target device operation and maintenance instruction corresponding to said device; and performing corresponding operation and maintenance processing on said device on the basis of the target device operation and maintenance instruction. The method can improve the operation and maintenance efficiency of the converter station device.

Description

A converter station equipment operation and maintenance method, computer equipment, and software product based on space computing Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for the operation and maintenance of converter station equipment based on spatial computing. Background Technology

[0002] Currently, in order to ensure the safe and stable operation of converter stations, it is crucial to carry out operation and maintenance of converter station equipment.

[0003] In traditional technology, manual inspection is generally used when performing operation and maintenance on converter station equipment; however, this method is cumbersome and requires a lot of time and manpower, resulting in low operation and maintenance efficiency of converter station equipment. Summary of the Invention

[0004] Therefore, it is necessary to provide a spatial computing-based method, apparatus, computer equipment, computer-readable storage medium, and computer program product for the operation and maintenance of converter station equipment, which can improve the operation and maintenance efficiency of converter station equipment, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a converter station equipment operation and maintenance method based on spatial computing, including:

[0006] Obtain equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed;

[0007] The device information, the target location information, and the environmental information are preprocessed respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0008] Feature extraction processing is performed on the preprocessed device information, the preprocessed location information, and the preprocessed environment information respectively to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information;

[0009] The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed.

[0010] The fused feature vector is input into a pre-trained device operation and maintenance instruction prediction model to obtain the target device operation and maintenance instruction corresponding to the device to be analyzed.

[0011] According to the target device operation and maintenance instructions, perform corresponding operation and maintenance processing on the device to be analyzed.

[0012] In one embodiment, obtaining the equipment information, target location information, and environmental information of the device to be analyzed in the converter station to be analyzed includes:

[0013] Obtain the initial position information of the equipment to be analyzed in the converter station to be analyzed;

[0014] The initial location information is transformed according to a preset correspondence to obtain the target location information; the preset correspondence is used to represent the correspondence between the initial location information and the target location information.

[0015] In one embodiment, the step of performing feature extraction processing on the preprocessed device information, the preprocessed location information, and the preprocessed environment information to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information includes:

[0016] The preprocessed device information is used as the main data, and the preprocessed location information and the preprocessed environmental information are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the first feature vector.

[0017] The preprocessed location information is used as the main data, and the preprocessed device information and the preprocessed environmental information are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the second feature vector.

[0018] The preprocessed environmental information is used as the primary data, and the preprocessed device information and the preprocessed location information are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the third feature vector.

[0019] In one embodiment, the step of fusing the first feature vector, the second feature vector, and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed includes:

[0020] Obtain the first initial weight corresponding to the preprocessed device information, the second initial weight corresponding to the preprocessed location information, and the third initial weight corresponding to the preprocessed environmental information;

[0021] The first initial weight, the second initial weight, and the third initial weight are normalized to obtain the first target weight corresponding to the preprocessed device information, the second target weight corresponding to the preprocessed location information, and the third target weight corresponding to the preprocessed environmental information.

[0022] Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector.

[0023] In one embodiment, before obtaining the equipment information, target location information, and environmental information of the device to be analyzed in the converter station to be analyzed, the method further includes:

[0024] Obtain voltage level and equipment type information for candidate converter stations;

[0025] From the candidate converter stations, those that meet the preset conditions in both voltage level information and equipment type information are selected as the converter stations to be analyzed.

[0026] In one embodiment, the pre-trained equipment maintenance instruction prediction model is trained in the following manner:

[0027] Obtain sample equipment information, sample location information, and sample environment information from the sample converter station;

[0028] The sample device information, the sample location information, and the sample environment information are preprocessed respectively to obtain preprocessed sample device information, preprocessed sample location information, and preprocessed sample environment information.

[0029] Feature extraction processing is performed on the preprocessed sample device information, the preprocessed sample location information, and the preprocessed sample environment information respectively to obtain a first sample feature vector corresponding to the preprocessed sample device information, a second sample feature vector corresponding to the preprocessed sample location information, and a third sample feature vector corresponding to the preprocessed sample environment information.

[0030] The first sample feature vector, the second sample feature vector, and the third sample feature vector are fused to obtain the sample fused feature vector corresponding to the sample device.

[0031] The sample fusion feature vector is input into the equipment operation and maintenance instruction prediction model to be trained to obtain the predicted equipment operation and maintenance instructions corresponding to the sample equipment.

[0032] Obtain the actual equipment operation and maintenance instructions corresponding to the sample equipment, and iteratively train the equipment operation and maintenance instruction prediction model to be trained based on the difference between the predicted equipment operation and maintenance instructions and the actual equipment operation and maintenance instructions to obtain the pre-trained equipment operation and maintenance instruction prediction model.

[0033] Secondly, this application also provides a converter station equipment operation and maintenance device based on space computing, comprising:

[0034] The information acquisition module is used to acquire equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed;

[0035] The information processing module is used to preprocess the device information, the target location information and the environmental information respectively to obtain preprocessed device information, preprocessed location information and preprocessed environmental information;

[0036] The feature extraction module is used to perform feature extraction processing on the preprocessed device information, the preprocessed location information and the preprocessed environment information respectively, to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information and a third feature vector corresponding to the preprocessed environment information;

[0037] The feature fusion module is used to fuse the first feature vector, the second feature vector and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed.

[0038] The instruction prediction module is used to input the fused feature vector into a pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction corresponding to the equipment to be analyzed.

[0039] The equipment operation and maintenance module is used to perform corresponding operation and maintenance processing on the equipment to be analyzed according to the target equipment operation and maintenance instructions.

[0040] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0041] Obtain equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed;

[0042] The device information, the target location information, and the environmental information are preprocessed respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0043] Feature extraction processing is performed on the preprocessed device information, the preprocessed location information, and the preprocessed environment information respectively to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information;

[0044] The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed.

[0045] The fused feature vector is input into a pre-trained device operation and maintenance instruction prediction model to obtain the target device operation and maintenance instruction corresponding to the device to be analyzed.

[0046] According to the target device operation and maintenance instructions, perform corresponding operation and maintenance processing on the device to be analyzed.

[0047] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0048] Obtain equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed;

[0049] The device information, the target location information, and the environmental information are preprocessed respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0050] Feature extraction processing is performed on the preprocessed device information, the preprocessed location information, and the preprocessed environment information respectively to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information;

[0051] The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed.

[0052] The fused feature vector is input into a pre-trained device operation and maintenance instruction prediction model to obtain the target device operation and maintenance instruction corresponding to the device to be analyzed.

[0053] According to the target device operation and maintenance instructions, perform corresponding operation and maintenance processing on the device to be analyzed.

[0054] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0055] Obtain equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed;

[0056] The device information, the target location information, and the environmental information are preprocessed respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0057] Feature extraction processing is performed on the preprocessed device information, the preprocessed location information, and the preprocessed environment information respectively to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information;

[0058] The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed.

[0059] The fused feature vector is input into a pre-trained device operation and maintenance instruction prediction model to obtain the target device operation and maintenance instruction corresponding to the device to be analyzed.

[0060] According to the target device operation and maintenance instructions, perform corresponding operation and maintenance processing on the device to be analyzed.

[0061] The aforementioned converter station equipment operation and maintenance method, device, computer equipment, storage medium, and computer program product based on spatial computing first acquire the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station. These information are then preprocessed to obtain preprocessed equipment information, preprocessed location information, and preprocessed environmental information. Feature extraction is then performed on these preprocessed information to obtain a first feature vector corresponding to the preprocessed equipment information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environmental information. Next, the first, second, and third feature vectors are fused to obtain a fused feature vector corresponding to the equipment to be analyzed. This fused feature vector is then input into a pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction for the equipment to be analyzed. Finally, based on the target equipment operation and maintenance instruction, corresponding operation and maintenance processing is performed on the equipment to be analyzed. In this way, when performing operation and maintenance on converter station equipment, after obtaining the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station, a series of processes such as preprocessing, feature extraction, and fusion processing are carried out. Based on the pre-trained equipment operation and maintenance instruction prediction model, the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed can be obtained quickly and directly. This helps to improve the efficiency of determining the equipment operation and maintenance instructions of the converter station equipment, thereby improving the operation and maintenance efficiency of the converter station equipment. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of the cumbersome manual inspection method, which requires a lot of time and manpower and leads to low operation and maintenance efficiency of the converter station equipment, further improving the operation and maintenance efficiency of the converter station equipment. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 is a flowchart illustrating a converter station equipment operation and maintenance method based on spatial computing in one embodiment;

[0064] Figure 2 is a flowchart illustrating the operation and maintenance method of converter station equipment based on spatial computing in another embodiment;

[0065] Figure 3 is a schematic diagram of an intelligent interaction system in one embodiment;

[0066] Figure 4 is a schematic diagram of the structural principle of a binocular vision measurement system in one embodiment;

[0067] Figure 5 is a schematic diagram of coordinate system transformation of LiDAR point cloud data in one embodiment;

[0068] Figure 6 is a schematic diagram of the overall technical route of the intelligent interaction module in one embodiment;

[0069] Figure 7 is a schematic diagram of the overall intelligent assistance scheme for tasks in one embodiment;

[0070] Figure 8 is a schematic diagram of the job result recognition technology framework in one embodiment;

[0071] Figure 9 is a structural block diagram of a converter station equipment operation and maintenance device based on spatial computing in one embodiment;

[0072] Figure 10 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0074] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0075] In an exemplary embodiment, as shown in Figure 1, a converter station equipment operation and maintenance method based on space computing is provided. This embodiment illustrates the method by applying it to a server; it is 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. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0076] Step S101: Obtain the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed.

[0077] Among them, the converter station to be analyzed refers to the converter station that requires equipment operation and maintenance.

[0078] Among them, the equipment to be analyzed refers to the converter station equipment that requires operation and maintenance.

[0079] The equipment information includes the name and model of the equipment to be analyzed. It should be noted that this equipment information is obtained by identifying the nameplate and pressure plate of the equipment being analyzed.

[0080] Among them, the target location information is used to represent the coordinate information of the device to be analyzed in the LiDAR (Light Detection and Ranging) coordinate system.

[0081] Among them, environmental information is used to represent the information around the device to be analyzed, including the location information of the devices around the device to be analyzed.

[0082] For example, the server determines the target aging level of each candidate device based on the aging level of key components in each candidate device in the converter station to be analyzed; then, the server selects candidate devices whose target aging level is greater than the preset aging level from each candidate device as the devices to be analyzed in the converter station to be analyzed; then, the server uses sensors to identify the nameplate and pressure plate of the device to be analyzed to obtain the device information of the device to be analyzed; then, the server uses a LiDAR measurement system to obtain the coordinate information of the device to be analyzed in the LiDAR coordinate system as the target location information of the device to be analyzed; finally, the server uses the location information of the device within a preset range of the device to be analyzed as the environmental information of the device to be analyzed.

[0083] Step S102: Preprocess the equipment information, target location information, and environmental information respectively to obtain preprocessed equipment information, preprocessed location information, and preprocessed environmental information.

[0084] Among them, the pre-processed equipment information refers to the equipment information after pre-processing.

[0085] Among them, the preprocessed location information refers to the target location information after preprocessing.

[0086] Among them, preprocessed environmental information refers to environmental information after preprocessing.

[0087] For example, the server performs noise removal, multi-view alignment, data simplification, and surface reconstruction on the device information, target location information, and environmental information respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0088] Step S103: Perform feature extraction processing on the preprocessed device information, preprocessed location information, and preprocessed environment information respectively to obtain the first feature vector corresponding to the preprocessed device information, the second feature vector corresponding to the preprocessed location information, and the third feature vector corresponding to the preprocessed environment information.

[0089] The first feature vector refers to the feature vector corresponding to the preprocessed device information.

[0090] The second feature vector refers to the feature vector corresponding to the preprocessed position information.

[0091] The third feature vector refers to the feature vector corresponding to the preprocessed environmental information.

[0092] For example, the server inputs the preprocessed device information, preprocessed location information, and preprocessed environment information into the feature extraction model. The feature extraction model then performs feature extraction processing on the preprocessed device information, preprocessed location information, and preprocessed environment information to obtain the first feature vector corresponding to the preprocessed device information, the second feature vector corresponding to the preprocessed location information, and the third feature vector corresponding to the preprocessed environment information.

[0093] Step S104: The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed.

[0094] Among them, the fused feature vector refers to the feature vector obtained by fusing the first feature vector, the second feature vector, and the third feature vector.

[0095] For example, the server performs a weighted summation of the first feature vector, the second feature vector, and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed.

[0096] Step S105: Input the fused feature vector into the pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction corresponding to the equipment to be analyzed.

[0097] Among them, the equipment operation and maintenance instruction prediction model refers to a network model that can use the fused feature vector corresponding to the equipment to be analyzed to obtain the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed, such as recurrent neural network model, convolutional neural network model, etc.

[0098] Among them, the target equipment operation and maintenance instructions refer to the instruction information for the operation and maintenance of the equipment to be analyzed, such as equipment inspection instructions, equipment maintenance instructions, etc.

[0099] For example, the server feeds the input corresponding to the device to be analyzed into a pre-trained device operation and maintenance instruction prediction model to obtain multiple preset device operation and maintenance instructions corresponding to the device to be analyzed, as well as the prediction probability corresponding to each preset device operation and maintenance instruction; then, the server selects the preset device operation and maintenance instruction with the highest prediction probability from each preset device operation and maintenance instruction as the target device operation and maintenance instruction corresponding to the device to be analyzed.

[0100] Step S106: Perform corresponding maintenance procedures on the device to be analyzed according to the target device maintenance instructions.

[0101] For example, the server performs an integrity check on the target device maintenance instructions (for example, the server checks whether the target device maintenance instructions contain key information such as device identifier, instruction type, and execution parameters) and obtains the integrity check result corresponding to the target device maintenance instructions; then, if the integrity check result passes, the server performs the corresponding maintenance processing on the device to be analyzed according to the target device maintenance instructions.

[0102] In the aforementioned spatial computing-based converter station equipment operation and maintenance method, the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station are first obtained. These information are then preprocessed to obtain preprocessed equipment information, preprocessed location information, and preprocessed environmental information. Feature extraction is then performed on these preprocessed information to obtain a first feature vector corresponding to the preprocessed equipment information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environmental information. Next, the first, second, and third feature vectors are fused to obtain a fused feature vector corresponding to the equipment to be analyzed. This fused feature vector is then input into a pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction for the equipment to be analyzed. Finally, based on the target equipment operation and maintenance instruction, the corresponding operation and maintenance processing is performed on the equipment to be analyzed. In this way, when performing operation and maintenance on converter station equipment, after obtaining the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station, a series of processes such as preprocessing, feature extraction, and fusion processing are carried out. Based on the pre-trained equipment operation and maintenance instruction prediction model, the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed can be obtained quickly and directly. This helps to improve the efficiency of determining the equipment operation and maintenance instructions of the converter station equipment, thereby improving the operation and maintenance efficiency of the converter station equipment. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of the cumbersome manual inspection method, which requires a lot of time and manpower and leads to low operation and maintenance efficiency of the converter station equipment, further improving the operation and maintenance efficiency of the converter station equipment.

[0103] In an exemplary embodiment, step S101 above, obtaining the device information, target location information, and environmental information of the device to be analyzed in the converter station to be analyzed, specifically includes the following: obtaining the initial location information of the device to be analyzed in the converter station to be analyzed; converting the initial location information according to a preset correspondence to obtain the target location information; the preset correspondence is used to represent the correspondence between the initial location information and the target location information.

[0104] The initial position information is used to represent the coordinate information of the device to be analyzed in the camera coordinate system.

[0105] The preset correspondence is used to represent the correspondence between initial position information and target position information. In practical scenarios, the preset correspondence refers to the coordinate transformation relationship between LiDAR and camera.

[0106] For example, the server obtains the coordinate information of the device to be analyzed in the camera coordinate system as the initial position information of the device to be analyzed in the converter station to be analyzed; then, the server sets the correspondence between the initial position information and the target position information as a preset correspondence; then, the server performs transformation processing on the initial position information according to the preset correspondence to obtain the target position information.

[0107] In this embodiment, the initial position information is converted and processed according to a preset correspondence to obtain the target position information. This enables the initial position information in different formats or coordinate systems to be uniformly converted into target position information that meets the specific format requirements. This allows for data standardization throughout the analysis and avoids the defect that data processing is prone to errors due to inconsistent position information formats.

[0108] In an exemplary embodiment, step S103 above, which involves performing feature extraction processing on the preprocessed device information, preprocessed location information, and preprocessed environment information to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information, specifically includes the following: using the preprocessed device information as the primary data and the preprocessed location information and preprocessed environment information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain the first feature vector; using the preprocessed location information as the primary data and the preprocessed device information and preprocessed environment information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain the second feature vector; and using the preprocessed environment information as the primary data and the preprocessed device information and preprocessed location information as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain the third feature vector.

[0109] Among them, the main data can refer to the data with a relatively large weight.

[0110] Auxiliary data can refer to data with relatively small weights.

[0111] For example, the server uses preprocessed device information as primary data and preprocessed location information and preprocessed environment information as auxiliary data, inputs them into a feature extraction model for feature extraction processing, and obtains a feature vector corresponding to the preprocessed device information, which is used as the first feature vector; uses preprocessed location information as primary data and preprocessed device information and preprocessed environment information as auxiliary data, inputs them into a feature extraction model for feature extraction processing, and obtains a feature vector corresponding to the preprocessed location information, which is used as the second feature vector; uses preprocessed environment information as primary data and preprocessed device information and preprocessed location information as auxiliary data, inputs them into a feature extraction model for feature extraction processing, and obtains a feature vector corresponding to the preprocessed environment information, which is used as the third feature vector.

[0112] In this embodiment, during the feature extraction process of the preprocessed device information, preprocessed location information, and preprocessed environmental information, it is equivalent to considering multiple different types of data simultaneously, thereby making the extracted feature vectors more comprehensive and improving the accuracy of determining the feature vectors corresponding to the first, second, and third feature vectors.

[0113] In an exemplary embodiment, step S104 above, which fuses the first feature vector, the second feature vector, and the third feature vector to obtain a fused feature vector corresponding to the device to be analyzed, specifically includes the following: obtaining the first initial weight corresponding to the preprocessed device information, the second initial weight corresponding to the preprocessed location information, and the third initial weight corresponding to the preprocessed environment information; normalizing the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight corresponding to the preprocessed device information, the second target weight corresponding to the preprocessed location information, and the third target weight corresponding to the preprocessed environment information; and fusing the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain a fused feature vector.

[0114] The first initial weight refers to the weight initially assigned to the preprocessed device information.

[0115] The second initial weight refers to the weight initially assigned to the preprocessed location information.

[0116] The third initial weight refers to the weight initially assigned to the preprocessed environmental information.

[0117] The first target weight refers to the weight ultimately assigned to the preprocessed device information.

[0118] The second target weight refers to the weight assigned to the preprocessed location information.

[0119] The third objective weight refers to the final weight assigned to the preprocessed environmental information.

[0120] For example, the server determines a first initial weight corresponding to the preprocessed device information, a second initial weight corresponding to the preprocessed location information, and a third initial weight corresponding to the preprocessed environment information based on the respective importance of the preprocessed device information, preprocessed location information, and preprocessed environment information (e.g., determined through prior knowledge or experience). Then, the server normalizes the first, second, and third initial weights to obtain a first target weight corresponding to the preprocessed device information, a second target weight corresponding to the preprocessed location information, and a third target weight corresponding to the preprocessed environment information. For example, the first initial weight is 0.8, and the third target weight is... The initial weights are 0.6 and 0.6 respectively. After normalization, the first target weight corresponding to the preprocessed device information is 0.4, the second target weight corresponding to the preprocessed location information is 0.3, and the third target weight corresponding to the preprocessed environmental information is 0.3. Then, the server performs a fusion process on the first feature vector, the second feature vector, and the third feature vector based on the first target weight, the second target weight, and the third target weight to obtain a fused feature vector. For example, the server performs a weighted summation process on the first feature vector, the second feature vector, and the third feature vector based on the first target weight, the second target weight, and the third target weight to obtain the fused feature vector.

[0121] In this embodiment, by using target weights for fusion processing, a clear proportional relationship can be provided for different feature vectors during the fusion process, so that the resulting fused feature vector can accurately reflect the contribution of each piece of information, which is beneficial to improving the accuracy of the determination of the fused feature vector.

[0122] In an exemplary embodiment, before obtaining the equipment information, target location information, and environmental information of the device to be analyzed in the converter station to be analyzed, the above step S101 specifically includes the following: obtaining the voltage level information and equipment type information of the candidate converter stations; selecting candidate converter stations from each candidate converter station whose voltage level information and equipment type information both meet the preset conditions as the converter stations to be analyzed.

[0123] Among them, candidate converter stations refer to converter stations that are to be selected.

[0124] Among them, voltage level information refers to the voltage level of the candidate converter station, including high voltage, medium voltage, and low voltage.

[0125] Among them, equipment type information refers to the number of equipment types in the candidate converter station, such as 10.

[0126] The preset conditions refer to pre-defined judgment criteria used to determine voltage level and equipment type information. For example, the voltage level information is greater than or equal to medium voltage, and the equipment type information is greater than 5. It should be noted that the preset conditions can be determined as needed.

[0127] For example, the server extracts the voltage level information and equipment type information of the candidate converter stations from the converter station information of the candidate converter stations; then, the server selects the candidate converter stations whose voltage level information and equipment type information both meet the preset conditions from each candidate converter station, and uses these candidate converter stations as the converter stations to be analyzed.

[0128] In this embodiment, by acquiring the voltage level information and equipment type information of candidate converter stations and filtering them according to preset conditions, it is possible to accurately identify converter stations that meet the conditions from multiple candidate converter stations, thus avoiding wasting time and resources on analyzing irrelevant or unsuitable converter stations.

[0129] In an exemplary embodiment, the converter station equipment operation and maintenance method based on spatial computing provided in this application further includes a training step of a pre-trained equipment operation and maintenance instruction prediction model, specifically including the following: obtaining sample equipment information, sample location information, and sample environment information of sample equipment in a sample converter station; preprocessing the sample equipment information, sample location information, and sample environment information respectively to obtain preprocessed sample equipment information, preprocessed sample location information, and preprocessed sample environment information; performing feature extraction processing on the preprocessed sample equipment information, preprocessed sample location information, and preprocessed sample environment information respectively to obtain a first sample corresponding to the preprocessed sample equipment information. The system firstly analyzes the first sample feature vector, the second sample feature vector corresponding to the preprocessed sample location information, and the third sample feature vector corresponding to the preprocessed sample environment information. It then fuses these three feature vectors to obtain a fused feature vector corresponding to the sample device. This fused feature vector is input into the device maintenance instruction prediction model to be trained, yielding the predicted device maintenance instruction for the sample device. Finally, it acquires the actual device maintenance instruction corresponding to the sample device and iteratively trains the device maintenance instruction prediction model based on the difference between the predicted and actual instructions, resulting in a pre-trained device maintenance instruction prediction model.

[0130] Among them, the sample converter station refers to the converter station used to train the equipment operation and maintenance instruction prediction model.

[0131] Among them, sample equipment refers to converter station equipment used to train the equipment operation and maintenance instruction prediction model.

[0132] Among them, sample equipment information refers to the equipment information of the sample equipment.

[0133] Among them, sample location information refers to the location information of the sample device.

[0134] Among them, sample environment information refers to the environmental information of the sample equipment.

[0135] Among them, the preprocessed sample equipment information refers to the sample equipment information after preprocessing.

[0136] Among them, the preprocessed sample location information refers to the sample location information after preprocessing.

[0137] Among them, the preprocessed sample environment information refers to the sample environment information after preprocessing.

[0138] The first sample feature vector refers to the feature vector corresponding to the preprocessed sample device information.

[0139] The second sample feature vector refers to the feature vector corresponding to the sample location information after preprocessing.

[0140] Among them, the third sample feature vector refers to the feature vector corresponding to the preprocessed sample environment information.

[0141] Among them, the sample fusion feature vector refers to the feature vector obtained by fusing the first sample feature vector, the second sample feature vector, and the third sample feature vector.

[0142] Among them, the predicted equipment maintenance instructions refer to the predicted values ​​corresponding to the equipment maintenance instructions of the sample equipment.

[0143] Among them, the actual equipment operation and maintenance instructions refer to the actual values ​​corresponding to the equipment operation and maintenance instructions of the sample equipment.

[0144] For example, in response to a model training instruction for a device operation and maintenance instruction prediction model to be trained, the server retrieves sample device information, sample location information, and sample environment information of sample devices in the sample converter station from the database. Then, the server preprocesses the sample device information, sample location information, and sample environment information to obtain preprocessed sample device information, preprocessed sample location information, and preprocessed sample environment information. Next, the server performs feature extraction processing on the preprocessed sample device information, preprocessed sample location information, and preprocessed sample environment information to obtain a first sample feature vector corresponding to the preprocessed sample device information, a second sample feature vector corresponding to the preprocessed sample location information, and a third sample feature vector corresponding to the preprocessed sample environment information. Then, the server further processes the first sample feature vector, the second sample feature vector, and the third sample feature vector. The feature vector and the third sample feature vector are fused to obtain the sample fused feature vector corresponding to the sample device. Then, the server inputs the sample fused feature vector into the device operation and maintenance instruction prediction model to be trained to obtain the predicted device operation and maintenance instruction corresponding to the sample device. Next, the server obtains the actual device operation and maintenance instruction corresponding to the sample device and obtains the loss value based on the difference between the predicted device operation and maintenance instruction and the actual device operation and maintenance instruction. Then, the server adjusts the model parameters of the device operation and maintenance instruction prediction model to be trained based on the loss value. Then, the server retrains the device operation and maintenance instruction prediction model with adjusted model parameters until the loss value obtained by the trained device operation and maintenance instruction prediction model is less than the loss value threshold. At this point, training stops, and the trained device operation and maintenance instruction prediction model is used as the pre-trained device operation and maintenance instruction prediction model.

[0145] In this embodiment, by pre-training the equipment operation and maintenance instruction prediction model, it is convenient to predict the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed after obtaining the fused feature vector corresponding to the equipment to be analyzed in practical applications. Moreover, the equipment operation and maintenance instruction prediction model receives new data in each iteration, and performs internal model improvement and optimization, which makes it easier to make predictions more effectively and improves the prediction accuracy of the equipment operation and maintenance instruction prediction model.

[0146] In an exemplary embodiment, as shown in Figure 2, another method for the operation and maintenance of converter station equipment based on spatial computing is provided. Taking the application of this method to a server as an example, it includes the following steps:

[0147] Step S201: Obtain the voltage level information and equipment type information of the candidate converter stations; from each candidate converter station, select the candidate converter stations whose voltage level information and equipment type information both meet the preset conditions, and use them as the converter stations to be analyzed.

[0148] Step S202: Obtain the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed.

[0149] Step S203: Preprocess the device information, target location information, and environmental information respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information.

[0150] Step S204: The preprocessed device information is used as the main data, and the preprocessed location information and preprocessed environmental information are used as auxiliary data. The data are input into the feature extraction model for feature extraction processing to obtain the first feature vector.

[0151] Step S205: The preprocessed location information is used as the main data, and the preprocessed device information and preprocessed environmental information are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the second feature vector.

[0152] Step S206: The preprocessed environmental information is used as the main data, and the preprocessed device information and preprocessed location information are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the third feature vector.

[0153] Step S207: Obtain the first initial weight corresponding to the preprocessed device information, the second initial weight corresponding to the preprocessed location information, and the third initial weight corresponding to the preprocessed environmental information.

[0154] Step S208: Normalize the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight corresponding to the preprocessed device information, the second target weight corresponding to the preprocessed location information, and the third target weight corresponding to the preprocessed environmental information.

[0155] Step S209: Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector.

[0156] Step S210: Input the fused feature vector into the pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction corresponding to the equipment to be analyzed.

[0157] Step S211: Perform corresponding maintenance procedures on the device to be analyzed according to the target device maintenance instructions.

[0158] In the aforementioned spatial computing-based converter station equipment operation and maintenance method, after obtaining the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station, a series of processes such as preprocessing, feature extraction, and fusion processing are performed. Based on a pre-trained equipment operation and maintenance instruction prediction model, the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed can be quickly and directly obtained. This is beneficial to improving the efficiency of determining the equipment operation and maintenance instructions of the converter station equipment, thereby improving the operation and maintenance efficiency of the converter station equipment. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of the cumbersome manual inspection method, which requires a lot of time and manpower and leads to low operation and maintenance efficiency of the converter station equipment, further improving the operation and maintenance efficiency of the converter station equipment.

[0159] In an exemplary embodiment, to more clearly illustrate the spatial computing-based converter station equipment operation and maintenance method provided in this application, the following specific embodiment will be used to describe the spatial computing-based converter station equipment operation and maintenance method in detail. In one embodiment, this application also provides a spatial computing-based intelligent interaction technology for converter station equipment operation and maintenance information. When performing operation and maintenance processing on converter station equipment, the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed are first obtained. The equipment information, target location information, and environmental information are then preprocessed to obtain preprocessed equipment information, preprocessed location information, and preprocessed environmental information. Based on the preprocessed equipment information, preprocessed location information, and preprocessed environmental information, corresponding operation and maintenance processing is performed on the equipment to be analyzed. Specifically, this includes the following:

[0160] The intelligent interactive platform for converter station equipment operation and maintenance information involved in this solution utilizes spatial computing technology to provide a visualized, interactive, and automated operation and maintenance solution for converter station equipment. This intelligent interactive platform mainly consists of three parts: a data acquisition module, a data processing module, and an intelligent interaction module. Its overall structure is shown in Figure 3.

[0161] (1) Data acquisition module: used to drive the sensor and transmit the sensor data to the data processing module.

[0162] (2) Data processing module: used to process and merge the data collected by the data acquisition module and generate a high-precision model of the converter station equipment that can be viewed.

[0163] (3) Intelligent Interaction Module: Staff can use intelligent mobile devices to realize intelligent operation and maintenance of converter station equipment in the intelligent interaction module.

[0164] To ensure the quality of the 3D reconstruction of the converter station, multi-view data of the key equipment is required. Therefore, this solution uses binocular stereo vision with two cameras to acquire 2D images. Each camera corresponds to a different viewpoint, acquiring structural data from that viewpoint. Finally, the data acquired by the two cameras are unified into the same coordinate system to generate global 3D point cloud data. The principle of binocular stereo vision triangulation is shown in Figure 4.

[0165] In Figure 4, O1-X1Y1Z1 and O2-X2Y2Z2 are the coordinate systems of the left and right cameras, respectively, and O1′-X1Y1 and O2′-X2Y2 are the coordinate systems of the left and right images, respectively. The origins O1 and O2 are the optical centers of the two cameras, and O1Z1 and O2Z2 are the optical axes of the two cameras. Assuming that any point P in the device under test is connected to O1 and O2 respectively, the projected coordinates of point P on the planes O1′-X1Y1 and O2′-X2Y2 are P1(x1, y1) and P2(x2, y2) respectively. Assuming that the world coordinate system coincides with the coordinate system of the left camera, the right camera can be approximated as a monocular camera model. The rotation matrix R and translation matrix t of the camera can be obtained through camera calibration. Combining the projection transformation formula, the three-dimensional coordinates of point P in the world coordinate system can be obtained as shown in equations (1) and (2).

[0166] or

[0167] In the formula, f1 and f2 are the focal lengths of the camera, and r i (i = 1, 2, ..., 9) are rotational components; t x , t y , t z The translation component is used. Therefore, the three-dimensional coordinates of any point in space can be obtained using the binocular vision theoretical model.

[0168] This solution fully utilizes LiDAR to first scan key equipment within the converter station, obtaining complete point cloud data. Specifically, the LiDAR rotates at a constant speed while continuously emitting infrared lasers, simultaneously receiving laser signals from reflection points, including distance, time, and horizontal angle. Each transmitter corresponds to a vertical angle, and these variable data allow for the acquisition of the positional information of the corresponding reflection point. The collection of coordinates of all reflection points gathered by the LiDAR during its 360° rotation becomes the point cloud, thus providing comprehensive environmental information.

[0169] Point cloud data acquired by LiDAR can be represented in spherical coordinates (R, ω, α). Here, ω is the pitch angle, a fixed value, and R and α are the distance and azimuth of the LiDAR from the point cloud data, respectively. For subsequent data processing, it is usually necessary to transform this point cloud data from the spherical coordinate system to a Cartesian spatial coordinate system, as illustrated in Figure 5.

[0170] The coordinate system transformation formula is:

[0171] Through the coordinate system transformation above, the data acquired by LiDAR can ultimately be described in form as a set of multidimensional points, where each point p i All can be represented by equation (4). Where x i y i , z i s represents the three-dimensional position coordinates of the point cloud data. i Indicates the intensity of reflection. p i ={x i ,y i ,z i ,s i Equation (4)

[0172] A point cloud dataset P containing n points can be represented by equation (5). P = {p1, p2, p3, ..., p...} n Equation (5)

[0173] Since the data acquisition module obtains point cloud data, which is sampled from objects in a real scene, the scanning and sampling process is inevitably affected by external factors such as environmental elements and the surface shape and texture of the target object. Therefore, errors and noise are unavoidable in the point cloud data, along with other irrelevant point clouds and redundant data. Thus, preprocessing of the point cloud data is necessary. Point cloud data preprocessing generally includes the following steps: noise removal, multi-view alignment, data simplification, and surface reconstruction.

[0174] (1) Noise removal refers to removing data other than the scanned object from the point cloud data. During the scanning process, due to the influence of certain environmental factors, such as people in the surrounding area, the scanner may also collect data. Therefore, this data needs to be deleted in the post-processing stage.

[0175] (2) Multi-view alignment refers to the process where, due to the large size or complex shape of the object being measured, it is often impossible to measure all the data at once during scanning. Instead, multiple scans from different positions and multiple perspectives are required. These point clouds need to be aligned and stitched together, which is called multi-view alignment. Point cloud alignment and stitching can be achieved by setting up control points with the same name on the surface of the object.

[0176] (3) Data simplification refers to the need to simplify point cloud data, which is a massive amount of data, without affecting surface reconstruction and maintaining a certain level of accuracy.

[0177] (4) Surface reconstruction refers to representing the scanned data with an accurate surface. After surface reconstruction, three-dimensional modeling can be performed to restore the original appearance of the scanned target.

[0178] Since data based on binocular stereo vision triangulation is easily affected by factors such as lighting and background interference, LiDAR target detection results are used to correct the acquired data and improve the accuracy of model data acquisition. Specifically, the relationship between the camera and LiDAR three-dimensional coordinates is established to realize the conversion between the two three-dimensional coordinates in the joint measurement system.

[0179] Suppose there is a point P in space. i (i = 1, 2, ..., n), if a LiDAR measurement system is used, use P li =(X li Y li Z li ) represents a spatial point P i Three-dimensional coordinates in the LiDAR measurement system coordinate system; if using a binocular stereo vision system, use P. ci =(X ci Y ci Z ci ) represents a spatial point P i Three-dimensional coordinates in a binocular stereo vision system. When performing joint measurement system data fusion, it is necessary to determine the correspondence between the coordinate systems of the two sensors.

[0180] The coordinate transformation process can generally be divided into three steps:

[0181] (1) The transformation from the LiDAR coordinate system to the camera coordinate system can be represented by the rotation transformation matrix R and the translation transformation matrix T. Wherein, R is a 3×3 matrix, representing the rotation of the spatial coordinates; T is a 3×1 matrix, representing the translation of the spatial coordinates. The transformation process is shown in Equation (6).

[0182] (2) The transformation from the camera coordinate system to the image coordinate system is a process of transforming from a three-dimensional coordinate system to a two-dimensional coordinate system. This is a perspective projection relationship and satisfies the similarity theorem of triangles. The transformation process is shown in equation (7).

[0183] (3) The transformation from the image coordinate system to the pixel coordinate system does not involve rotation transformation, but the position of the origin and the unit length are different. It mainly involves scaling transformation and translation transformation. The transformation process is shown in equation (8).

[0184] In summary, the coordinate transformation relationship between LiDAR and camera can be expressed as:

[0185] Intelligent operations include remote operation of converter station equipment, as well as equipment assembly, maintenance, and other business scenarios. Its objectives are as follows:

[0186] (1) During equipment assembly and maintenance, staff can receive guidance and assistance from auxiliary equipment at any time through rich and good human-machine interaction, so as to improve work efficiency and reliability.

[0187] (2) Remote operation of equipment: The original background judgment method and intelligent image recognition, infrared sensing, pressure sensing and other automatic methods are used to judge whether the remote operation is in place, so as to realize the automatic programming of switching operation and the unmanned operation on site.

[0188] The overall technical roadmap for the intelligent interaction module is shown in Figure 6.

[0189] As shown in Figure 6, the overall technical approach of the intelligent interaction module is divided into two levels: intelligent operation assistance and operation result recognition.

[0190] Intelligent assistance for tasks includes two aspects:

[0191] (1) Staff members can obtain real-time information on equipment, environment and location during the operation by wearing smart equipment and operation assistance devices, and display the operation process and operation status on the smart equipment to provide operation assistance information for staff members.

[0192] (2) Staff members can interact with remote collaborative staff in real time via voice and video through auxiliary devices to conduct remote operation control, operation guidance, and task collaboration. The specific technical solution is shown in Figure 7.

[0193] First, AR technology is used to guide staff in completing maintenance and repair work in a standardized and regulated manner in real time. Throughout the process, staff wear smart devices that identify equipment nameplates and pressure plates, overlaying equipment information onto their actual field of vision to improve work efficiency.

[0194] Secondly, during the inspection process, wearable smart devices can obtain specific task information from the production management system through automatic and manual methods, and synchronize the inspection work instructions to the intelligent interactive platform. Staff can receive and execute tasks through smart devices, and use AR technology to project virtual indicator labels in real-world scenarios to provide clear work guidance to staff, effectively improving work quality.

[0195] During cross-regional, multi-person mobile maintenance operations, real-time interaction of voice and video information is achieved through wearable smart devices.

[0196] On-site staff wear smart devices to inspect power equipment. When interacting with back-end staff, they can transmit observed equipment and environmental information to the monitoring center via video images. Back-end staff can then use the smart devices to monitor the on-site operations and overlay virtual information, such as text, images, or animations, to guide on-site staff in their operations.

[0197] Traditional converter station equipment operation involves multiple stages, including pre-operation preparation, ticket filling, departure, arrival at the site, receiving orders, simulation rehearsal, formal operation, and completion reporting. In intelligent converter stations, however, the automated system can automatically complete a series of circuit breaker and disconnector operations based on pre-set operational logic, enabling complex on-site operations to be completed remotely with a single click. The entire operation process requires no additional manual intervention, significantly reducing labor intensity, greatly improving operational efficiency, and effectively lowering operational safety risks.

[0198] Operation result recognition technology is mainly applied in remote operation scenarios of converter station equipment to identify the actions of primary and secondary equipment and determine whether each operation step is completed correctly. To improve the accuracy of operation result recognition, at least two non-coordinated signals are often required for double confirmation. This paper takes switchgear in power equipment as a typical application scenario, and its operation result recognition technology framework is shown in Figure 8.

[0199] As shown in Figure 8, the real-time monitoring module for on-site information mainly consists of the following parts:

[0200] (1) Infrared sensor, used to monitor contact temperature signal. The infrared temperature probe is installed on the internal circuit board under the infrared glass. By monitoring the contact temperature, it can be detected in time whether the disconnecting switch has completed closing;

[0201] (2) Pressure sensor, used to monitor sudden changes in contact pressure. A pressure sensor is installed at the contact position of the disconnecting switch to measure the pressure during opening and closing, and the pressure value reflects the opening and closing status;

[0202] (3) The image monitoring device acquires images of the disconnect switch in real time, monitors the actual mechanical position of the disconnect switch, and accurately identifies the status of the disconnect switch.

[0203] The methods described above enable a direct, effective, and realistic perception of the results of remote operations. This provides technical support for a dual-confirmation mechanism for non-homogeneous signals in operation results.

[0204] In the above embodiments, when performing operation and maintenance on converter station equipment, after obtaining the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station, a series of processes such as preprocessing, feature extraction, and fusion processing are performed. Based on a pre-trained equipment operation and maintenance instruction prediction model, the target equipment operation and maintenance instructions corresponding to the equipment to be analyzed can be quickly and directly obtained. This is beneficial to improving the efficiency of determining the equipment operation and maintenance instructions of the converter station equipment, thereby improving the operation and maintenance efficiency of the converter station equipment. Moreover, the entire process does not require manual intervention, avoiding the shortcomings of the cumbersome manual inspection method, which requires a lot of time and manpower and leads to low operation and maintenance efficiency of the converter station equipment, further improving the operation and maintenance efficiency of the converter station equipment.

[0205] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0206] Based on the same inventive concept, this application also provides a space-computation-based converter station equipment operation and maintenance device for implementing the aforementioned space-computation-based converter station equipment operation and maintenance method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more space-computation-based converter station equipment operation and maintenance device embodiments provided below can be found in the limitations of the space-computation-based converter station equipment operation and maintenance method described above, and will not be repeated here.

[0207] In an exemplary embodiment, as shown in FIG9, a converter station equipment operation and maintenance device based on spatial computing is provided, including: an information acquisition module 901, an information processing module 902, a feature extraction module 903, a feature fusion module 904, an instruction prediction module 905, and an equipment operation and maintenance module 906, wherein:

[0208] The information acquisition module 901 is used to acquire equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed.

[0209] The information processing module 902 is used to preprocess the equipment information, target location information and environmental information respectively to obtain preprocessed equipment information, preprocessed location information and preprocessed environmental information.

[0210] The feature extraction module 903 is used to perform feature extraction processing on the preprocessed device information, preprocessed location information and preprocessed environment information respectively, to obtain the first feature vector corresponding to the preprocessed device information, the second feature vector corresponding to the preprocessed location information and the third feature vector corresponding to the preprocessed environment information.

[0211] The feature fusion module 904 is used to fuse the first feature vector, the second feature vector and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed.

[0212] The instruction prediction module 905 is used to input the fused feature vector into the pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction corresponding to the equipment to be analyzed.

[0213] The equipment operation and maintenance module 906 is used to perform corresponding operation and maintenance processing on the equipment to be analyzed according to the operation and maintenance instructions of the target equipment.

[0214] In an exemplary embodiment, the information acquisition module 901 is further configured to acquire the initial position information of the device to be analyzed in the converter station to be analyzed; and to convert the initial position information according to a preset correspondence to obtain the target position information; the preset correspondence is used to represent the correspondence between the initial position information and the target position information.

[0215] In an exemplary embodiment, the feature extraction module 903 is further configured to input the preprocessed device information as primary data, and the preprocessed location information and preprocessed environment information as auxiliary data into the feature extraction model for feature extraction processing to obtain a first feature vector; input the preprocessed location information as primary data, and the preprocessed device information and preprocessed environment information as auxiliary data into the feature extraction model for feature extraction processing to obtain a second feature vector; and input the preprocessed environment information as primary data, and the preprocessed device information and preprocessed location information as auxiliary data into the feature extraction model for feature extraction processing to obtain a third feature vector.

[0216] In an exemplary embodiment, the feature fusion module 904 is further configured to obtain a first initial weight corresponding to the preprocessed device information, a second initial weight corresponding to the preprocessed location information, and a third initial weight corresponding to the preprocessed environment information; normalize the first initial weight, the second initial weight, and the third initial weight to obtain a first target weight corresponding to the preprocessed device information, a second target weight corresponding to the preprocessed location information, and a third target weight corresponding to the preprocessed environment information; and fuse the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain a fused feature vector.

[0217] In an exemplary embodiment, the converter station equipment operation and maintenance device based on spatial computing further includes a converter station determination module, which is used to obtain the voltage level information and equipment type information of candidate converter stations; and select candidate converter stations from each candidate converter station whose voltage level information and equipment type information both meet the preset conditions as the converter stations to be analyzed.

[0218] In an exemplary embodiment, the converter station equipment operation and maintenance device based on spatial computing further includes a model training module, used to acquire sample equipment information, sample location information, and sample environment information of sample equipment in the sample converter station; preprocess the sample equipment information, sample location information, and sample environment information respectively to obtain preprocessed sample equipment information, preprocessed sample location information, and preprocessed sample environment information; and perform feature extraction processing on the preprocessed sample equipment information, preprocessed sample location information, and preprocessed sample environment information respectively to obtain the first sample feature vector and the preprocessed sample location corresponding to the preprocessed sample equipment information. The first sample feature vector corresponds to the second sample feature vector and the third sample feature vector corresponds to the preprocessed sample environment information. The first sample feature vector, the second sample feature vector and the third sample feature vector are fused to obtain the sample fused feature vector corresponding to the sample device. The sample fused feature vector is input into the device operation and maintenance instruction prediction model to be trained to obtain the predicted device operation and maintenance instruction corresponding to the sample device. The actual device operation and maintenance instruction corresponding to the sample device is obtained, and the device operation and maintenance instruction prediction model to be trained is iteratively trained according to the difference between the predicted device operation and maintenance instruction and the actual device operation and maintenance instruction to obtain the pre-trained device operation and maintenance instruction prediction model.

[0219] The modules in the aforementioned space-computing-based converter station equipment operation and maintenance device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0220] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 10. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores data such as device information, target location information, and environmental information. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a converter station equipment operation and maintenance method based on spatial computing.

[0221] Those skilled in the art will understand that the structure shown in Figure 10 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0222] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0223] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0224] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0225] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media 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), 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0226] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0227] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A converter station equipment operation and maintenance method based on spatial computing, characterized in that, The method includes: Obtain equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed; The device information, the target location information, and the environmental information are preprocessed respectively to obtain preprocessed device information, preprocessed location information, and preprocessed environmental information. Feature extraction processing is performed on the preprocessed device information, the preprocessed location information, and the preprocessed environment information respectively to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information; The first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector corresponding to the device to be analyzed. The fused feature vector is input into a pre-trained device operation and maintenance instruction prediction model to obtain the target device operation and maintenance instruction corresponding to the device to be analyzed. According to the target device operation and maintenance instructions, perform corresponding operation and maintenance processing on the device to be analyzed.

2. The method according to claim 1, characterized in that, The acquisition of equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed includes: Obtain the initial position information of the equipment to be analyzed in the converter station to be analyzed; The initial location information is transformed according to a preset correspondence to obtain the target location information; the preset correspondence is used to represent the correspondence between the initial location information and the target location information.

3. The method according to claim 1, characterized in that, The step of performing feature extraction processing on the preprocessed device information, the preprocessed location information, and the preprocessed environment information to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information, and a third feature vector corresponding to the preprocessed environment information includes: The preprocessed device information is used as the main data, and the preprocessed location information and the preprocessed environmental information are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the first feature vector. The preprocessed location information is used as the main data, and the preprocessed device information and the preprocessed environmental information are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the second feature vector. The preprocessed environmental information is used as the primary data, and the preprocessed device information and the preprocessed location information are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the third feature vector.

4. The method according to claim 1, characterized in that, The step of fusing the first feature vector, the second feature vector, and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed includes: Obtain the first initial weight corresponding to the preprocessed device information, the second initial weight corresponding to the preprocessed location information, and the third initial weight corresponding to the preprocessed environmental information; The first initial weight, the second initial weight, and the third initial weight are normalized to obtain the first target weight corresponding to the preprocessed device information, the second target weight corresponding to the preprocessed location information, and the third target weight corresponding to the preprocessed environmental information. Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are fused to obtain the fused feature vector.

5. The method according to claim 1, characterized in that, Before obtaining the equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed, the following is also included: Obtain voltage level and equipment type information for candidate converter stations; From the candidate converter stations, those that meet the preset conditions in both voltage level information and equipment type information are selected as the converter stations to be analyzed.

6. The method according to any one of claims 1 to 5, wherein the pre-trained equipment operation and maintenance instruction prediction model is trained in the following manner: Obtain sample equipment information, sample location information, and sample environment information from the sample converter station; The sample device information, the sample location information, and the sample environment information are preprocessed respectively to obtain preprocessed sample device information, preprocessed sample location information, and preprocessed sample environment information. Feature extraction processing is performed on the preprocessed sample device information, the preprocessed sample location information, and the preprocessed sample environment information respectively to obtain a first sample feature vector corresponding to the preprocessed sample device information, a second sample feature vector corresponding to the preprocessed sample location information, and a third sample feature vector corresponding to the preprocessed sample environment information. The first sample feature vector, the second sample feature vector, and the third sample feature vector are fused to obtain the sample fused feature vector corresponding to the sample device. The sample fusion feature vector is input into the equipment operation and maintenance instruction prediction model to be trained to obtain the predicted equipment operation and maintenance instructions corresponding to the sample equipment. Obtain the actual equipment operation and maintenance instructions corresponding to the sample equipment, and iteratively train the equipment operation and maintenance instruction prediction model to be trained based on the difference between the predicted equipment operation and maintenance instructions and the actual equipment operation and maintenance instructions to obtain the pre-trained equipment operation and maintenance instruction prediction model.

7. A converter station equipment operation and maintenance device based on spatial computing, characterized in that, The device includes: The information acquisition module is used to acquire equipment information, target location information, and environmental information of the equipment to be analyzed in the converter station to be analyzed; The information processing module is used to preprocess the device information, the target location information and the environmental information respectively to obtain preprocessed device information, preprocessed location information and preprocessed environmental information; The feature extraction module is used to perform feature extraction processing on the preprocessed device information, the preprocessed location information and the preprocessed environment information respectively, to obtain a first feature vector corresponding to the preprocessed device information, a second feature vector corresponding to the preprocessed location information and a third feature vector corresponding to the preprocessed environment information; The feature fusion module is used to fuse the first feature vector, the second feature vector and the third feature vector to obtain the fused feature vector corresponding to the device to be analyzed. The instruction prediction module is used to input the fused feature vector into a pre-trained equipment operation and maintenance instruction prediction model to obtain the target equipment operation and maintenance instruction corresponding to the equipment to be analyzed. The equipment operation and maintenance module is used to perform corresponding operation and maintenance processing on the equipment to be analyzed according to the target equipment operation and maintenance instructions.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

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

Images