Icing information updating method and device, computer equipment and computer storage medium

Abstract

The invention relates to an icing information updating method and device, computer equipment and a computer storage medium. The method comprises the steps of obtaining meteorological data, topographic data and icing thickness, inputting the meteorological data, the topographic data and the icing thickness into a clustering model, obtaining a meteorological similarity degree according to a first meteorological weight and the meteorological data, obtaining a topographic similarity degree according to a first topographic weight and the topographic data, and performing clustering by using the meteorological similarity degree, the topographic similarity degree and the icing thickness to obtain a clustering result; the method comprises the following steps: obtaining icing similar area information, inputting meteorological data, topographic data and the icing similar area information into a prediction model, updating a weight acquisition module in the prediction model, obtaining a second meteorological weight and a second topographic weight, and obtaining an updated icing thickness according to the information. And taking the second meteorological weight as the first meteorological weight, the second terrain weight as the first terrain weight and the updated icing thickness as the icing thickness, and returning to execute the previous steps. By adopting the method, the accuracy of the icing information and the environment adaptability can be improved.

Description

Technical Field

[0001] The present application relates to the field of remote sensing technology, and in particular to an ice cover information updating method, device, computer equipment, computer readable storage medium and computer program product. Background Art

[0002] In winter, ice on transmission lines is a common natural phenomenon. However, ice on conductors can cause disasters such as overload, ice flash, ice dancing, and ice shedding jumping, which can lead to conductor breakage, electrical failures, and line failures, which may seriously endanger the safe and stable operation of the power grid. Therefore, it is very important to carry out targeted ice treatment in iced areas.

[0003] In this regard, an ice model drawing method is proposed, that is, through the ice meteorological data observed by the regional ice observation station or meteorological station, a relationship model between ice and terrain is established for drawing. A transmission line ice prediction model based on statistical methods is proposed, that is, through mathematical statistical methods, the linear relationship between factors such as temperature and wind speed and the ice thickness of the transmission line is obtained, and then prediction is made.

[0004] However, the existing ice cover model drawing method has the problem that the ice cover information is not accurate enough. Summary of the invention

[0005] Based on this, it is necessary to provide an icing information updating method, apparatus, computer equipment, computer readable storage medium and computer program product that can improve the accuracy of icing information in order to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for updating ice coverage information, comprising:

[0007] Obtain meteorological data and terrain data of the power transmission lines in each area, and obtain the ice thickness of the power transmission lines in each area;

[0008] Inputting meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtaining the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similarity zone clustering model, and obtaining the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similarity zone clustering model;

[0009] Using the similarity of meteorology, terrain and ice thickness, each region is clustered to obtain the ice-covered similarity area information corresponding to each region;

[0010] Inputting meteorological data, terrain data and ice-covered similar area information into a pre-built ice thickness prediction model, using the ice-covered similar area information to update the attention weight acquisition module of the ice thickness prediction model, and obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module;

[0011] According to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight, an updated ice thickness of the transmission lines in each area is obtained;

[0012] The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice cover thickness is used as the new ice cover thickness, and the step of inputting the meteorological data, terrain data and ice cover thickness into the pre-built ice cover similarity area clustering model is returned to obtain the updated ice cover similarity area information of each area.

[0013] In one embodiment, obtaining ice thickness of power transmission lines in each area includes:

[0014] Obtain the actual ice thickness monitored by user terminals on the transmission lines in each area;

[0015] The meteorological data is input into a pre-built ice thickness simulation model, and the simulated ice thickness is obtained through the ice thickness simulation model;

[0016] When the difference between the simulated ice coating thickness and the actual ice coating thickness is less than a preset difference threshold, the actual ice coating thickness and the simulated ice coating thickness are determined as the ice coating thickness.

[0017] In one embodiment, the method includes:

[0018] Determine the area to be optimized from each area according to the updated ice thickness, and obtain the layout information of the user terminals on the transmission line in the area to be optimized;

[0019] The layout information is adjusted using the NSGA-II algorithm to obtain multiple layout schemes for user terminals;

[0020] Obtaining a corresponding objective function value according to the layout information of the user terminal in the layout scheme, and determining the layout scheme corresponding to the minimum objective function value as the target layout scheme;

[0021] According to the layout information of the user terminals in the target layout plan, the user terminals on the transmission lines in the area to be optimized are rearranged.

[0022] In one embodiment, the method further comprises:

[0023] Obtain updated layout information of user terminals on transmission lines in each area, and display the updated layout information of user terminals in the form of highlights on the map, as well as display the real-time ice thickness monitored by each user terminal.

[0024] In an exemplary embodiment, obtaining meteorological data and terrain data of power transmission lines in each area includes:

[0025] Obtain original meteorological data and original terrain data of power transmission lines in each area;

[0026] Remove blank data and duplicate data from the original meteorological data and original terrain data to obtain cleaned original meteorological data and original terrain data;

[0027] The cleaned original meteorological data and original terrain data are subjected to data dimension reduction and converted into a unified data format to obtain meteorological data and terrain data.

[0028] In one embodiment, the method includes:

[0029] When the step of inputting the meteorological data, the terrain data and the ice thickness into the pre-built ice similarity zone clustering model is returned and the preset return number threshold is reached, the last ice similarity zone division information and ice thickness are obtained;

[0030] Divide each area according to the last ice-covered similar area information to obtain multiple ice-covered similar areas;

[0031] Based on the ice thickness corresponding to each ice-covered similar area, determine the ice-covered magnitude information corresponding to each ice-covered similar area;

[0032] The map displays similar ice-covered areas in different colors, and also displays the corresponding ice-covered magnitude information for each similar ice-covered area.

[0033] In a second aspect, the present application also provides an ice coverage information updating device, comprising:

[0034] A data acquisition module is used to acquire meteorological data and terrain data of the power transmission lines in each area, and to acquire the ice thickness of the power transmission lines in each area;

[0035] The similarity zone information determination module is used to input meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similar zone clustering model, obtain the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similar zone clustering model, and obtain the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similar zone clustering model; cluster the regions using the meteorological similarity, terrain similarity and ice thickness to obtain the ice-covered similar zone information corresponding to each region;

[0036] A thickness updating module is used to input meteorological data, terrain data and ice-covered similar area information into a pre-built ice-covered thickness prediction model, and use the ice-covered similar area information to update the attention weight acquisition module of the ice-covered thickness prediction model, and obtain the second meteorological weight and the second terrain weight through the updated attention weight acquisition module; according to the meteorological data, terrain data, the second meteorological weight and the second terrain weight, the updated ice thickness of the transmission lines in each area is obtained;

[0037] The updating module is used to use the second meteorological weight as the new first meteorological weight, the second terrain weight as the new first terrain weight, and the updated ice thickness as the new ice thickness, and return to execute the step of inputting the meteorological data, terrain data and ice thickness into the pre-built ice similarity area clustering model to obtain the updated ice similarity area information of each area.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Obtain meteorological data and terrain data of the power transmission lines in each area, and obtain the ice thickness of the power transmission lines in each area;

[0040] Inputting meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtaining the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similarity zone clustering model, and obtaining the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similarity zone clustering model;

[0041] Using the similarity of meteorology, terrain and ice thickness, each region is clustered to obtain the ice-covered similarity area information corresponding to each region;

[0042] Inputting meteorological data, terrain data and ice-covered similar area information into a pre-built ice thickness prediction model, using the ice-covered similar area information to update the attention weight acquisition module of the ice thickness prediction model, and obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module;

[0043] According to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight, an updated ice thickness of the transmission lines in each area is obtained;

[0044] The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice cover thickness is used as the new ice cover thickness, and the step of inputting the meteorological data, terrain data and ice cover thickness into the pre-built ice cover similarity area clustering model is returned to obtain the updated ice cover similarity area information of each area.

[0045] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Obtain meteorological data and terrain data of the power transmission lines in each area, and obtain the ice thickness of the power transmission lines in each area;

[0047] Inputting meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtaining the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similarity zone clustering model, and obtaining the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similarity zone clustering model;

[0048] Using the similarity of meteorology, terrain and ice thickness, each region is clustered to obtain the ice-covered similarity area information corresponding to each region;

[0049] Inputting meteorological data, terrain data and ice-covered similar area information into a pre-built ice thickness prediction model, using the ice-covered similar area information to update the attention weight acquisition module of the ice thickness prediction model, and obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module;

[0050] According to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight, an updated ice thickness of the transmission lines in each area is obtained;

[0051] The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice cover thickness is used as the new ice cover thickness, and the step of inputting the meteorological data, terrain data and ice cover thickness into the pre-built ice cover similarity area clustering model is returned to obtain the updated ice cover similarity area information of each area.

[0052] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0053] Obtain meteorological data and terrain data of the power transmission lines in each area, and obtain the ice thickness of the power transmission lines in each area;

[0054] Inputting meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtaining the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similarity zone clustering model, and obtaining the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similarity zone clustering model;

[0055] Using the similarity of meteorology, terrain and ice thickness, each region is clustered to obtain the ice-covered similarity area information corresponding to each region;

[0056] Inputting meteorological data, terrain data and ice-covered similar area information into a pre-built ice thickness prediction model, using the ice-covered similar area information to update the attention weight acquisition module of the ice thickness prediction model, and obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module;

[0057] According to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight, an updated ice thickness of the transmission lines in each area is obtained;

[0058] The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice cover thickness is used as the new ice cover thickness, and the step of inputting the meteorological data, terrain data and ice cover thickness into the pre-built ice cover similarity area clustering model is returned to obtain the updated ice cover similarity area information of each area.

[0059] The above-mentioned ice cover information updating method, device, computer equipment, computer-readable storage medium and computer program product obtain the meteorological data and terrain data of the transmission lines in each area, and obtain the ice cover thickness of the transmission lines in each area, input the meteorological data, terrain data and ice cover thickness into a pre-constructed ice cover similarity zone clustering model, obtain the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice cover similarity zone clustering model, and obtain the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice cover similarity zone clustering model, cluster the regions using the meteorological similarity, terrain similarity and ice cover thickness to obtain the ice cover similarity zone information corresponding to each region, and input the meteorological data, terrain data and ice cover thickness into a pre-constructed ice cover similarity zone clustering model, and obtain the meteorological similarity between the regions according to the first terrain weight and terrain data preset in the ice cover similarity zone clustering model. The terrain data and ice-covered similar area information are input into a pre-built ice-covered thickness prediction model, and the attention weight acquisition module of the ice-covered thickness prediction model is updated using the ice-covered similar area information. The second meteorological weight and the second terrain weight are obtained through the updated attention weight acquisition module. The updated ice-covered thickness of the transmission lines in each area is obtained according to the meteorological data, terrain data, the second meteorological weight and the second terrain weight. The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice-covered thickness is used as the new ice-covered thickness. The step of inputting the meteorological data, terrain data and ice-covered thickness data into the pre-built ice-covered similar area clustering model is returned to execute, and the updated ice-covered similar area information of each area is obtained. Through the feedback update mechanism of the above-mentioned model output results and weight information, the iterative update of the ice-covered information output by the two models is realized, thereby improving the correlation and accuracy between the ice-covered information. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A diagram showing an application environment of an ice coverage information updating method in an embodiment;

[0062] Figure 2 It is a flowchart of an ice coverage information updating method in one embodiment;

[0063] Figure 3 A schematic diagram of a process for obtaining ice thickness in one embodiment;

[0064] Figure 4 is a flow chart of an ice coverage information updating method in another embodiment;

[0065] Figure 5 A schematic diagram of interactive updates between models in one embodiment;

[0066] Figure 6 is a structural block diagram of an ice coverage information updating device in one embodiment;

[0067] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] The ice coverage information updating method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. In each area, a transmission line for transmitting electricity is laid, and some nodes of the transmission line are equipped with user terminals for monitoring the ice thickness of the line. Each area is also equipped with a meteorological station for meteorological monitoring. The user terminals and meteorological stations in each area communicate with the server 102 through the network, and the server 102 can also obtain data monitored by satellite remote sensing. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. The server 102 obtains the meteorological data and terrain data of the power transmission lines in each area through the communication network, as well as the ice thickness of the power transmission lines in each area, inputs the meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtains the meteorological similarity between the areas according to the first meteorological weight and meteorological data preset in the ice-covered similarity zone clustering model, and obtains the terrain similarity between the areas according to the first terrain weight and terrain data preset in the ice-covered similarity zone clustering model, clusters the areas using the meteorological similarity, terrain similarity and ice thickness, obtains the ice-covered similarity zone information corresponding to each area, and inputs the meteorological data, terrain data and ice-covered similarity zone information into a pre-constructed ice-covered similarity zone clustering model. The information is input into a pre-built ice thickness prediction model, and the attention weight acquisition module of the ice thickness prediction model is updated using the ice similar area information. The second meteorological weight and the second terrain weight are obtained through the updated attention weight acquisition module. According to the meteorological data, terrain data, the second meteorological weight and the second terrain weight, the updated ice thickness of the transmission lines in each area is obtained, and the second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice thickness is used as the new ice thickness. Return to execute the step of inputting meteorological data, terrain data and ice thickness into the pre-built ice similar area clustering model to obtain the updated ice similar area information of each area. Among them, server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0070] In an exemplary embodiment, Figure 2 As shown, a method for updating ice coverage information is provided, and the method is applied to Figure 1 The server 102 in the example is used as an example to illustrate the method, which includes the following steps S201 to S206. Among them:

[0071] Step S202, obtaining meteorological data and topographic data of the power transmission lines in each area, and obtaining the ice thickness of the power transmission lines in each area.

[0072] Among them, meteorological data can be understood as information related to the atmospheric state and weather phenomena within the corresponding range monitored by the meteorological station, usually including temperature, humidity, air pressure, wind speed, precipitation, cloud cover and other data; terrain data can be understood as information describing the surface morphology and characteristics of the earth monitored by the geographic information monitoring system, such as elevation, slope, windward slope or leeward slope, the angle between the main wind direction in winter and the line direction, the height difference of the line direction, and the distance from the water body; ice cover thickness can be understood as the thickness of the ice layer on the transmission line.

[0073] Optionally, the server 102 obtains the meteorological data of the transmission lines in each area monitored by the meteorological station, the terrain data of the transmission lines in each area monitored by the geographic information monitoring system, and the ice thickness of the transmission lines in each area through the communication network, thereby laying a data foundation for the subsequent acquisition of information on similar ice-covered areas and updating of ice thickness.

[0074] Step S202, input meteorological data, terrain data and ice cover thickness into a pre-constructed ice-covered similar area clustering model, obtain the meteorological similarity between the areas according to the first meteorological weight and meteorological data preset in the ice-covered similar area clustering model, and obtain the terrain similarity between the areas according to the first terrain weight and terrain data preset in the ice-covered similar area clustering model.

[0075] Step S203, clustering the regions using the meteorological similarity, terrain similarity and ice thickness to obtain ice similarity area information corresponding to each region.

[0076] Among them, the ice-covered similarity area clustering model can be understood as a Gaussian mixture model, in which the initial values ​​of the preset first meteorological weight and the first terrain weight are equal.

[0077] For example, server 102 inputs meteorological data, terrain data and ice cover thickness into a pre-built Gaussian mixture model for cluster analysis. Initially, equal weights are assigned to meteorological data and terrain data. The similarity between meteorological data points and terrain data points is measured by weighted Euclidean distance. There is a high correlation between terrain data points and meteorological data points, and the two generally appear in pairs. The model assigns cluster labels to each pair of data points according to the ice cover thickness to indicate the cluster to which they belong, and then obtains the cluster labels corresponding to each area. The cluster labels here are the information of ice cover similarity areas. Cluster analysis is performed by comprehensively considering meteorological data and terrain data, which improves the accuracy of clustering and lays a data foundation for the subsequent adjustment of corresponding weights.

[0078] Step S204, input meteorological data, terrain data and ice-covered similar area information into a pre-built ice thickness prediction model, use the ice-covered similar area information to update the attention weight acquisition module of the ice thickness prediction model, and obtain the second meteorological weight and the second terrain weight through the updated attention weight acquisition module.

[0079] Step S205, obtaining the updated ice thickness of the power transmission lines in each area according to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight.

[0080] Among them, the ice thickness prediction model can be a neural network model. Through the complex neural network model, the nonlinear relationship between meteorological data, terrain data and ice thickness can be more accurately captured; the attention weight acquisition module can be understood as the self-attention mechanism in the ice thickness prediction model.

[0081] Optionally, the server 102 inputs the meteorological data, terrain data and ice-covered similar area information into a pre-built ice-covered thickness prediction model, and uses the ice-covered similar area information to update the attention weight acquisition module of the ice-covered thickness prediction model. The focus of the update is to determine which part of the meteorological data and terrain features have a greater weight in the influence on the ice-covered thickness. The second meteorological weight and the second terrain weight are obtained through the updated attention weight acquisition module, and the updated ice-covered thickness of the power transmission lines in each area is obtained based on the meteorological data, terrain data, the second meteorological weight and the second terrain weight. The attention weight acquisition module is updated using the ice-covered similar area information, so that the features that have a greater impact on the ice-covered thickness occupy a larger proportion in the calculation, and the most suitable weight information is adjusted, thereby improving the accuracy of the updated ice-covered thickness and laying a data foundation for continuing to update the ice-covered similar area clustering model.

[0082] Step S206, using the second meteorological weight as the new first meteorological weight, the second terrain weight as the new first terrain weight, and the updated ice cover thickness as the new ice cover thickness, returns to execute the step of inputting the meteorological data, terrain data, and ice cover thickness into the pre-built ice cover similarity area clustering model to obtain the updated ice cover similarity area information of each area.

[0083] For example, the server 102 uses the second meteorological weight as the new first meteorological weight, the second terrain weight as the new first terrain weight, and the updated ice thickness as the new ice thickness, and returns to execute the step of inputting the meteorological data, terrain data, and ice thickness into the pre-built ice similarity zone clustering model to obtain the updated ice similarity zone information of each region. The corresponding data in the ice similarity zone clustering model is updated using the second meteorological weight, the second terrain weight, and the updated ice thickness to improve the accuracy of cluster center determination, and repeat this iterative update process so that clustering and prediction gradually converge, and finally form a more accurate ice similarity zone division and ice thickness prediction.

[0084] In the above-mentioned ice cover information updating method, the meteorological data and terrain data of the transmission lines in each area are obtained, and the ice cover thickness of the transmission lines in each area is obtained, and the meteorological data, terrain data and ice cover thickness are input into a pre-constructed ice cover similarity zone clustering model, and the meteorological similarity between the regions is obtained according to the first meteorological weight and meteorological data preset in the ice cover similarity zone clustering model, and the terrain similarity between the regions is obtained according to the first terrain weight and terrain data preset in the ice cover similarity zone clustering model, and the meteorological similarity between the regions is obtained. The meteorological similarity, terrain similarity and ice cover thickness are used to cluster the regions to obtain the ice cover similarity zone information corresponding to each region, and the meteorological data, terrain data and ice cover similarity zone information are input into the pre-constructed ice cover similarity zone clustering model. Input a pre-built ice thickness prediction model, use the ice similarity zone information to update the attention weight acquisition module of the ice thickness prediction model, obtain the second meteorological weight and the second terrain weight through the updated attention weight acquisition module, obtain the updated ice thickness of the transmission lines in each area according to the meteorological data, terrain data, the second meteorological weight and the second terrain weight, use the second meteorological weight as the new first meteorological weight, the second terrain weight as the new first terrain weight, and the updated ice thickness as the new ice thickness, return to execute the step of inputting the meteorological data, terrain data and ice thickness data into the pre-built ice similarity zone clustering model, and obtain the updated ice similarity zone information of each area. Through the feedback update mechanism of the above-mentioned model output results and weight information, the iterative update of the ice information output by the two models is realized, thereby improving the correlation and accuracy between the ice information.

[0085] In an exemplary embodiment, Figure 3 As shown, obtaining the ice thickness of the power transmission lines in each area includes steps S301 to S303. Among them:

[0086] Step S301, obtaining the actual ice thickness monitored by user terminals on the transmission lines in each area.

[0087] Step S302: inputting meteorological data into a pre-built ice thickness simulation model, and obtaining a simulated ice thickness through the ice thickness simulation model.

[0088] Among them, the ice thickness simulation model can be understood as a wire model that characterizes the linear relationship between meteorological data and ice thickness, which is generally a physical model.

[0089] Optionally, the server 102 obtains the actual ice thickness monitored by the user terminal on the transmission line in each area, and then inputs the previously obtained meteorological data into a pre-built ice thickness simulation model, and simulates the ice thickness through the ice thickness simulation model. The ice thickness simulation model is used to simulate the ice thickness, which greatly increases the data for users to update the model, thereby improving the generalization ability and robustness of the model.

[0090] Step S303: when the difference between the simulated ice thickness and the actual ice thickness is less than a preset difference threshold, the actual ice thickness and the simulated ice thickness are determined as the ice thickness.

[0091] The preset difference threshold can be understood as the error of simulation data that the model can tolerate in the current application environment.

[0092] For example, when the server 102 determines that the difference between the simulated ice coating thickness and the actual ice coating thickness is less than a preset difference threshold, the actual ice coating thickness and the simulated ice coating thickness are determined as the ice coating thickness. By comparing the difference between the actual ice coating thickness and the simulated ice coating thickness, the simulated ice coating thickness is selectively filtered out, thereby ensuring the reliability of the ice coating data input to the model.

[0093] In one embodiment, the method includes: determining an area to be optimized from various areas according to an updated ice coating thickness, and obtaining layout information of user terminals on the transmission lines in the area to be optimized; adjusting the layout information using the NSGA-II algorithm to obtain multiple layout schemes for the user terminals; obtaining corresponding objective function values ​​according to the layout information of the user terminals in the layout schemes, and determining the layout scheme corresponding to the minimum objective function value as the target layout scheme; and rearranging the user terminals on the transmission lines in the area to be optimized according to the layout information of the user terminals in the target layout scheme.

[0094] Among them, the area to be optimized can be understood as the updated ice thickness output by the ice thickness prediction model, the large error area with a large difference from the real-time ice thickness monitored by the user terminal, and the high-risk area where the updated ice thickness exceeds the set high-risk level; NSGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm is a genetic algorithm for multi-objective optimization problems. It can effectively find a set of high-quality solutions when dealing with multiple objective functions; the objective function value includes the error function value and the risk function value. The smaller the function value, the smaller the error and the lower the risk.

[0095] Optionally, the server 102 determines the area to be optimized from each area according to the updated ice thickness, including the large error area and the high-risk area, and obtains the layout information of the user terminals on the transmission line in the area to be optimized, and uses the genetic algorithm of multi-objective optimization to adjust the layout information, including adjusting the number and layout positions of the user terminals, thereby obtaining multiple layout schemes of the user terminals, and obtaining the corresponding objective function value according to the layout information of the user terminals in the layout scheme, determining the layout scheme corresponding to the minimum objective function value as the target layout scheme, and finally re-layout the user terminals on the transmission line in the area to be optimized according to the layout information of the user terminals in the target layout scheme. Through the above means, the layout of monitoring points can be optimized under the condition of resource priority, and the monitoring accuracy of the area to be optimized can be improved.

[0096] In one of the embodiments, the method further includes: obtaining updated layout information of user terminals on the transmission lines in each area, and displaying the updated layout information of user terminals in the form of highlights on the map, and displaying the real-time ice thickness monitored by each user terminal.

[0097] For example, the server 102 obtains updated layout information of user terminals on the transmission lines in each area, and displays the updated layout information of user terminals in the form of highlights on the map, as well as the real-time ice thickness monitored by each user terminal. The above visualization processing can more intuitively display the monitoring range and monitoring results of user terminals in each area, which helps relevant personnel design and adjust processing solutions based on the displayed content.

[0098] In an exemplary embodiment, meteorological data and terrain data of power transmission lines in each region are obtained, including: obtaining original meteorological data and original terrain data of power transmission lines in each region; removing blank data and duplicate data in the original meteorological data and original terrain data to obtain cleaned original meteorological data and original terrain data; performing data dimensionality reduction on the cleaned original meteorological data and original terrain data and converting them into a unified data format to obtain meteorological data and terrain data.

[0099] Optionally, the server 102 obtains the original meteorological data and original terrain data of the power transmission lines in each area, removes blank data and duplicate data in the original meteorological data and original terrain data, obtains cleaned original meteorological data and original terrain data, performs data dimension reduction on the cleaned original meteorological data and original terrain data and converts them into a unified data format to obtain meteorological data and terrain data. Processing meteorological data and terrain data by the above data preprocessing means enhances the availability of meteorological data and terrain data, thereby improving the generalization ability of the model.

[0100] In one embodiment, the method includes: when the step of inputting meteorological data, terrain data and ice cover thickness into a pre-built ice cover similar area clustering model reaches a preset return number threshold, obtaining the last ice cover similar area division information and ice cover thickness; dividing each area according to the last ice cover similar area information to obtain multiple ice cover similar areas; determining the ice cover magnitude information corresponding to each ice cover similar area based on the ice cover thickness corresponding to each ice cover similar area; displaying each ice cover similar area on the map with different colors, and displaying the ice cover magnitude information corresponding to each ice cover similar area at the same time.

[0101] Among them, the ice cover level information can be understood as the corresponding levels assigned according to the ice cover thickness, such as high risk, medium risk, and low risk.

[0102] For example, when the server 102 determines that the step of inputting meteorological data, terrain data, and ice thickness into a pre-built ice-covered similar area clustering model has reached a preset return number threshold, that is, the number of iterations between the models has reached the standard or the similar area division is consistent with the ice thickness prediction, the server 102 obtains the last ice-covered similar area division information and ice thickness, divides each area according to the last ice-covered similar area division information, obtains a plurality of ice-covered similar areas, determines the ice magnitude information corresponding to each ice-covered similar area based on the ice thickness corresponding to each ice-covered similar area, and displays the ice-covered similar areas on the map in different colors. Display each similar ice-covered area. For example, when the ice-covered level information indicates that the similar ice-covered area is a high-risk level area, the ice-covered similar area is displayed in a striking red color on the map, and the high-risk ice-covered level information is displayed; when the ice-covered level information indicates that the similar ice-covered area is a medium-risk level area, the ice-covered similar area is displayed in a striking yellow color on the map, and the medium-risk ice-covered level information is displayed; when the ice-covered level information indicates that the similar ice-covered area is a low-risk level area, the ice-covered similar area is displayed in blue on the map, and the low-risk ice-covered level is displayed; the remaining normal ice-covered similar areas are displayed in green.

[0103] By using the thickness of the last ice cover to accurately assess the risk level of similar ice-covered areas, and using different colors to visualize the risks of similar ice-covered areas with different risk levels, the risk levels of different areas can be intuitively displayed, and risk avoidance plans can be designed in a targeted manner based on the display content to improve the adaptability of the plan.

[0104] In an exemplary embodiment, Figure 4 As shown, a specific implementation of an ice coverage information updating method is provided, wherein:

[0105] Step 1: Establish a data acquisition module, which covers the collection of monitoring data and the generation and integration of numerical simulation data, and builds a complete and dynamically updated database to support subsequent analysis and decision-making on ice cover magnitude prediction, similarity zone division, and optimal layout of monitoring equipment.

[0106] 1. In some possible implementations, the data acquisition module in step 1 includes two submodules. The first submodule is used to collect meteorological station monitoring data and terrain data (module G-1), including but not limited to meteorological data (such as temperature, humidity, wind speed) and terrain data (such as elevation, slope, windward slope or leeward slope, the angle between the main wind direction in winter and the line direction, the height difference of the line direction, and the distance from the water body). The second submodule is used to collect real-time monitoring data of ice thickness in the ice monitoring terminal (module G-2).

[0107] 2. In some possible implementations, step 1 uses DEM (digital elevation model) data to extract micro-topographic factors, such as elevation and slope. By combining DEM data with specific geographic point coordinates through GIS (geographic information system) technology, terrain factors such as elevation, slope, windward slope or leeward slope, angle between the main wind direction in winter and the route direction, route direction height difference, and distance from water bodies can be extracted.

[0108] 3. In some possible implementations, the data acquisition module in step 1 can acquire and update meteorological data, transmission line ice thickness and terrain data in real time by connecting to a meteorological database, an ice monitoring terminal and a GIS system.

[0109] Step 2: Establish a numerical simulation module. By constructing a numerical simulation model of the transmission line tower and using large-scale numerical simulation software to perform a large number of calculations, a rich data set is created to improve the training effect and generalization performance of the neural network.

[0110] 1. In some possible implementations, the numerical simulation module in step 2 can be completed with the help of Fluent and FluentIcing software. By establishing a conductor model and inputting meteorological monitoring data, the module outputs the ice thickness value. Before using the numerical simulation data calculated by the module, the numerical simulation results need to be cross-validated with the ice thickness of the transmission line under the corresponding meteorological monitoring data. If the error between the two is within 10%, 10% is an exemplary value that can be adjusted according to the actual application situation, it means that the numerical simulation results have good credibility.

[0111] Step 3: Establish a data preprocessing module to preprocess the data in the training set, including data cleaning, normalization, and feature selection, to improve the training effect of the neural network and ensure the accuracy of the prediction.

[0112] 1. In some possible implementations, the data preprocessing module in step 3 is a key step to improve data quality and model performance. Through standardization, normalization, missing value processing, category coding, dimensionality reduction, data transformation and other methods, the noise, inconsistency and scale difference problems in the data can be effectively solved, thereby improving the performance of the model.

[0113] Step 4: Establish a clustering module, use the Gaussian mixture model for clustering analysis, input the meteorological and terrain data features, and initially assign equal weights to each feature. By measuring the similarity between data points using weighted Euclidean distance, the model will assign a cluster label to each data point to indicate the cluster to which it belongs. The feature weights generated by the neural network model will be fed back to the Gaussian mixture model, and the weighted Euclidean distance of the features will be continuously adjusted to optimize the clustering effect, thereby improving the accuracy of ice cover pattern prediction.

[0114] 1. In some possible implementations, the clustering module in step 4 uses a Gaussian mixture model (GMM) for clustering. First, meteorological data features and terrain data features are selected as input variables, and the sensitivity of these features is analyzed by training a neural network model to determine the weight of each feature on the prediction of ice cover patterns. Then, these features and their corresponding weights are input into the GMM together, and the weighted Euclidean distance is used for measurement during the clustering process, so that the features that have a greater impact on the ice cover pattern occupy a larger proportion in the distance calculation, thereby achieving more accurate regional division.

[0115] 2. In some possible implementations, the data preprocessing module in step 4 uses the standardized sensitivity coefficients of different variables in the proxy model as feature weights and combines them with the clustering method of the Gaussian mixture model, so that the clustering process focuses more on the variables that have a greater impact on the ice cover pattern.

[0116] For a containing A collection of data points , we need to calculate any two data points and This distance takes into account all the features The influence of , each feature is weighted using the neural network prediction results. The formula of weighted Euclidean distance is expanded to:

[0117]

[0118] in: It is The data point in The value of a feature, It is The data point in The value of a feature, It is a feature The standardized sensitivity coefficients of different variables This is obtained by performing sensitivity analysis on the proxy model.

[0119] 3. In some possible implementations, such as Figure 5 As shown, when the clustering algorithm in step 4 is dynamically adjusted, the neural network prediction results can be used to guide clustering. The neural network prediction results can be used as a parameter of clustering weight or distance measurement, thereby affecting the determination of cluster centers. In addition, the clustering results can also be fed back to the neural network model for retraining to further optimize the neural network model. After the retraining, the prediction results of the neural network model will be more accurate and in line with the actual situation. This iterative process makes the clustering and neural network models gradually converge, and ultimately forms a more accurate division of ice cover similarity areas and regularity predictions.

[0120] Step 5: Establish a neural network model and use the Transformer model-based architecture to predict ice thickness. The input features include time series data, cluster labels, meteorological and terrain data (such as temperature, humidity, wind speed, altitude, etc.). Transformer automatically identifies important features through the self-attention mechanism and combines cluster labels to generate more accurate ice thickness predictions. At the same time, the feature weights generated by the model are fed back to the Gaussian mixture model to help adjust its feature weights, further improve prediction accuracy, and provide a powerful tool for risk warning and decision support.

[0121] 1. In some possible implementations, the neural network module in step 5 uses a Transformer-based model to predict the changing relationship between ice thickness and input features such as time, cluster labels, altitude, temperature, humidity, and wind speed. The Transformer model consists of multiple layers and can capture complex nonlinear relationships between input features. The architecture of the model includes a feature input layer, a position encoding layer, a Transformer encoder layer, a self-attention layer, a first fully connected layer, a second fully connected layer, and a regression output layer. By adjusting the number of units in the self-attention layer and the fully connected layer, it is ensured that the model can fully capture the nonlinear relationship between the input features, and ultimately achieve accurate prediction of ice thickness changes over time and environmental characteristics.

[0122] 2. In some possible implementations, the trained Gaussian mixture model is used to perform similar division of ice-covered areas and the Transformer-based neural network is used to predict ice thickness.

[0123] Clustering based on trained Gaussian mixture models: Based on new input features (such as meteorological data, terrain data, etc.) and feature weights optimized during training, the trained GMM model is used to assign cluster labels to each data point (dividing areas with similar ice coverage). These labels reflect the similarity of data points in ice coverage characteristics and help with subsequent predictions.

[0124] Prediction based on the trained Transformer model: The cluster labels generated by GMM are input into the trained Transformer model together with other input features (such as time series data, meteorological and terrain features). The Transformer model comprehensively analyzes these input features through the self-attention mechanism to predict the future ice thickness, provide accurate estimation results, and help with risk warning and decision support.

[0125] Step 6: Establish a multi-objective optimization model. By constructing an optimization problem with neural network prediction error and high-risk area coverage as the main objectives, combined with the NSGA-II algorithm, the monitoring point layout is optimized. This not only improves the monitoring accuracy of high-risk areas, but also ensures that areas with large neural network errors are monitored, while controlling the redundant coverage between monitoring points through constraints.

[0126] 1. In some possible implementations, the multi-objective optimization module in step 6 constructs an optimization problem with neural network prediction error and high-risk area coverage as the main objectives, and solves it in combination with the NSGA-II algorithm. Under limited resources, this method can effectively optimize the layout of monitoring points, improve the monitoring accuracy of high-risk areas, ensure that areas with large neural network errors are monitored, and control the redundant coverage between monitoring points through constraints.

[0127] Finally, we formulate the problem as:

[0128]

[0129] Constraints:

[0130]

[0131]

[0132]

[0133] Among them, RiskCoverage(x): indicates the coverage of the high-risk area by the monitoring point layout x; ErrorCoverage(x): indicates the coverage of the area with large neural network prediction error by the monitoring point layout x; Redundancy(x): indicates the sum of overlapping areas in the monitoring point layout x; MaxRedundancy(x): is the maximum allowed redundant coverage area; Num(x): indicates the number of current monitoring points; MaxNum: is the maximum number of available monitoring devices; CheckPosition(x): is used to check whether each monitoring point is located in the allowed geographical location (for example, to ensure that the monitoring point is not located in an area where equipment cannot be placed).

[0134] 2. In some possible implementations, in order to compare different objectives in step 6, we normalize the two objective functions. Assume that on the Pareto front, the objective function and The value ranges are and The normalized objective function is expressed as follows:

[0135]

[0136]

[0137] The normalized value is in the range [0,1], where 0 corresponds to the optimal target value and 1 corresponds to the worst target value.

[0138] Step 7: Create a result output module, generate multiple similar ice-covered areas, and visualize them on the map to facilitate analysis and interpretation of ice-covered risk characteristics in different areas. The output also includes: time series graphs, height profiles, layout diagrams, and detailed optimization reports, which fully display the prediction and optimization results.

[0139] 1. In some possible implementations, the output of step 7 includes multiple charts and reports that explain the relevant information of the ice cover forecast. The time series chart shows the trend of the predicted ice cover thickness over time, which helps to identify high-risk periods; the altitude profile chart shows the change of ice cover thickness with altitude, which is convenient for identifying the ice cover level at key altitude sections; the layout plan chart shows the optimized monitoring equipment location on the map, highlighting the coverage of high-risk areas and areas with large prediction errors. The optimization report records in detail the scope of each monitoring point, the high-risk areas covered, and the predicted ice cover thickness information.

[0140] Compared with the prior art, this application has the following advantages:

[0141] (1) By constructing a numerical simulation model of the transmission line tower and using large-scale numerical simulation software to perform a large number of calculations, a rich data set was created without the need for a large amount of measured data. At the same time, the numerical simulation results were cross-validated with the ice thickness of the transmission line under the corresponding meteorological monitoring data to ensure the reliability of the data.

[0142] (2) The retrained neural network model can be used to derive the complex nonlinear relationship between meteorological and topographic factors and ice cover magnitude, making the prediction results more consistent with the actual situation and improving the prediction accuracy. At the same time, this method can also obtain and update meteorological data, transmission line ice thickness and topographic data in real time to ensure that new data is included in the analysis in a timely manner.

[0143] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0144] Based on the same inventive concept, the embodiment of the present application also provides an ice covering information updating device for implementing the ice covering information updating method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the ice covering information updating device provided below can refer to the limitations of the ice covering information updating method above, and will not be repeated here.

[0145] In an exemplary embodiment, Figure 6 As shown, an ice coverage information updating device is provided, comprising: a data acquisition module 601, a similar area information determination module 602, a thickness updating module 603 and an updating module 604, wherein:

[0146] The data acquisition module 601 is used to acquire the meteorological data and terrain data of the power transmission lines in each area, and acquire the ice thickness of the power transmission lines in each area;

[0147] The similarity zone information determination module 602 is used to input the meteorological data, terrain data and ice thickness into a pre-constructed ice-covered similar zone clustering model, obtain the meteorological similarity between the regions according to the first meteorological weight and meteorological data preset in the ice-covered similar zone clustering model, and obtain the terrain similarity between the regions according to the first terrain weight and terrain data preset in the ice-covered similar zone clustering model; cluster the regions using the meteorological similarity, terrain similarity and ice thickness to obtain the ice-covered similar zone information corresponding to each region;

[0148] The thickness updating module 603 is used to input the meteorological data, terrain data and ice-covered similar area information into the pre-built ice-covered thickness prediction model, update the attention weight acquisition module of the ice-covered thickness prediction model by using the ice-covered similar area information, obtain the second meteorological weight and the second terrain weight through the updated attention weight acquisition module; obtain the updated ice-covered thickness of the transmission lines in each area according to the meteorological data, terrain data, the second meteorological weight and the second terrain weight;

[0149] The updating module 604 is used to use the second meteorological weight as the new first meteorological weight, the second terrain weight as the new first terrain weight, and the updated ice cover thickness as the new ice cover thickness, and return to execute the step of inputting the meteorological data, terrain data and ice cover thickness into the pre-built ice cover similarity area clustering model to obtain the updated ice cover similarity area information of each area.

[0150] In one embodiment, the data acquisition module 601 is also used to obtain the actual ice thickness monitored by user terminals on the transmission lines in each area; input the meteorological data into a pre-built ice thickness simulation model, and obtain the simulated ice thickness through the ice thickness simulation model; when the difference between the simulated ice thickness and the actual ice thickness is less than a preset difference threshold, the actual ice thickness and the simulated ice thickness are determined as the ice thickness.

[0151] In one of the embodiments, the ice cover information updating device is also used to determine the area to be optimized from each area according to the updated ice cover thickness, and obtain the layout information of the user terminals on the transmission line in the area to be optimized; adjust the layout information using the NSGA-II algorithm to obtain multiple layout schemes for the user terminals; obtain the corresponding objective function value according to the layout information of the user terminals in the layout scheme, and determine the layout scheme corresponding to the minimum objective function value as the target layout scheme; and re-layout the user terminals on the transmission line in the area to be optimized according to the layout information of the user terminals in the target layout scheme.

[0152] In an exemplary embodiment, the ice coverage information updating device further includes a visualization unit, wherein:

[0153] The visualization unit is used to obtain the updated layout information of the user terminals on the transmission lines in each area, and display the updated layout information of the user terminals in the form of highlights on the map, as well as display the real-time ice thickness monitored by each user terminal.

[0154] In one embodiment, the data acquisition module 601 is also used to obtain the original meteorological data and original terrain data of the transmission lines in each area; remove blank data and duplicate data in the original meteorological data and original terrain data to obtain cleaned original meteorological data and original terrain data; perform data dimensionality reduction on the cleaned original meteorological data and original terrain data and convert them into a unified data format to obtain meteorological data and terrain data.

[0155] In one of the embodiments, the visualization unit is also used to obtain the last ice-covered similar area division information and ice thickness when the step of inputting meteorological data, terrain data and ice thickness into a pre-built ice-covered similar area clustering model is returned and reaches a preset return number threshold; divide each area according to the last ice-covered similar area information to obtain multiple ice-covered similar areas; determine the ice-covered magnitude information corresponding to each ice-covered similar area based on the ice-covered thickness corresponding to each ice-covered similar area; display each ice-covered similar area on the map with different colors, and display the ice-covered magnitude information corresponding to each ice-covered similar area at the same time.

[0156] Each module in the ice cover information updating device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0157] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store meteorological data, terrain data, ice thickness, ice similarity area information, first meteorological weight, second meteorological weight, first terrain weight and second terrain weight data of the transmission lines in each area. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for updating ice information is implemented.

[0158] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the ice coverage information updating method of the above embodiment is implemented.

[0160] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the ice coverage information updating method in the above embodiment is implemented.

[0161] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the ice coverage information updating method in the above embodiment is implemented.

[0162] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0163] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0164] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0165] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for updating ice coverage information, characterized in that: The method comprises: Obtaining meteorological data and topographic data of the power transmission lines in each area, and obtaining the ice thickness of the power transmission lines in each of the areas; Inputting the meteorological data, the terrain data and the ice thickness into a pre-constructed ice-covered similarity zone clustering model, obtaining the meteorological similarity between the regions according to the first meteorological weight preset in the ice-covered similarity zone clustering model and the meteorological data, and obtaining the terrain similarity between the regions according to the first terrain weight preset in the ice-covered similarity zone clustering model and the terrain data; Clustering the regions using the meteorological similarity, the terrain similarity and the ice thickness to obtain ice similarity area information corresponding to the regions; Inputting the meteorological data, the terrain data and the ice-covered similar area information into a pre-constructed ice-covered thickness prediction model, using the ice-covered similar area information to update an attention weight acquisition module of the ice-covered thickness prediction model, and obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module; Obtaining updated ice thickness of the power transmission lines in each of the areas according to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight; The second meteorological weight is used as the new first meteorological weight, the second terrain weight is used as the new first terrain weight, and the updated ice cover thickness is used as the new ice cover thickness, and the step of inputting the meteorological data, the terrain data and the ice cover thickness into a pre-constructed ice cover similarity area clustering model is returned to obtain the updated ice cover similarity area information of each of the areas.

2. The method according to claim 1, characterized in that: The obtaining of ice thickness of the power transmission lines in each of the areas includes: Obtaining the actual ice thickness monitored by user terminals on the transmission lines in each of the areas; Inputting the meteorological data into a pre-built ice thickness simulation model, and obtaining a simulated ice thickness through the ice thickness simulation model; When the difference between the simulated ice coating thickness and the actual ice coating thickness is less than a preset difference threshold, the actual ice coating thickness and the simulated ice coating thickness are determined as the ice coating thickness.

3. The method according to claim 1, characterized in that The method comprises: Determine an area to be optimized from each of the areas according to the updated ice thickness, and obtain layout information of user terminals on the transmission line in the area to be optimized; Using the NSGA-II algorithm to adjust the layout information, and obtain multiple layout schemes of the user terminal; Acquire a corresponding objective function value according to the layout information of the user terminal in the layout scheme, and determine the layout scheme corresponding to the minimum objective function value as the target layout scheme; According to the layout information of the user terminals in the target layout scheme, the user terminals on the transmission lines in the area to be optimized are rearranged.

4. The method according to claim 3, characterized in that The method further comprises: The updated layout information of the user terminals on the transmission lines in each of the areas is obtained, and the updated layout information of the user terminals is displayed in the form of highlights on the map, and the real-time ice thickness monitored by each of the user terminals is displayed.

5. The method according to claim 1, characterized in that: The obtaining of meteorological data and terrain data of the power transmission lines in each area includes: Obtain original meteorological data and original terrain data of power transmission lines in each area; Removing blank data and duplicate data from the original meteorological data and the original terrain data to obtain cleaned original meteorological data and original terrain data; The cleaned original meteorological data and original terrain data are subjected to data dimension reduction and converted into a unified data format to obtain the meteorological data and the terrain data.

6. The method according to claim 1, characterized in that The method comprises: When the step of inputting the meteorological data, the terrain data and the ice thickness into the pre-built ice similarity zone clustering model is returned and reaches a preset return number threshold, the last ice similarity zone division information and ice thickness are obtained; Divide each of the regions according to the last ice-covered similarity region information to obtain a plurality of ice-covered similarity regions; Based on the ice thickness corresponding to each of the ice-covered similar areas, determining the ice-covered magnitude information corresponding to each of the ice-covered similar areas; The ice-covered similar areas are displayed in different colors on the map, and the ice-covered magnitude information corresponding to each ice-covered similar area is also displayed.

7. An ice coverage information updating device, characterized in that: The device comprises: A data acquisition module, used to acquire meteorological data and terrain data of the power transmission lines in each area, and to acquire the ice thickness of the power transmission lines in each of the areas; A similarity zone information determination module, for inputting the meteorological data, the terrain data and the ice cover thickness into a pre-constructed ice cover similarity zone clustering model, obtaining the meteorological similarity between the regions according to a first meteorological weight preset in the ice cover similarity zone clustering model and the meteorological data, and obtaining the terrain similarity between the regions according to a first terrain weight preset in the ice cover similarity zone clustering model and the terrain data; clustering the regions according to the meteorological similarity, the terrain similarity and the ice cover thickness to obtain ice cover similarity zone information corresponding to the regions; A thickness updating module, used for inputting the meteorological data, the terrain data and the ice-covered similar area information into a pre-built ice-covered thickness prediction model, using the ice-covered similar area information to update the attention weight acquisition module of the ice-covered thickness prediction model, obtaining a second meteorological weight and a second terrain weight through the updated attention weight acquisition module; obtaining the updated ice-covered thickness of the transmission lines in each of the areas according to the meteorological data, the terrain data, the second meteorological weight and the second terrain weight; An updating module is used to use the second meteorological weight as a new first meteorological weight, the second terrain weight as a new first terrain weight, and the updated ice thickness as a new ice thickness, and return to execute the step of inputting the meteorological data, the terrain data, and the ice thickness into a pre-constructed ice similarity area clustering model to obtain the updated ice similarity area information of each of the areas.

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

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

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

Images