A method and related device for processing electric power engineering survey data

Abstract

The present invention provides a power engineering survey data processing method and related device. The method obtains a multi-source survey data set for a target area, the multi-source survey data set including geological and topographic data, electromagnetic interference data, and equipment layout data. The multi-source survey data set is jointly feature mapped using a pre-trained feature extraction network to generate a multidimensional survey feature vector. The multidimensional survey feature vector is input into an optimization decision model for iterative parameter adjustment to generate a power engineering optimization parameter set for the target area. The optimization decision model is trained based on the mapping relationship between historical survey data and verified optimization results. A power facility deployment plan for the target area is generated based on the power engineering optimization parameter set. The deployment plan includes transmission line path planning results, substation site selection coordinates, and electromagnetic interference suppression strategies. The present invention can improve the environmental adaptability, global coordination, and construction feasibility of the power facility deployment plan.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and related device for processing electric power engineering survey data. Background Art

[0002] Power engineering survey data processing involves comprehensive analysis of the target area to develop a plan for power facility deployment. Existing technologies typically plan transmission line routes based on terrain elevation data or screen substation sites based on electromagnetic radiation intensity thresholds. This leads to problems such as overlap between route planning and electromagnetic interference areas, and conflicts between equipment layout and geological stability. Furthermore, traditional deployment solutions lack a dynamic response mechanism to real-time terrain changes during construction and electromagnetic fluctuations during operation. This results in high construction rework rates, increased costs for subsequent shielding equipment expansion, and poor overall coordination of deployment plans. These solutions are unable to effectively address multiple constraint conflicts in complex environments, limiting the overall reliability and economic efficiency of power engineering deployment. Summary of the Invention

[0003] The present invention provides a method for processing electric power engineering survey data and a related device.

[0004] In a first aspect, an embodiment of the present invention provides a method for processing power engineering survey data, the method comprising: obtaining a multi-source survey data set of a target area, the multi-source survey data set comprising geological and topographic data, electromagnetic interference data, and equipment layout data, wherein the electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of the power facilities in the target area, and the equipment layout data is used to indicate the transmission line topology and substation location in the target area; performing joint feature mapping on the multi-source survey data set through a pre-trained feature extraction network to generate a multidimensional survey feature vector, wherein the multidimensional survey feature vector comprises a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector; inputting the multidimensional survey feature vector into an optimization decision model for iterative parameter adjustment to generate a power engineering optimization parameter set for the target area, wherein the optimization decision model is trained based on a mapping relationship between historical survey data and verified optimization results; and generating a power facility deployment plan for the target area based on the power engineering optimization parameter set, wherein the deployment plan comprises a transmission line path planning result, substation site selection coordinates, and an electromagnetic interference suppression strategy.

[0005] In a second aspect, an embodiment of the present invention provides a power engineering survey data processing device, the device comprising: a data acquisition module for acquiring a multi-source survey data set of a target area, the multi-source survey data set comprising geological and topographic data, electromagnetic interference data, and equipment layout data, wherein the electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of the power facilities in the target area, and the equipment layout data is used to indicate the transmission line topology and substation location in the target area; a feature mapping module for performing joint feature mapping on the multi-source survey data set using a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, wherein the multi-dimensional survey feature vector comprises a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector; a parameter generation module for inputting the multi-dimensional survey feature vector into an optimization decision model for iterative parameter adjustment to generate a power engineering optimization parameter set for the target area, wherein the optimization decision model is trained based on a mapping relationship between historical survey data and verified optimization results; and a solution generation module for generating a power facility deployment solution for the target area based on the power engineering optimization parameter set, wherein the deployment solution comprises a transmission line path planning result, substation site selection coordinates, and an electromagnetic interference suppression strategy.

[0006] The power engineering survey data processing method provided by the present invention constructs a multi-source survey data set by acquiring geological and topographic data, electromagnetic interference data, and equipment layout data of the target area, and uses a pre-trained feature extraction network to perform joint feature mapping to generate a multidimensional survey feature vector containing a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector; iteratively adjusts the parameters of the multidimensional survey feature vector based on an optimization decision model to generate a power engineering optimization parameter set that integrates terrain constraints, electromagnetic safety, and topological coverage requirements, and based on this, generates a power facility deployment plan that combines transmission line path planning results, substation site selection coordinates, and electromagnetic interference suppression strategy. This method breaks through the limitations of traditional single-dimensional data processing through collaborative feature extraction and dynamic optimization decision-making of multi-source survey data. It can simultaneously avoid geological risk areas and high electromagnetic radiation areas in path planning, balance coverage efficiency and electromagnetic suppression requirements in substation site selection, and realize dynamic adaptation of spatial parameters and real-time monitoring in equipment deployment, thereby significantly improving the environmental adaptability, global coordination and construction feasibility of power facility deployment plans. At the same time, through the spatial fusion of multi-dimensional feature vectors and the embedding of joint control logic, it ensures that the deployment plan can be dynamically optimized and adjusted according to real-time terrain changes, electromagnetic fluctuations and load conditions during the construction and operation stages, effectively reducing rework costs and operational risks, and improving the overall safety and economy of power project deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1The present invention provides a flowchart of a method for processing power engineering survey data.

[0008] Figure 2 The figure is a schematic diagram of the composition of a power engineering survey data processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0010] See also Figure 1 , Figure 1 A flowchart of a method for processing power engineering survey data provided by an embodiment of the present invention is provided. The method for processing power engineering survey data can be executed by a computer system and may include the following steps:

[0011] Step S100: Acquire a multi-source survey data set of the target area, where the multi-source survey data set includes geological and topographic data, electromagnetic interference data, and equipment layout data. The electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of the power facilities in the target area, and the equipment layout data is used to indicate the transmission line topology and substation location in the target area.

[0012] In an embodiment of the present invention, geological and topographic data refers to information about the geological structure, topographic undulations, etc. of the target area. This information can reflect the geological stability of the area and the complexity of the terrain. For example, the geological and topographic data of a mountainous area will include the slope, height, rock type, etc. of the mountain. Electromagnetic interference data focuses on the electromagnetic radiation generated by the power facilities in the target area. By collecting and analyzing this data, we can clearly understand the distribution of electromagnetic radiation intensity in different locations and frequency bands. For example, near a substation, the electromagnetic radiation intensity may be relatively high. The equipment layout data mainly records the connection method and direction of the transmission lines in the target area, as well as the specific location of the substation. By analyzing these data, we can construct the power network topology of the area.

[0013] In practice, geological and topographic data can be obtained through technologies such as satellite remote sensing and geographic information systems (GIS). These technologies can accurately capture information such as terrain elevation and geological stratification within the target area. For electromagnetic interference data, multiple electromagnetic monitoring points are typically set up within the target area. Using specialized electromagnetic monitoring equipment, data is collected at predefined intervals to comprehensively and accurately capture the distribution of electromagnetic radiation intensity. Equipment layout data can be obtained from power company databases, which detail the layout of transmission lines and substation construction.

[0014] Step S200: performing joint feature mapping on a multi-source survey data set through a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, wherein the multi-dimensional survey feature vector includes a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector.

[0015] A pretrained feature extraction network is a neural network model trained on historical data. Its purpose is to extract representative features from the input data. In this embodiment of the present invention, the network performs joint feature mapping on a multi-source survey data set, deeply integrating geological and topographic data, electromagnetic interference data, and equipment layout data to generate a multidimensional survey feature vector containing information from multiple dimensions.

[0016] The terrain parameter subvector is derived from feature extraction of geological and topographic data. It contains key information such as terrain relief and geological stability, which reflects the topographic characteristics and geological conditions of the target area. The electromagnetic intensity subvector is extracted from electromagnetic interference data. It contains information on the distribution of electromagnetic radiation intensity across different frequency bands, helping to understand the complexity of the electromagnetic environment within the target area. The layout topology subvector is generated based on equipment layout data and reflects information such as the topology of transmission lines and the coverage of substations.

[0017] In practice, the pre-trained feature extraction network can employ architectures such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs). Taking CNN as an example, convolutional layers can extract features from multi-source survey data, while pooling layers reduce and compress the features, ultimately generating a multi-dimensional survey feature vector. For example, for a power engineering survey in a mountainous area, the pre-trained feature extraction network can generate a multi-dimensional survey feature vector that accurately reflects the region's topographical, electromagnetic, and equipment layout characteristics.

[0018] As an embodiment, step S200, performing joint feature mapping on a multi-source survey data set through a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, may specifically include the following steps:

[0019] Step S210: performing elevation gradient analysis on the geological and topographic data, extracting terrain relief characteristics and geological stability characteristics, and fusing the terrain relief characteristics and geological stability characteristics into a terrain parameter sub-vector based on a preset terrain coding structure.

[0020] Elevation gradient analysis involves processing and analyzing the elevation information contained in geological and topographic data. By calculating the numerical differences between adjacent elevation points, a slope gradient map is generated, which contains the rate of change and azimuth of elevation at each coordinate point. Terrain relief characteristics are derived through further analysis of the slope gradient map and reflect the degree of relief in the target area. For example, mountainous terrain has a more pronounced relief characteristic. Geological stability characteristics are derived through structural continuity analysis of the rock layer distribution data in geological and topographic data. These characteristics reflect the geological stability of the target area. For example, the presence of fault lines or loose sedimentary areas can reduce geological stability.

[0021] The preset terrain coding structure is a predefined rule for fusing terrain relief features with geological stability features. In practice, this rule can be implemented using a feature fusion layer, converting terrain relief features into a relief code sequence and geological stability features into a stability code sequence. These two code sequences are then weighted element-by-element at each coordinate point to generate a terrain parameter subvector.

[0022] In the specific operation, the elevation distribution matrix in the geological and topographic data is first obtained, and the slope gradient map is generated by calculating the numerical differences between adjacent elevation points. Then, the terrain area type is divided according to the elevation change rate in the slope gradient map, the boundary coordinate set of the area with continuous slope change is extracted, and the terrain relief feature is generated based on the maximum slope difference within the boundary coordinate set. At the same time, the structural continuity analysis of the rock layer distribution data in the geological and topographic data is performed to identify the range of fault lines or loose sedimentary areas, and the geological stability feature is generated based on the overlapping area ratio between the range and the slope gradient map. Finally, the feature fusion layer in the preset terrain encoding structure is called to fuse the terrain relief feature and the geological stability feature to generate a terrain parameter sub-vector. For example, when conducting a power engineering survey in an area containing mountains and plains, the above steps can accurately extract the terrain relief feature and geological stability feature of the area and generate the corresponding terrain parameter sub-vector.

[0023] As an embodiment, step S210 performs elevation gradient analysis on geological and topographic data, extracts terrain relief characteristics and geological stability characteristics, and fuses the terrain relief characteristics and geological stability characteristics into terrain parameter subvectors based on a preset terrain coding structure. Specifically, the following steps may be included:

[0024] Step S211: obtaining an elevation distribution matrix in the geological and topographic data, and generating a slope gradient map based on the numerical difference between adjacent elevation points, wherein the slope gradient map includes the elevation change rate and direction angle of each coordinate point.

[0025] The elevation distribution matrix is ​​a matrix representation of elevation information in geological and topographic data. It records the elevation values ​​of each coordinate point within the target area. Obtaining the elevation distribution matrix provides a comprehensive understanding of the terrain elevation conditions in the target area. Slope gradient maps are generated based on the numerical differences between adjacent elevation points. This is achieved by calculating the elevation differences between adjacent elevation points and combining them with the distance between them to determine the slope value and azimuth angle at each coordinate point.

[0026] The rate of change of elevation in a slope gradient map reflects the steepness of the terrain; the greater the rate of change, the steeper the terrain. The direction angle indicates the direction of the terrain's inclination. Using a slope gradient map, you can intuitively understand the terrain's undulations in the target area.

[0027] In practice, tools such as geographic information systems (GIS) can be used to obtain the elevation distribution matrix from geological and topographic data. Algorithms can then be developed to calculate the numerical differences between adjacent elevation points and generate a slope gradient map. For example, when processing geological and topographic data for a mountainous area, obtaining the elevation distribution matrix and calculating a slope gradient map can provide a clear understanding of the terrain's undulations and slopes.

[0028] Step S212: Classify the terrain area types according to the elevation change rate in the slope gradient map, extract the boundary coordinate set of the slope continuously changing area, and generate the terrain relief feature based on the maximum slope difference in the boundary coordinate set.

[0029] Terrain region classification based on the rate of elevation change in a slope gradient map involves dividing the target area into different terrain types, such as plains, hills, and mountains, based on different ranges of elevation change rates. Continuously varying slope regions are areas within the slope gradient map where the slope values ​​continuously change. Extracting the boundary coordinate sets of these regions accurately determines their extent. Generating a terrain relief feature based on the maximum slope difference within the boundary coordinate set is done by calculating the difference between the maximum and minimum slope values ​​within the boundary coordinate set. This feature reflects the degree of relief in the target area; the greater the maximum slope difference, the greater the relief. In specific implementation, the region in the slope gradient map is first divided into different terrain region types based on a preset elevation change rate threshold. Then, using techniques such as image segmentation, the boundary coordinate sets of the continuously varying slope regions are extracted. Finally, the maximum slope difference within the boundary coordinate set is calculated to generate the terrain relief feature. For example, when processing geological and topographic data in an area containing multiple terrain types, the above steps can accurately classify terrain regions, extract the boundary coordinate sets of the continuously varying slope regions, and generate the terrain relief feature.

[0030] Step S213: Perform structural continuity analysis on the rock layer distribution data in the geological and topographic data to identify the range of the fault line or loose sedimentary area, and generate geological stability characteristics based on the overlapping area ratio of the range and the slope gradient map.

[0031] Strata distribution data records the distribution of strata within the target area, including information such as type, thickness, and orientation. Structural continuity analysis of strata distribution data identifies fault lines or areas of loose sedimentation by analyzing the structure and continuity of the strata. Fault lines are areas of fracture within a stratum, while loose sedimentation areas are areas of relatively loose rock structure, which can affect geological stability.

[0032] The geological stability characteristics are generated based on the overlapping area ratio of the range and the slope gradient map. The geological stability characteristics are obtained by calculating the overlapping area ratio of the range of the fault line or loose sediment area and the corresponding area in the slope gradient map. The larger the overlapping area ratio, the worse the geological stability. In actual operation, geological exploration and other methods can be used to obtain rock layer distribution data in geological and topographic data. Then, through geological modeling and other technologies, the rock layer distribution data is analyzed for structural continuity to identify the range of the fault line or loose sediment area. Finally, the overlapping area ratio is calculated to generate the geological stability characteristics. For example, when processing geological and topographic data in an area with complex geological conditions, the above steps can accurately identify the range of the fault line or loose sediment area and generate geological stability characteristics.

[0033] Step S214: calling the feature fusion layer in the preset terrain coding structure to convert the terrain relief feature into a relief coding sequence, and convert the geological stability feature into a stability coding sequence.

[0034] The feature fusion layer in the preset terrain coding structure is a predefined layer structure used to encode and fuse terrain relief features and geological stability features. Converting terrain relief features into a relief code sequence converts the terrain relief features into a sequence according to the preset coding structure. Similarly, converting geological stability features into a stability code sequence also converts the geological stability features into a code.

[0035] In specific implementations, the feature fusion layer can employ a model structure such as a neural network. By training this model, it can accurately convert terrain relief features and geological stability features into corresponding coding sequences. For example, a multi-layer perceptron (MLP) can be used as the feature fusion layer, taking terrain relief features and geological stability features as inputs. After processing by the MLP, the output is a relief coding sequence and a stability coding sequence.

[0036] Step S215: performing element-by-element weighted superposition of the relief coding sequence and the stability coding sequence according to the coordinate points to generate a terrain parameter sub-vector, wherein the weighting coefficient is dynamically adjusted according to the terrain area type.

[0037] The element-by-element weighted superposition of the relief code sequence and the stability code sequence at each coordinate point is performed by weighted summing the elements of the relief code sequence and the stability code sequence corresponding to the coordinate point, resulting in a new vector. The weighting coefficient is dynamically adjusted based on the terrain region type, assigning different weights to the elements of the relief code sequence and the stability code sequence depending on the terrain region type. In practice, the weighting coefficient is first determined based on the terrain region type. The relief code sequence and the stability code sequence are then weighted superposed element-by-element at each coordinate point to generate a terrain parameter subvector. For example, when processing geological and topographic data in an area containing both mountainous and plain areas, the weighting coefficient of the relief code sequence can be appropriately increased for mountainous coordinate points, while the weighting coefficient of the stability code sequence can be appropriately increased for plain coordinate points. In this way, the generated terrain parameter subvectors can more accurately reflect the characteristics of different terrain regions.

[0038] Step S220: Perform spectral decomposition on the electromagnetic interference data to obtain electromagnetic radiation intensity distribution maps of different frequency bands, and extract the peak intensity characteristics and spatial attenuation characteristics of each frequency band through sliding convolution kernels. The peak intensity characteristics and spatial attenuation characteristics are superimposed according to the frequency band to generate electromagnetic intensity sub-vectors.

[0039] Spectral decomposition decomposes electromagnetic interference data in the frequency domain, converting it into electromagnetic radiation intensity distribution information across different frequency bands. Spectral decomposition provides a clear understanding of the distribution of electromagnetic radiation intensity across different frequency bands within the target area. Sliding the convolution kernel is a common technique in image and signal processing. In this embodiment of the present invention, by sliding the convolution kernel across the electromagnetic radiation intensity distribution map across different frequency bands, the peak intensity characteristics and spatial attenuation characteristics of each frequency band can be extracted.

[0040] The peak intensity feature is the maximum value of electromagnetic radiation intensity within each frequency band, reflecting the strongest electromagnetic radiation within that frequency band. The spatial attenuation feature describes the attenuation of electromagnetic radiation intensity over space, that is, how the electromagnetic radiation intensity changes with increasing distance. The peak intensity feature and the spatial attenuation feature are superimposed on a frequency band basis. That is, the peak intensity feature and the spatial attenuation feature of each frequency band are combined to generate an electromagnetic intensity subvector.

[0041] In practice, EMI data can be spectrally decomposed using methods such as Fourier transforms to obtain electromagnetic radiation intensity distribution maps for different frequency bands. A suitable convolution kernel is then designed and slid across the distribution map to extract the peak intensity and spatial attenuation characteristics for each frequency band. Finally, these two characteristics are superimposed by frequency band to generate electromagnetic intensity subvectors. For example, when processing EMI data in an area containing multiple substations and transmission lines, the above steps can accurately extract the electromagnetic radiation characteristics of the area in different frequency bands, generating representative electromagnetic intensity subvectors.

[0042] Step S230: performing topological structure analysis on the equipment layout data, identifying the connection nodes of the transmission lines and the coverage radius of the substation, and generating a layout topology subvector based on the node connection density and the coverage radius weight.

[0043] Topology analysis involves in-depth analysis of equipment layout data to identify transmission line connections and substation coverage. Transmission line connection nodes are the points where transmission lines connect to each other. The distribution and connection method of these nodes determine the topology of the transmission line. The coverage radius of a substation refers to the area within which the substation can effectively provide power. This radius is related to the substation capacity and the layout of the transmission lines.

[0044] Node connection density refers to the number of nodes connected by transmission lines within a certain area and reflects the density of transmission lines. The coverage radius weight is determined based on factors such as the substation's coverage area and importance. It is used to weight the coverage radius when generating the layout topology subvector. The layout topology subvector is generated by combining node connection density and coverage radius weight, taking these two factors into consideration.

[0045] In practical implementation, graph theory and other methods can be used to perform topological analysis on device layout data. Transmission lines and substations can be abstracted as nodes and edges in a graph. By analyzing the graph structure, the connection nodes of the transmission lines and the coverage radius of the substations can be identified. Node connection density and coverage radius weights are then calculated, and these two factors are weighted together to generate a layout topology subvector. For example, in a city's power grid, topological analysis of device layout data can provide a clear understanding of the transmission line connections and substation coverage, thereby generating an accurate layout topology subvector.

[0046] Step S240: The terrain parameter sub-vector, the electromagnetic intensity sub-vector, and the layout topology sub-vector are spliced ​​according to a preset dimensional alignment rule to obtain a multi-dimensional survey feature vector.

[0047] The preset dimensional alignment rule is a predefined rule used to ensure that the terrain parameter sub-vectors, electromagnetic intensity sub-vectors, and layout topology sub-vectors have consistent dimensions when stitching. In practice, this rule can be adjusted based on the dimensional information of each sub-vector to ensure that they are accurately aligned when stitching.

[0048] The terrain parameter subvector, electromagnetic intensity subvector, and layout topology subvector are concatenated according to preset dimensional alignment rules. This means that these three subvectors are connected in a predetermined order to form a multidimensional survey feature vector containing information from multiple dimensions. This multidimensional survey feature vector integrates information from multiple aspects, including topography, electromagnetics, and equipment layout, to more comprehensively describe the characteristics of the target area.

[0049] In practice, the system first determines a preset dimensional alignment rule and then adjusts the dimensions of the terrain parameter subvector, electromagnetic intensity subvector, and layout topology subvector according to this rule. These three adjusted subvectors are then concatenated to produce a multidimensional survey feature vector. For example, in a large-scale power engineering survey, concatenating the terrain parameter subvector, electromagnetic intensity subvector, and layout topology subvector according to the preset dimensional alignment rule creates a multidimensional survey feature vector that can provide comprehensive and accurate feature information for subsequent power engineering planning.

[0050] Step S300: Input the multi-dimensional survey feature vector into the optimization decision model for iterative parameter adjustment to generate a set of power engineering optimization parameters for the target area, wherein the optimization decision model is trained based on the mapping relationship between historical survey data and verified optimization results.

[0051] The optimization decision model is based on machine learning or deep learning. It learns the mapping relationship between large amounts of historical survey data and verified optimization results. It generates a set of optimized power engineering parameters for the target area based on the input multi-dimensional survey feature vector. Iterative parameter adjustment involves continuously adjusting model parameters during model training to gradually bring the model's output closer to the optimal solution.

[0052] In practical implementation, the optimization decision model can employ models such as neural networks and genetic algorithms. For example, neural networks, through the connection and computation of multiple layers of neurons, process and analyze multidimensional survey feature vectors, outputting a set of optimized parameters for the power project. During training, historical survey data is used as input, and verified optimization results are output. By continuously adjusting the neural network's weights and biases, the model learns the mapping between historical survey data and verified optimization results.

[0053] For example, in a city's power engineering planning, the city's multidimensional survey feature vector is input into the optimization decision-making model. After iterative parameter adjustment, the model can generate a set of optimized parameters for the city's power engineering, including transmission line path planning parameters, substation site coordinate parameters, and interference suppression parameters. These parameters can provide scientific and reasonable guidance for the construction of power engineering.

[0054] In one embodiment, the optimization decision model includes a parameter adjustment network and a verification feedback network. Based on this, step S300 inputs the multi-dimensional survey feature vector into the optimization decision model for iterative parameter adjustment to generate a set of optimized power engineering parameters for the target area. Specifically, the following steps may be included:

[0055] Step S310: performing nonlinear transformation on the multi-dimensional survey feature vector through a parameter adjustment network to generate an initial optimization parameter set, wherein the initial optimization parameter set includes path planning parameters, site selection coordinate parameters and interference suppression parameters.

[0056] The parameter adjustment network is a key component of the optimization decision model. It is used to perform nonlinear transformations on multidimensional survey feature vectors. Nonlinear transformations involve processing input data through nonlinear functions, resulting in more complex output features and patterns. In this embodiment of the present invention, the parameter adjustment network performs nonlinear transformations on the multidimensional survey feature vectors to generate an initial set of optimized parameters.

[0057] The path planning parameters in the initial optimization parameter set are used to determine the path of the transmission line, the site selection coordinate parameters are used to determine the location of the substation, and the interference suppression parameters are used to control the impact of electromagnetic interference. These parameters are important for power project planning.

[0058] In specific implementations, the parameter adjustment network can adopt a fusion structure of a multilayer perceptron (MLP) and an attention mechanism. The MLP is a common neural network structure consisting of an input layer, hidden layers, and an output layer. Through the connection and calculation of multiple layers of neurons, it achieves nonlinear transformations on input data. The attention mechanism helps the network focus on important features in the input data, improving model performance.

[0059] For example, by inputting a multidimensional survey feature vector into a parameter adjustment network, the network, through the computational power of a multilayer perceptron and the action of an attention mechanism, can comprehensively analyze features such as terrain, electromagnetics, and equipment layout to generate an initial set of optimized parameters. For example, in a power project planning project in a mountainous area, the parameter adjustment network can generate reasonable transmission line routing parameters and substation site coordinate parameters based on the mountain's topographical characteristics and electromagnetic environment.

[0060] As an embodiment, the parameter adjustment network includes a fusion structure of a multilayer perceptron and an attention mechanism. Based on this, step S310 performs a nonlinear transformation on the multidimensional survey feature vector through the parameter adjustment network to generate an initial optimization parameter set. Specifically, the following steps may be included:

[0061] Step S311: Input the terrain parameter sub-vector into the first hidden layer of the multilayer perceptron for weight distribution to obtain the terrain influence weight coefficient.

[0062] A multilayer perceptron is a neural network structure composed of multiple neuron layers. The first hidden layer is the first hidden layer in the multilayer perceptron. Inputting the terrain parameter subvector into the first hidden layer of the multilayer perceptron for weight assignment involves performing a weighted summation of the elements in the terrain parameter subvector using the neurons in the first hidden layer to obtain the terrain influence weight coefficient.

[0063] The terrain influence weight coefficient reflects the importance of terrain factors in power project planning, affecting subsequent decisions such as route planning and site selection. In practice, the first hidden layer of a multilayer perceptron can be trained to obtain appropriate weight values, enabling it to accurately calculate the terrain influence weight coefficient based on the terrain parameter subvector.

[0064] For example, in planning a power project in a mountainous area, the terrain parameter subvector contains information such as the mountain's topographic relief and geological stability. This subvector is input into the first hidden layer of a multilayer perceptron, where neurons perform calculations to determine the terrain influence weight coefficient. If the mountainous area has high topographic relief and poor geological stability, the terrain influence weight coefficient will be relatively large, indicating that topographic factors need to be considered prominently in power project planning.

[0065] Step S312: Perform cross-attention calculation on the electromagnetic intensity sub-vector and the layout topology sub-vector to generate electromagnetic-layout association features.

[0066] Cross-attention calculation is a computational method used to process the relationships between multiple feature vectors. It can help the model better capture the correlation information between different feature vectors. In this embodiment of the present invention, cross-attention calculation is performed on the electromagnetic intensity subvector and the layout topology subvector. This means that through the attention mechanism, the model focuses on the important features in the electromagnetic intensity subvector and the layout topology subvector, generating electromagnetic-layout correlation features.

[0067] The electromagnetic-layout correlation feature reflects the relationship between the electromagnetic environment and equipment layout. For example, the layout of transmission lines may affect the distribution of electromagnetic radiation, and the intensity of electromagnetic radiation may also affect equipment operation. By generating the electromagnetic-layout correlation feature, we can better consider the role of electromagnetic and layout factors in power project planning.

[0068] In specific implementations, cross-attention calculations can be performed using methods such as dot product attention in the attention mechanism. For example, the electromagnetic intensity subvector and the layout topology subvector are used as the query vector and key-value vector, respectively. By calculating the dot product between them, an attention score is obtained. The key-value vector is then weighted and summed according to the attention score to generate the electromagnetic-layout association feature.

[0069] Step S313: performing weighted aggregation on the electromagnetic-layout correlation features based on the terrain influence weight coefficient to generate a comprehensive decision feature.

[0070] The weighted aggregation of electromagnetic-layout correlation features based on the terrain influence weight coefficient refers to multiplying the terrain influence weight coefficient with each element in the electromagnetic-layout correlation feature, and then summing the multiplied results to obtain the comprehensive decision-making feature.

[0071] The comprehensive decision-making feature integrates information from multiple aspects, including topography, electromagnetics, and layout. It can more comprehensively reflect the characteristics of the target area and the needs of power project planning. Through weighted aggregation, topographic factors are reasonably reflected in the comprehensive decision-making feature, making the model's decision-making more scientific and accurate.

[0072] For example, in a city's power engineering planning, the terrain influence weight coefficient reflects the degree of impact of the city's topography on the power project. By combining this weight coefficient with the electromagnetic-layout correlation feature, the resulting comprehensive decision-making feature comprehensively considers factors such as the city's topography, electromagnetic environment, and equipment layout, providing a more comprehensive basis for subsequent route planning and site selection.

[0073] Step S314: Linearly map the comprehensive decision features through the output layer of the multilayer perceptron to generate an initial optimization parameter set.

[0074] The output layer of the multilayer perceptron is the last layer in the multilayer perceptron, which is used to linearly map the input feature vector to generate the final output result. In an embodiment of the present invention, linear mapping of the comprehensive decision-making features through the output layer of the multilayer perceptron means taking the comprehensive decision-making features as input and obtaining an initial optimization parameter set through neuron calculation in the output layer. The initial optimization parameter set includes information such as path planning parameters, site selection coordinate parameters, and interference suppression parameters. These parameters are the preliminary plan for power engineering planning. Through the linear mapping of the output layer of the multilayer perceptron, the comprehensive decision-making features can be converted into specific parameter values, providing a basis for subsequent simulation deployment verification and iterative adjustment.

[0075] In practical implementation, the output layer of a multilayer perceptron can perform linear calculations on the integrated decision features based on trained weights and biases. For example, the integrated decision features are multiplied by the output layer's weight matrix and then added to the bias vector to generate an initial set of optimized parameters. In the planning of a large-scale power project, linear mapping of the integrated decision features through the output layer of a multilayer perceptron can generate an initial set of optimized parameters that can provide specific parameter guidance for preliminary project planning.

[0076] Step S320: Calling the verification feedback network to perform simulated deployment verification on the initial optimization parameter set and generate a parameter adjustment feedback signal, wherein the simulated deployment verification includes calculation of the matching degree between the transmission path and the terrain, analysis of the overlap rate of the substation coverage, and prediction of the electromagnetic interference suppression effect.

[0077] The verification feedback network is another component of the optimization decision model, used to simulate the deployment of the initial optimization parameter set. Simulation verification involves simulating the implementation of the initial optimization parameter set in a virtual environment to evaluate its feasibility and effectiveness.

[0078] Transmission path and terrain matching calculations measure the degree of alignment between the transmission line's path and the target area's terrain, for example, determining whether the line passes through steep slopes or geological fault zones. Substation coverage overlap analysis analyzes the overlap between the virtual substation's coverage area and that of existing power facilities to avoid wasted resources. Electromagnetic interference suppression effectiveness predictions predict the attenuation of electromagnetic radiation intensity in the target area after applying interference suppression parameters, thereby evaluating the effectiveness of interference suppression measures.

[0079] Based on the results of the simulated deployment verification, a parameter adjustment feedback signal is generated. The parameter adjustment feedback signal includes path adjustment direction, coordinate offset, and interference suppression correction coefficient. These signals are used to guide the parameter adjustment network to adjust the initial optimized parameter set.

[0080] In practical implementation, the verification feedback network can utilize a simulation model to simulate the deployment of an initial set of optimized parameters, calculating metrics such as the degree of transmission path compatibility with terrain, the overlap rate of substation coverage, and electromagnetic interference suppression effectiveness. These metrics are then used to generate parameter adjustment feedback signals. For example, in a city's power engineering planning, the verification feedback network can simulate the laying of transmission lines and the construction of substations, assessing their compatibility with the terrain and existing power infrastructure, and generating corresponding parameter adjustment feedback signals.

[0081] As an implementation method, step S320, invoking the verification feedback network to perform simulated deployment verification on the initial optimization parameter set and generate a parameter adjustment feedback signal, may specifically include the following steps:

[0082] Step S321: Generate a virtual power transmission path according to the path planning parameters, and calculate a matching score between the virtual power transmission path and the geological stability characteristics in the terrain parameter sub-vector.

[0083] Generating a virtual transmission path based on path planning parameters means simulating the transmission line path in a virtual environment based on the path planning parameters in the initial optimization parameter set. The geological stability feature is an important feature in the terrain parameter subvector, which reflects the geological stability of the target area.

[0084] The match score between the virtual transmission path and the geological stability characteristics is calculated by evaluating whether the virtual transmission path passes through geologically unstable areas and the degree to which it passes through these areas. A higher match score indicates a better match between the virtual transmission path and the geological stability characteristics, and a higher safety rating for the transmission line.

[0085] In practice, a spatial overlay analysis can be performed on the virtual transmission path and the geological stability characteristics in the terrain parameter subvector. Statistics are then compiled to show indicators such as the length or area of ​​geologically unstable areas that the virtual transmission path passes through. A matching score is then calculated based on pre-set scoring rules. For example, in power project planning in a mountainous area, a virtual transmission path is generated based on the path planning parameters, and the matching score between this path and the geological stability characteristics of the mountain area is calculated. If the virtual transmission path avoids fault lines and areas of loose sedimentation, the matching score will be relatively high.

[0086] Step S322: Generate a virtual substation coverage area based on the site selection coordinate parameters, and analyze the overlap rate between the virtual substation coverage area and the coverage range of existing power facilities.

[0087] Generating a virtual substation coverage area based on site selection coordinate parameters involves determining the substation's location in a virtual environment based on the site selection coordinate parameters in the initial optimization parameter set. The substation's coverage area is then calculated based on the substation's capacity and the layout of the transmission lines. Existing power facility coverage refers to the coverage of existing substations and transmission lines within the target area.

[0088] The overlap ratio between the virtual substation coverage area and the coverage area of ​​existing power facilities is analyzed by calculating the ratio of the overlapping area between the virtual substation coverage area and the existing power facility coverage area to the area of ​​the virtual substation coverage area. A higher overlap ratio indicates a greater degree of overlap between the virtual substation coverage area and the existing power facility coverage area, potentially leading to resource waste. In practical implementation, tools such as Geographic Information Systems (GIS) can be used to perform spatial analysis of the virtual substation coverage area and the coverage area of ​​existing power facilities to calculate the overlap ratio. For example, in a city's power project planning, a virtual substation coverage area is generated based on site coordinate parameters, and then the overlap ratio between this area and the coverage area of ​​the city's existing power facilities is analyzed. A high overlap ratio indicates that the substation site needs to be adjusted to avoid resource waste.

[0089] Step S323: predicting the electromagnetic radiation intensity attenuation curve of the target area based on the interference suppression parameter, and calculating the deviation value between the attenuation curve and the preset electromagnetic safety threshold.

[0090] Predicting the electromagnetic radiation intensity attenuation curve of a target area based on interference suppression parameters involves using electromagnetic propagation models and other methods based on the interference suppression parameters in the initial optimized parameter set to predict the attenuation of the electromagnetic radiation intensity in the target area after interference suppression measures are implemented. The preset electromagnetic safety threshold is the upper limit of electromagnetic radiation intensity specified to ensure the safety of personnel and equipment.

[0091] Calculating the deviation between the attenuation curve and the preset electromagnetic safety threshold is done by comparing the difference between each point on the attenuation curve and the preset electromagnetic safety threshold. Smaller deviations indicate more effective interference suppression measures and closer electromagnetic radiation intensity to the safety threshold. In practical implementation, tools such as electromagnetic simulation software can be used to predict the electromagnetic radiation intensity attenuation curve for the target area based on interference suppression parameters. An algorithm is then developed to calculate the deviation between the attenuation curve and the preset electromagnetic safety threshold. For example, in planning a power project near a substation, the electromagnetic radiation intensity attenuation curve for the area is predicted based on interference suppression parameters, and the deviation between this curve and the preset electromagnetic safety threshold is calculated. A smaller deviation indicates that the interference suppression measures are effectively controlling electromagnetic radiation intensity.

[0092] Step S324: Generate a parameter adjustment feedback signal based on the matching score, overlap ratio, and deviation value. The parameter adjustment feedback signal includes the path adjustment direction, coordinate offset, and interference suppression correction factor. Generating the parameter adjustment feedback signal based on the matching score, overlap ratio, and deviation value refers to generating the parameter adjustment feedback signal based on the calculated matching score, overlap ratio, and deviation value, taking into account the impact of these indicators. The parameter adjustment feedback signal is used to guide the parameter adjustment network to adjust the initial optimization parameter set, resulting in a more reasonable and effective set of optimized power engineering parameters.

[0093] Path adjustment direction refers to determining the direction in which the transmission line path needs to be adjusted, such as shifting it left or right, based on the matching score. Coordinate offset refers to determining the offset by which the substation site coordinates need to be adjusted, based on the overlap ratio, to avoid overlapping coverage areas. The interference suppression correction coefficient refers to determining the coefficient by which the interference suppression parameters need to be adjusted, based on the deviation value, to improve the effectiveness of interference suppression measures. In specific implementations, a parameter adjustment feedback signal can be generated based on the matching score, overlap ratio, and deviation value, according to preset rules and algorithms. For example, if the matching score is low, it indicates that the transmission line path needs to be adjusted, and the path adjustment direction is determined based on the terrain and geological conditions. If the overlap ratio is high, it indicates that the substation site needs to be adjusted, and the coordinate offset is calculated. If the deviation value is large, it indicates that the interference suppression parameters need to be adjusted, and the interference suppression correction coefficient is determined.

[0094] Step S330: updating the weight coefficients of the parameter adjustment network according to the parameter adjustment feedback signal, and repeatedly performing nonlinear transformation and simulated deployment verification until the initial optimized parameter set meets the preset deployment constraints.

[0095] Updating the weight coefficients of the parameter adjustment network based on the parameter adjustment feedback signal refers to adjusting the weights of the parameter adjustment network based on the information in the parameter adjustment feedback signal so that the network's output results better meet actual needs. Repeatedly performing nonlinear transformation and simulated deployment verification refers to using the updated parameter adjustment network to perform nonlinear transformation on the multi-dimensional survey feature vector again to generate a new set of initial optimized parameters, and then calling the verification feedback network to simulate and verify the new set of initial optimized parameters.

[0096] Pre-set deployment constraints refer to conditions that must be met during power project planning, such as transmission line security, substation coverage, and electromagnetic interference limitations. The iteration process stops only when the initial set of optimized parameters satisfies the preset deployment constraints. In specific implementations, optimization algorithms such as gradient descent can be used to update the weight coefficients of the parameter adjustment network based on the parameter adjustment feedback signal. For example, the weight coefficients related to path planning and site selection in the parameter adjustment network can be adjusted based on information such as path adjustment direction and coordinate offset. Through repeated iterations, the initial set of optimized parameters gradually satisfies the preset deployment constraints.

[0097] Step S340: Determine the initial optimization parameter set that meets the deployment constraint conditions as the power engineering optimization parameter set.

[0098] After multiple iterations, if the initial optimized parameter set meets the preset deployment constraints, it is determined as the power project optimization parameter set. This set contains the optimal parameters required for power project planning in the target area, including transmission line routing parameters, substation site coordinate parameters, and interference suppression parameters.

[0099] Power engineering optimization parameter sets are a crucial foundation for power engineering construction. They ensure the safe and efficient operation of transmission lines, the rational layout of substations, and the effective control of electromagnetic interference. For example, in the power engineering planning of a large industrial park, the determined power engineering optimization parameter set can guide the laying of transmission lines and the construction of substations, ensuring a more stable and reliable power supply for the park.

[0100] As an implementation method, the pre-trained feature extraction network can be trained by the following steps:

[0101] Step S10: Acquire a historical survey data set, where the historical survey data set includes terrain data, electromagnetic data, and equipment layout data of multiple historical areas, as well as a verified optimization parameter set corresponding to each historical area.

[0102] A historical survey dataset refers to a collection of data collected during past power engineering surveys. It contains topographic data, electromagnetic data, and equipment layout data for multiple historical regions, as well as a verified optimization parameter set corresponding to each historical region. The topographic data reflects the topographic characteristics of the historical region, the electromagnetic data records the electromagnetic environment of the historical region, and the equipment layout data shows the layout of power facilities in the historical region. The verified optimization parameter set is the power engineering optimization parameters that have been verified and applied to the historical region.

[0103] Historical survey datasets can be obtained in a variety of ways, such as from power company databases or from relevant survey reports. This data is an important foundation for pre-training feature extraction networks. By learning from this data, the network can understand the relationship between topographic, electromagnetic, and equipment layout data and power engineering optimization parameters.

[0104] For example, historical survey data from multiple cities can be collected, including information such as terrain elevation, geological structure, electromagnetic radiation intensity distribution, transmission line topology, and substation locations, along with corresponding verified optimization parameter sets, such as transmission line routing, substation site selection, and interference suppression measures. This data can provide rich training samples for pre-training feature extraction networks.

[0105] Step S20: performing data enhancement processing on the historical survey data set to generate an expanded training sample set, wherein the data enhancement processing includes random rotation of terrain data, noise injection of electromagnetic data, and perturbation of layout data nodes.

[0106] Data augmentation is a method that increases the number and diversity of training samples by transforming and expanding the original data. In this embodiment of the present invention, data augmentation is performed on the historical survey dataset, including random rotation of the terrain data, noise injection of the electromagnetic data, and node perturbation of the layout data.

[0107] Random rotation of terrain data involves randomly rotating information such as the elevation distribution matrix within the terrain data to simulate different terrain perspectives and orientations. Electromagnetic data noise injection involves adding noise to electromagnetic data to simulate noise interference in real-world environments. Layout data node perturbation involves randomly disconnecting and reconnecting transmission line nodes within the layout data to alter the topology of the transmission lines.

[0108] Data augmentation can generate expanded training sample sets, increase the diversity and complexity of training data, and improve the generalization ability of pre-trained feature extraction networks. In practice, data augmentation can be implemented using techniques such as image processing and data processing. For example, image processing libraries can be used to randomly rotate terrain data, noise generation algorithms can be used to inject noise into electromagnetic data, and graph theory algorithms can be used to perturb nodes in layout data.

[0109] As an implementation manner, the above step S20, performing data enhancement processing on the historical survey data set to generate an expanded training sample set, may specifically include the following steps:

[0110] Step S21: performing random rotation transformation on the terrain data to generate a rotated terrain elevation map, and adding randomly generated geological fracture simulation features to the rotated terrain elevation map.

[0111] Performing a random rotation transformation on terrain data involves randomly rotating the terrain elevation map in the terrain data to simulate different terrain perspectives and orientations. This random rotation transformation can increase the diversity of the terrain data, making the training samples more representative.

[0112] After generating the rotated terrain elevation map, randomly generated geological fracture simulation features are added to simulate the geological fractures that may exist in the actual terrain. Geological fractures can affect terrain stability and power engineering construction. By adding geological fracture simulation features, the pre-trained feature extraction network can learn more complex terrain features.

[0113] In a specific implementation, an image processing library such as OpenCV can be used to randomly rotate the terrain elevation map. Then, using a noise generation algorithm or image processing techniques, randomly generated geological fracture simulation features can be added to the rotated terrain elevation map. For example, a Gaussian noise generation algorithm can be used to generate a noise image of geological fractures, which can then be overlaid on the rotated terrain elevation map to obtain a terrain elevation map containing the geological fracture simulation features.

[0114] Step S22: injecting Gaussian white noise into the electromagnetic data to generate a noisy electromagnetic spectrum diagram, and smoothing the noisy electromagnetic spectrum diagram through frequency domain filtering.

[0115] Injecting Gaussian white noise into electromagnetic data involves adding Gaussian white noise to the electromagnetic data spectrum to simulate the noise interference found in real environments. Gaussian white noise is a type of noise with a uniform power spectral density, which can increase the complexity and diversity of electromagnetic data.

[0116] After generating a noisy electromagnetic spectrum, frequency-domain filtering is used to smooth it out. This removes high-frequency components from the noise, making the spectrum smoother and more stable. Frequency-domain filtering can be implemented using methods such as Fourier transforms. The noisy electromagnetic spectrum is converted to the frequency domain, then filtered to remove high-frequency components. Finally, the spectrum is converted back to the time domain to produce a smoothed electromagnetic spectrum.

[0117] In practice, signal processing libraries such as SciPy can be used to inject Gaussian white noise into the electromagnetic data. Fourier transforms and filters can then be used to perform frequency-domain filtering and smoothing on the noisy electromagnetic spectrum. For example, a fast Fourier transform (FFT) can be used to convert the noisy electromagnetic spectrum to the frequency domain, a low-pass filter can be used to remove high-frequency components, and an inverse fast Fourier transform (IFFT) can be used to convert the spectrum back to the time domain to obtain the smoothed electromagnetic spectrum.

[0118] Step S23: Randomly disconnect and reconnect the transmission line nodes in the equipment layout data to generate an equipment layout diagram with a mutated topology structure.

[0119] Randomly disconnecting and reconnecting transmission line nodes in the device layout data involves randomly selecting transmission line nodes for disconnection or reconnection, thereby changing the topology of the transmission lines. This operation can simulate line failures or modifications that may occur in actual power networks, increasing the diversity of the device layout data.

[0120] The equipment layout diagram after the topology mutation is generated by randomly disconnecting and reconnecting transmission line nodes. This diagram shows the mutated transmission line topology and provides more training samples for the pre-trained feature extraction network.

[0121] In practice, graph theory algorithms can be used to randomly disconnect and reconnect transmission line nodes in the device layout data. For example, Python's NetworkX library can be used to represent the graph structure of the device layout data. Nodes are then randomly selected for disconnection and reconnection, updating the graph structure to obtain a device layout graph with a modified topology.

[0122] Step S24: combining the rotated terrain elevation map, the noisy electromagnetic spectrum map, and the equipment layout map after topological structure variation into new training samples, and adding them to the expanded training sample set.

[0123] Combining the rotated terrain elevation map, the noisy electromagnetic spectrum map, and the topologically modified equipment layout map as a new training sample involves integrating the augmented terrain data, electromagnetic data, and equipment layout data to create a new training sample. This sample contains more features and information, which can improve the learning ability of the pre-trained feature extraction network.

[0124] Adding new training samples to the augmented training set increases the number and diversity of training samples. By continuously performing data augmentation and sample combination, the augmented training set can include more diverse training samples, enabling the pre-trained feature extraction network to learn more comprehensive features and patterns.

[0125] For example, a terrain elevation map that has undergone random rotation and has been enhanced with geological fracture simulation features, an electromagnetic spectrum map that has undergone noise injection and frequency domain filtering, and a device layout map that has undergone topological structure mutation are combined to form a new training sample. This sample is then added to the expanded training sample set for training the pre-trained feature extraction network.

[0126] Step S30: construct an initial feature extraction network, and input the expanded training sample set into the initial feature extraction network to perform feature extraction and generate a prediction optimization parameter set.

[0127] Building an initial feature extraction network involves designing and building a neural network model for feature extraction. This model can use architectures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), depending on specific needs and data characteristics.

[0128] Inputting the expanded training sample set into the initial feature extraction network for feature extraction involves using the terrain data, electromagnetic data, and equipment layout data from the expanded training sample set as input. The initial feature extraction network then calculates and processes the data to extract representative features and generate a set of prediction optimization parameters. The prediction optimization parameter set is the initial optimization parameter generated by the initial feature extraction network based on the input data.

[0129] In specific implementations, you can use deep learning frameworks such as TensorFlow and PyTorch to build an initial feature extraction network. For example, you can build an initial feature extraction network based on CNN, input the expanded training sample set into the network, and generate a set of prediction optimization parameters through calculations in convolutional layers, pooling layers, and fully connected layers.

[0130] Step S40: Calculate the mean square error loss between the predicted optimization parameter set and the verified optimization parameter set, and update the parameters of the initial feature extraction network based on the gradient descent algorithm until the mean square error loss converges to a preset threshold.

[0131] The mean square error loss is a loss function used to measure the difference between the predicted value and the true value. In an embodiment of the present invention, the mean square error loss between the predicted optimization parameter set and the verified optimization parameter set is calculated by calculating the average of the sum of the squares of the differences between each parameter in the predicted optimization parameter set and the corresponding parameter in the verified optimization parameter set to obtain the mean square error loss.

[0132] Updating the parameters of the initial feature extraction network using the gradient descent algorithm involves adjusting the weights and biases of the initial feature extraction network based on the gradient information of the mean squared error loss, thereby gradually reducing the mean squared error loss. Gradient descent is a commonly used optimization algorithm that iteratively updates the network parameters to minimize the loss function.

[0133] The preset threshold is a pre-set error value. When the mean squared error loss converges to the preset threshold, it indicates that the initial feature extraction network has learned enough information and the training process can be stopped. In practice, you can use the optimizer provided by the deep learning framework to implement the gradient descent algorithm. For example, use the Adam optimizer to update the parameters of the initial feature extraction network based on the mean squared error loss until the mean squared error loss converges to the preset threshold.

[0134] Step S50: determining the initial feature extraction network after parameter update as the pre-trained feature extraction network.

[0135] When the mean squared error loss converges to a preset threshold, the initial feature extraction network with updated parameters is designated as the pretrained feature extraction network. This network has learned from historical survey datasets the relationship between topographic, electromagnetic, and equipment layout data and power engineering optimization parameters, making it capable of effectively extracting features from new multi-source survey data.

[0136] The pre-trained feature extraction network can be used in subsequent power engineering survey data processing to support the generation of multi-dimensional survey feature vectors. For example, in a new power engineering survey project, the multi-source survey data for the project can be input into the pre-trained feature extraction network. The network can extract representative features and generate multi-dimensional survey feature vectors, providing a basis for subsequent optimization decisions.

[0137] Step S400: Generate a power facility deployment plan for the target area based on the power engineering optimization parameter set. The deployment plan includes transmission line path planning results, substation site coordinates, and electromagnetic interference suppression strategy.

[0138] The power engineering optimization parameter set includes information such as transmission line routing parameters, substation site coordinate parameters, and interference suppression parameters. These parameters are used to generate a power facility deployment plan for the target area. The transmission line routing result refers to the specific path of the transmission line determined based on the routing parameters. It takes into account factors such as topography, geology, and electromagnetics to ensure the safe and efficient operation of the transmission line. Substation site coordinates refer to the specific location of the substation determined based on the site selection coordinate parameters. They consider factors such as power load distribution, topographic conditions, and the electromagnetic environment to achieve a reasonable substation layout. Electromagnetic interference suppression strategies refer to measures for controlling electromagnetic interference, such as installing shielding equipment and adjusting the transmission line layout, based on the interference suppression parameters.

[0139] In practical implementation, tools such as geographic information systems (GIS) can be used to generate power facility deployment plans based on a set of optimized power engineering parameters. For example, transmission line routing parameters and terrain data can be input into the GIS, and spatial analysis and routing algorithms can be used to generate transmission line routing results. Substation site coordinates can be determined in the GIS based on substation site selection coordinate parameters and power load distribution data. Electromagnetic interference suppression strategies can be developed based on interference suppression parameters and electromagnetic environment data.

[0140] As an embodiment, step S400, generating a power facility deployment plan for a target area based on a set of power engineering optimization parameters, may specifically include the following steps:

[0141] Step S410: extracting an initial transmission line coordinate point set based on the path planning parameters in the power engineering optimization parameter set, and identifying coordinate points in the coordinate point set that overlap with steep slope areas or geological fault zones in combination with the elevation gradient distribution characteristics in the terrain parameter subvector.

[0142] Extracting an initial set of transmission line coordinate points based on the path planning parameters in the power engineering optimization parameter set involves determining the approximate direction and location of the transmission line based on the path planning parameters and extracting a set of coordinate points along the transmission line. This set of coordinate points is the initial result of the transmission line path planning.

[0143] By combining the elevation gradient distribution characteristics of the terrain parameter subvectors, we identify coordinate points that overlap with steep slopes or geological fault zones. This involves spatially overlaying the initial transmission line coordinate point set with the elevation gradient distribution characteristics of the terrain parameter subvectors to identify coordinate points that are concentrated in steep slopes or geological fault zones. These coordinate points may affect the safety and stability of the transmission line and require further processing.

[0144] In practical implementation, tools such as geographic information systems (GIS) can be used for spatial overlay analysis. The initial transmission line coordinate point set and the elevation gradient distribution characteristics within the terrain parameter subvector are imported into the GIS. Using spatial analysis, coordinate points that overlap with steep slopes or geological fault zones can be identified. For example, in planning a power project in a mountainous area, the initial transmission line coordinate point set can be extracted based on the path planning parameters. The elevation gradient distribution characteristics within the terrain parameter subvector of the mountainous area can then be combined to identify coordinate points located within steep slopes.

[0145] Step S420: verify the electromagnetic interference intensity of the overlapping coordinate points, call the peak intensity distribution data of the corresponding area in the electromagnetic intensity sub-vector, and select the coordinate points whose peak intensity exceeds the safety threshold as high-risk path nodes.

[0146] Verifying the electromagnetic interference intensity of overlapping coordinate points refers to checking whether the electromagnetic interference intensity of the coordinate points identified in step S410 that overlap with the steep slope area or geological fault zone exceeds the safety threshold. Retrieving the peak intensity distribution data for the corresponding area in the electromagnetic intensity subvector refers to obtaining the peak electromagnetic radiation intensity information for the area where these coordinate points are located from the electromagnetic intensity subvector.

[0147] Screening coordinate points with peak intensity exceeding the safety threshold as high-risk path nodes means marking coordinate points where the peak intensity of electromagnetic radiation exceeds the safety threshold as high-risk path nodes. These nodes may be subject to strong electromagnetic interference, affecting the normal operation of the transmission line, and appropriate measures must be taken to address them.

[0148] In practical implementation, an algorithm can be developed to verify the electromagnetic interference intensity of overlapping coordinate points. Based on the coordinate point's location, the peak intensity distribution data for the corresponding area is extracted from the electromagnetic intensity subvector. This data is then compared with a safety threshold, and coordinate points exceeding the safety threshold are identified as high-risk path nodes. For example, in power project planning near a substation, electromagnetic interference intensity verification is performed on coordinate points that overlap with steep slopes, and coordinate points with peak intensity exceeding the safety threshold are identified as high-risk path nodes.

[0149] Step S430: Execute path detour optimization for high-risk path nodes, generate avoidance path correction trajectories based on the geological stability characteristics in the terrain parameter subvector, and smoothly connect the endpoints of the correction trajectory with the unadjusted initial coordinate point set to form the transmission line path planning result.

[0150] Performing route detour optimization on high-risk path nodes involves taking measures to change the transmission line's route to avoid the high-risk path nodes identified in step S420. Generating an avoidance path correction trajectory based on the geological stability characteristics in the terrain parameter subvector involves finding a reasonable path that avoids the high-risk path nodes based on the geological stability characteristics and generating an avoidance path correction trajectory.

[0151] Smoothly connecting the endpoints of the corrected trajectory to the unadjusted initial coordinate point set means connecting the start and end points of the avoidance path corrected trajectory to the unadjusted initial coordinate point set, making the transmission line path smoother and more continuous. The final transmission line path planning result is obtained by optimizing the circuitous path and connecting high-risk path nodes.

[0152] In specific implementations, path planning algorithms and spatial analysis techniques can be used to perform detour optimization on high-risk path nodes. Based on the geological stability characteristics of the terrain parameter subvector, detourable areas are determined, and then a corrected avoidance path trajectory is generated within the detourable area. Finally, methods such as curve fitting are used to smoothly connect the endpoints of the corrected trajectory with the unadjusted initial coordinate point set. For example, in the planning of a power project in a mountainous area, detour optimization is performed on high-risk path nodes. Based on the geological stability characteristics of the mountainous area, a corrected avoidance path trajectory is generated and smoothly connected with the unadjusted initial coordinate point set to form the transmission line path planning result.

[0153] As an embodiment, step S430 performs path detour optimization on high-risk path nodes and generates an avoidance path correction trajectory based on the geological stability characteristics in the terrain parameter subvector. Specifically, the following steps may be included:

[0154] Step S431: Extract the terrain undulation characteristics of the area where the high-risk path node is located, generate a contour distribution map centered on the node, and determine the boundary of the detourable area based on the direction of change of the contour curvature.

[0155] Extracting the terrain relief characteristics of the area where the high-risk path node is located refers to obtaining the terrain relief information of the area where the high-risk path node is located from the terrain parameter subvector. Generating a contour distribution map centered on the high-risk path node is to draw a contour map centered on the high-risk path node based on the terrain relief characteristics. This map can intuitively display the terrain relief of the area.

[0156] Determining the boundaries of detourable areas based on the curvature of contour lines involves analyzing the curvature of contour lines to identify areas with relatively flat terrain suitable for transmission line detours and then determining the boundaries of these areas. The boundaries of the detourable areas define the range within which transmission line detours can be made.

[0157] In practical implementation, tools such as Geographic Information Systems (GIS) can be used to extract the topographical characteristics of areas where high-risk route nodes are located and generate contour maps. Spatial analysis algorithms can then be used to determine the boundaries of detour areas by analyzing the curvature of the contour lines. For example, in power project planning in a mountainous area, for a high-risk route node, the topographical characteristics of the area where it is located are extracted, and a contour map is generated. The boundaries of the detour area are then determined based on the curvature of the contour lines.

[0158] Step S432: Call the peak intensity distribution data of the corresponding area in the electromagnetic intensity sub-vector, exclude the sub-area whose electromagnetic radiation intensity exceeds the preset threshold in the detourable area, and generate the electromagnetic safety detour range.

[0159] Retrieving peak intensity distribution data for corresponding areas within the electromagnetic intensity subvectors refers to obtaining peak electromagnetic radiation intensity information for areas containing high-risk path nodes and detourable areas from the electromagnetic intensity subvectors. Excluding sub-areas within detourable areas where electromagnetic radiation intensity exceeds a preset threshold refers to excluding sub-areas within the detourable area where electromagnetic radiation intensity exceeds the threshold, based on a preset electromagnetic radiation safety threshold, and retaining only areas within a safe range.

[0160] The electromagnetic safety detour range is generated by excluding sub-areas where electromagnetic radiation intensity exceeds a preset threshold, resulting in a safe area for transmission line detours. This area takes into account both topographical factors and electromagnetic radiation factors, ensuring that the transmission line is not subject to excessive electromagnetic interference during the detour.

[0161] In a specific implementation, an algorithm can be written to access the peak intensity distribution data for the corresponding areas in the electromagnetic intensity subvector and perform filtering and exclusion operations. The detourable area and electromagnetic intensity data are imported into the algorithm. Sub-areas with electromagnetic radiation intensity exceeding the threshold are excluded based on a preset threshold to generate an electromagnetically safe detour range. For example, in a power project planning near a substation, the peak intensity distribution data for the corresponding areas in the electromagnetic intensity subvector are retrieved. Sub-areas with electromagnetic radiation intensity exceeding the preset threshold are excluded within the detourable area to generate an electromagnetically safe detour range. In a specific implementation, an algorithm can be written to access the peak intensity distribution data for the corresponding areas in the electromagnetic intensity subvector and perform filtering and exclusion operations. The detourable area and electromagnetic intensity data are imported into the algorithm. Sub-areas with electromagnetic radiation intensity exceeding the threshold are excluded based on a preset threshold to generate an electromagnetically safe detour range. For example, in a power project planning near a substation, for detourable areas at high-risk path nodes, the peak intensity distribution of electromagnetic radiation in and around the area is obtained from the electromagnetic intensity subvector. Assuming a preset electromagnetic radiation safety threshold, the algorithm checks the electromagnetic radiation intensity of each sub-area within the detourable zone. If the electromagnetic radiation intensity of a sub-area exceeds the threshold, it is removed from the detourable zone. This method ensures that the electromagnetic radiation exposure to transmission lines within this safe detour range remains at a safe level, preventing electromagnetic interference from impacting the normal operation of the transmission line.

[0162] Step S433: Based on the superposition result of the terrain undulation characteristics and the electromagnetic safety detour range, a detour channel model that allows path correction is constructed. The model includes the maximum allowable slope and electromagnetic radiation safety range in the channel.

[0163] Constructing a detour model based on the superposition of terrain relief characteristics and electromagnetic safety detour ranges comprehensively considers topographic and electromagnetic safety factors. Terrain relief characteristics reflect the complexity of an area, while the electromagnetic safety detour range defines the feasible area while ensuring electromagnetic radiation safety. By superimposing these two factors, we can identify areas that meet both topographic conditions and electromagnetic safety requirements, thus building a detour model.

[0164] The model includes a maximum allowable slope within the channel and an electromagnetic radiation safety zone. The maximum allowable slope is determined based on transmission line construction requirements and terrain conditions. Slopes exceeding this value may increase the difficulty and cost of transmission line construction and even affect line stability. The electromagnetic radiation safety zone is determined based on electromagnetic radiation safety standards. Within this range, the electromagnetic interference experienced by the transmission line remains within an acceptable range.

[0165] When constructing the model, a Geographic Information System (GIS) combined with mathematical modeling can be used. First, terrain relief characteristics and electromagnetic safety detour range data are imported into the GIS for overlay analysis to determine the boundaries of areas that meet the requirements. Then, based on transmission line construction standards and experience, specific values ​​for the maximum allowable slope and electromagnetic radiation safety range are determined. Finally, a mathematical model is used to integrate this information to construct a detour model that allows for route correction. For example, in a power project in a mountainous area, by overlaying terrain relief characteristics and electromagnetic safety detour ranges, it was found that certain areas, despite significant terrain relief, were within safe electromagnetic radiation levels; whereas other areas, with relatively flat terrain, had higher electromagnetic radiation levels. Through comprehensive analysis, a detour model was determined that met both terrain slope requirements and electromagnetic safety standards.

[0166] Step S434: Generate multiple alternative path trajectories based on the circuitous channel model, and calculate the deviation angle of each trajectory from the original path, the cumulative slope change, and the average electromagnetic radiation value of the passed area.

[0167] Generating multiple alternative transmission line paths based on the circuitous channel model utilizes the range and conditions determined by the circuitous channel model and uses a path planning algorithm to generate multiple different transmission line paths. These paths are all within the range allowed by the circuitous channel model and meet the requirements of the maximum allowable slope and electromagnetic radiation safety range.

[0168] Calculating the deviation angle of each trajectory from the original path measures the degree of deviation of the alternative path from the original transmission line path. A larger deviation angle indicates a greater divergence between the alternative path and the original path. The cumulative slope change reflects the gradient of the alternative path over its entire length. A smaller cumulative slope change indicates a relatively flatter path, potentially reducing construction difficulty and cost. The mean electromagnetic radiation value of the area passed through refers to the average electromagnetic radiation intensity in the area traversed by the alternative path. A lower value indicates less electromagnetic interference on the path.

[0169] In practice, path planning algorithms, such as the Dijkstra or A* algorithms, can be used to generate multiple alternative path trajectories within a circuitous channel model. For each alternative path, the spatial relationship between the path and the original path is obtained through a geographic information system (GIS) to calculate the deviation angle. The cumulative slope change is calculated by analyzing the slope information of each point on the path. The mean electromagnetic radiation value of the traversed area is calculated by calling the data for the corresponding area in the electromagnetic intensity subvector. For example, in a city's power project, multiple alternative path trajectories were generated for high-risk path nodes. Calculations revealed that while some paths deviated significantly from the original path, the cumulative slope change was small and the mean electromagnetic radiation value of the traversed area was low. Other paths, on the other hand, deviated slightly but had a large cumulative slope change and a high mean electromagnetic radiation value.

[0170] Step S435: Select the alternative trajectory with a deviation angle less than a preset tolerance, the smallest cumulative slope change, and the lowest electromagnetic radiation mean as the avoidance path correction trajectory, and connect the endpoint of the correction trajectory with the unadjusted initial coordinate point set in a curvature continuous manner.

[0171] The alternative trajectory with a deviation angle less than a preset tolerance, the smallest cumulative slope change, and the lowest mean electromagnetic radiation value is selected as the avoidance path correction trajectory. This involves screening multiple alternative paths to find the optimal path correction solution. The preset tolerance is a permissible deviation angle range determined based on the design requirements and actual conditions of the transmission line. If the deviation angle of the alternative path exceeds this tolerance, it may have a significant impact on the overall layout and operation of the transmission line. Minimizing the cumulative slope change ensures a relatively flat path, reducing construction costs and maintenance difficulties; minimizing the mean electromagnetic radiation value reduces the impact of electromagnetic interference on the transmission line.

[0172] Connecting the endpoints of the corrected trajectory to the unadjusted initial coordinate point set through curvature continuity ensures the continuity and stability of the transmission line. This curvature continuity prevents sudden changes in the line, reduces stress concentration, and improves the safety and reliability of the transmission line.

[0173] In the specific implementation, the alternative path trajectories are first screened according to the preset tolerance, and the paths with deviation angles exceeding the tolerance are excluded. Then, the cumulative slope change and the mean electromagnetic radiation of the screened paths are calculated, and the path with the smallest cumulative slope change and the lowest mean electromagnetic radiation is selected as the avoidance path correction trajectory. Finally, the curve fitting method is used to connect the endpoints of the correction trajectory with the unadjusted initial coordinate point set in a curvature-continuous manner. For example, in a power project in a mountainous area, through screening and comparison, an alternative trajectory with a deviation angle within the preset tolerance range, the smallest cumulative slope change, and the lowest mean electromagnetic radiation was selected as the avoidance path correction trajectory, and it was smoothly connected to the unadjusted initial coordinate point set in a curvature-continuous manner, ensuring the smoothness and stability of the transmission line.

[0174] Step S436: Encapsulate the terrain constraint parameters and electromagnetic safety parameters involved in the avoidance path correction trajectory into path optimization rules and embed them into the dynamic adjustment logic of the transmission line path planning results to ensure that local correction instructions are generated based on the real-time terrain data reuse rules when encountering unsurveyed obstacles during the construction phase.

[0175] Encapsulating the terrain constraint parameters and electromagnetic safety parameters involved in the avoidance path correction trajectory into path optimization rules organizes and encapsulates the terrain factors (such as the maximum allowable slope) and electromagnetic safety factors (such as the electromagnetic radiation safety range) considered in the generation of the avoidance path correction trajectory into a set of rules. These rules can reflect the optimal conditions for transmission line path planning under predefined terrain and electromagnetic environments.

[0176] Embedding the dynamic adjustment logic of transmission line routing results incorporates encapsulated path optimization rules into the dynamic adjustment mechanism of transmission line routing results. During the construction phase, unforeseen obstacles may be encountered, such as unexpected geological faults or newly discovered electromagnetic interference sources. In these cases, these path optimization rules can be reused based on real-time terrain data to make local corrections to the transmission line route.

[0177] In specific implementations, terrain constraint parameters and electromagnetic safety parameters can be encapsulated into a rule object or class using a programming language. This rule object can then be called and applied within the dynamic adjustment logic for transmission line routing. During the construction phase, after acquiring real-time terrain data, the system automatically determines whether the transmission line path needs to be corrected based on this data and path optimization rules, and generates corresponding local correction instructions. For example, during the construction of a large-scale power project, when encountering an unsurveyed steep slope, the system determines whether the area exceeds the maximum allowable slope based on the real-time terrain data and encapsulated path optimization rules. If so, the system automatically generates local correction instructions to adjust the transmission line path to avoid the steep slope while ensuring that the new path still meets the electromagnetic radiation safety zone requirements.

[0178] Step S440: Generate a set of candidate substation locations based on the site selection coordinate parameters in the power engineering optimization parameter set. Combined with the coverage radius weight in the layout topology subvector and the spatial attenuation characteristics of the electromagnetic intensity subvector, calculate the coverage efficiency of each candidate location for the surrounding lines and the electromagnetic radiation suppression demand score.

[0179] Generating a set of candidate substation locations based on the siting coordinate parameters in the power engineering optimization parameter set involves identifying multiple possible substation locations based on the siting coordinate parameters to form a set of candidate substation locations. Combining the coverage radius weights in the layout topology subvector and the spatial attenuation characteristics of the electromagnetic intensity subvector, each candidate location's coverage efficiency for surrounding lines and its electromagnetic radiation suppression requirement score are calculated. This evaluates the pros and cons of each candidate location, taking into account the substation's coverage range and electromagnetic radiation impact.

[0180] Coverage efficiency refers to the degree to which a substation covers surrounding transmission lines. A higher coverage efficiency indicates that the substation is better able to supply power to surrounding lines. The electromagnetic radiation suppression need score assesses the need for electromagnetic radiation suppression at a candidate location based on the spatial attenuation characteristics of the electromagnetic intensity subvector. A higher score indicates that the location requires stronger electromagnetic radiation suppression measures.

[0181] In specific implementations, tools such as geographic information systems (GIS) can be used to calculate the coverage efficiency of each candidate location for surrounding lines and the electromagnetic radiation suppression need score. The candidate substation location set, the coverage radius weights in the layout topology subvector, and the spatial attenuation characteristics of the electromagnetic intensity subvector are imported into the GIS. Through spatial analysis and calculation, the coverage efficiency and electromagnetic radiation suppression need score of each candidate location are obtained. For example, in a city's power engineering planning, a candidate substation location set is generated based on site selection coordinate parameters. Then, combined with the information from the layout topology subvector and the electromagnetic intensity subvector, the coverage efficiency and electromagnetic radiation suppression need score of each candidate location are calculated.

[0182] Step S450: Select the substation site coordinates according to the comprehensive weight value of coverage efficiency and suppression demand score, and generate shielding equipment installation density and orientation parameters matching the site coordinates based on the interference suppression parameters in the power engineering optimization parameter set to form an electromagnetic interference suppression strategy.

[0183] Selecting the substation site coordinates based on the comprehensive weight value of coverage efficiency and suppression demand score means comprehensively considering coverage efficiency and electromagnetic radiation suppression demand score, assigning corresponding weights to each indicator, calculating the comprehensive weight value, and then selecting the candidate location with the highest comprehensive weight value as the substation site coordinates.

[0184] Generating shielding equipment installation density and orientation parameters that match the site coordinates based on the interference suppression parameters in the power engineering optimization parameter set refers to determining the installation density and orientation of shielding equipment based on the interference suppression parameters and the selected substation site coordinates to effectively suppress electromagnetic radiation. Forming an electromagnetic interference suppression strategy involves integrating information such as shielding equipment installation density and orientation parameters into a complete electromagnetic interference suppression strategy.

[0185] In practical implementation, an algorithm can be developed to select substation site coordinates based on the combined weighting of coverage efficiency and suppression need scores. Then, based on the interference suppression parameters and site coordinates, electromagnetic simulation software and other tools can be used to calculate the installation density and orientation parameters of shielding equipment. For example, in power project planning for an industrial park, substation site coordinates can be selected based on the combined weighting of coverage efficiency and suppression need scores. Then, based on the interference suppression parameters, shielding equipment installation density and orientation parameters matching the site coordinates are generated, forming an electromagnetic interference suppression strategy.

[0186] Step S460: Perform spatial topological association on the transmission line path planning results, substation site selection coordinates, and electromagnetic interference suppression strategies to generate a power facility deployment plan that includes construction coordinate mapping rules and electromagnetic protection joint control logic. The joint control logic is used to dynamically adjust the shielding equipment operating parameters according to real-time electromagnetic data during the substation operation phase.

[0187] Spatial topological association of transmission line routing results, substation site coordinates, and electromagnetic interference suppression strategies involves spatially linking the transmission line paths, substation locations, and electromagnetic interference suppression measures to ensure coordination and consistency. Generating a power facility deployment plan that includes construction coordinate mapping rules and electromagnetic protection joint control logic integrates the results of this spatial topological association to form a complete power facility deployment plan that includes these construction coordinate mapping rules and electromagnetic protection joint control logic.

[0188] Construction coordinate mapping rules convert transmission line routing and substation site coordinates into actual construction coordinates to guide construction personnel. Electromagnetic protection control logic dynamically adjusts shielding equipment parameters based on real-time electromagnetic data during substation operation to ensure electromagnetic radiation intensity consistently meets safety standards.

[0189] In practical implementation, tools such as geographic information systems (GIS) can be used for spatial topological association. Transmission line routing results, substation site coordinates, and electromagnetic interference suppression strategies can be imported into the GIS. Through spatial analysis and data processing, construction coordinate mapping rules and electromagnetic protection joint control logic can be generated. For example, in the planning of a large-scale power project, transmission line routing results, substation site coordinates, and electromagnetic interference suppression strategies can be spatially topologically associated to generate a power facility deployment plan that includes construction coordinate mapping rules and electromagnetic protection joint control logic.

[0190] As an implementation manner, the method provided in the embodiment of the present invention further includes a step of updating the optimization decision model, which may specifically include the following steps:

[0191] Step S500: collecting in real time the operation monitoring data set of the power facilities deployed in the target area, the operation monitoring data set including the transmission line load rate fluctuation curve, substation equipment operation efficiency index and electromagnetic radiation intensity real-time monitoring value.

[0192] Real-time collection of operational monitoring data from deployed power facilities in the target area is designed to provide timely insights into the status and performance of these facilities during actual operation. The transmission line load factor fluctuation curve reflects the load conditions of the transmission line over different time periods. By analyzing this curve, we can understand the load variation patterns of the transmission line and determine whether there are abnormal conditions such as overload or underload. Substation equipment operating efficiency indicators, such as transformer efficiency and circuit breaker actuation times, reflect the operating status and efficiency of substation equipment. These indicators can reflect the health and operational quality of substation equipment. Real-time monitoring of electromagnetic radiation intensity provides real-time insights into changes in the electromagnetic environment within the target area, ensuring that electromagnetic radiation intensity remains within a safe range.

[0193] In practice, load sensors can be installed on transmission lines to collect current and voltage data in real time, and load factor fluctuation curves can be calculated. Various monitoring devices, such as power meters and thermometers, can be installed in substations to collect operating parameters of substation equipment and calculate operating efficiency indicators. Multiple electromagnetic monitoring points can be set up within the target area, and professional electromagnetic monitoring equipment can be used to collect electromagnetic radiation intensity data in real time. For example, in a city's power grid, monitoring equipment distributed across various transmission lines and substations can collect operational monitoring data in real time, providing data support for subsequent model updates and optimization.

[0194] Step S600: Input the operation monitoring data set into the pre-trained feature extraction network to generate a real-time multi-dimensional feature vector, and call the optimization decision model to process the real-time multi-dimensional feature vector to generate a current optimization parameter prediction set.

[0195] The operational monitoring data set is fed into a pre-trained feature extraction network, which extracts and maps features from the data. This network, having previously learned the relationships between topographic, electromagnetic, and equipment layout data, is able to extract representative features from the operational monitoring data set and generate a real-time multidimensional feature vector. This vector incorporates characteristic information about transmission line load, substation equipment operating status, and electromagnetic radiation.

[0196] The optimization decision model is invoked to process the real-time multidimensional feature vector. Based on the input real-time multidimensional feature vector, the optimization decision model combines its internal parameters and algorithms to generate a set of current optimization parameter predictions. This set includes the predicted values ​​of optimization parameters for transmission line routing, substation site selection, and electromagnetic interference suppression under the current circumstances.

[0197] In specific implementations, the operational monitoring data set is formatted and preprocessed according to the input requirements of the pre-trained feature extraction network before being input into the network. After calculation and processing, the network outputs a real-time multidimensional feature vector. This vector is then input into the optimization decision model, which processes it through internal modules such as the parameter adjustment network and the verification feedback network to generate a set of current optimized parameter predictions. For example, in an industrial park power project, the real-time collected operational monitoring data set is input into the pre-trained feature extraction network to generate a real-time multidimensional feature vector. This vector is then input into the optimization decision model to obtain the current set of optimized parameter predictions, providing a basis for real-time optimization of power facilities.

[0198] Step S700: Compare the current optimization parameter prediction set with the power engineering optimization parameter set to generate a model parameter deviation index, where the difference comparison includes the path planning parameter offset, the site coordinate distance difference and the interference suppression effect attenuation rate.

[0199] Comparing the current set of predicted optimization parameters with the set of optimized power engineering parameters is intended to assess the degree of discrepancy between the actual operation of power facilities and the initially planned scheme. The path planning parameter offset reflects the degree of deviation between the currently predicted transmission line path and the initially planned path, and is calculated by comparing information such as the coordinates and direction of the two. The site selection coordinate distance difference refers to the distance between the currently predicted substation site coordinates and the initially planned site coordinates. The larger the distance difference, the greater the discrepancy between the actual substation site and the planned site. The interference suppression effect attenuation rate reflects the attenuation between the current electromagnetic interference suppression effect and the initially planned interference suppression effect, and is calculated by comparing the electromagnetic radiation intensity control levels of the two.

[0200] Generating a model parameter deviation index comprehensively considers factors such as path planning parameter deviation, site coordinate distance difference, and interference suppression effect attenuation rate to form an indicator that reflects the degree of model parameter deviation. This indicator can help determine whether the optimization decision model needs to be updated and adjusted.

[0201] In specific implementations, an algorithm can be written to perform an element-by-element comparison between the current set of predicted optimization parameters and the set of optimized power engineering parameters. For path planning parameters, the deviation between their coordinates and orientation is calculated to obtain the path planning parameter offset. For site selection coordinates, the Euclidean distance between the two is calculated to obtain the site selection coordinate distance difference. For interference suppression, the electromagnetic radiation intensity control effect at different time points is compared to calculate the interference suppression effect attenuation rate. Finally, based on the weights of these indicators, the model parameter deviation index is calculated. For example, in a city's power grid, by comparing the current set of predicted optimization parameters with the set of optimized power engineering parameters, it was found that the transmission line path planning parameter offset was large, the site selection coordinate distance difference also increased, and the interference suppression effect attenuation rate reached a preset level. The comprehensively calculated model parameter deviation index exceeded the preset threshold, indicating that the optimization decision model needs to be updated.

[0202] Step S800: If the model parameter deviation index exceeds the dynamic update threshold, the operation monitoring data set and the corresponding real-time multi-dimensional feature vector are used as incremental training samples to perform local weight correction on the parameter adjustment network in the optimization decision model to generate an updated parameter adjustment network.

[0203] If the model parameter deviation index exceeds the dynamic update threshold, it indicates that the actual operation of the power facility is significantly different from the original planning scheme. The original optimization decision model may no longer be applicable and needs to be updated. The operation monitoring data set and the corresponding real-time multidimensional feature vector are used as incremental training samples because this data reflects the current actual operation status of the power facility and can provide new information for model updates.

[0204] Local weight correction of the parameter adjustment network in the optimization decision model involves adjusting some of the weights of the parameter adjustment network based on incremental training samples without changing the overall model structure. This allows the model to better adapt to the actual operation of power facilities and improves the model's prediction accuracy.

[0205] In its implementation, the first step is to determine whether the model parameter deviation exceeds the dynamic update threshold. If so, the operational monitoring data set and the real-time multidimensional feature vector are combined into an incremental training sample set. The parameter adjustment network is then trained using this incremental training sample set, and some of the network weights are updated using optimization algorithms such as gradient descent. For example, in a large-scale power project, when the model parameter deviation exceeds the dynamic update threshold, the recently collected operational monitoring data set and the corresponding real-time multidimensional feature vector are used as incremental training samples to perform local weight corrections on the parameter adjustment network. After multiple iterations of training, an updated parameter adjustment network is generated.

[0206] Step S900: reprocessing the multi-dimensional survey feature vector based on the updated parameter adjustment network to generate a revised power engineering optimization parameter set, and adjusting the transmission line path planning results or substation site selection coordinates in the power facility deployment plan according to the revised parameter set.

[0207] The multidimensional survey feature vector is reprocessed based on the updated parameter adjustment network. This updated parameter adjustment network has been modified locally using incremental training samples to better adapt to the actual operation of power facilities. The multidimensional survey feature vector is fed into the updated parameter adjustment network, which performs a nonlinear transformation on it to generate a revised set of optimized power engineering parameters.

[0208] Adjusting the transmission line routing results or substation site coordinates in the power facility deployment plan based on the revised parameter set involves applying the revised parameters to the actual power facility deployment plan. If the routing parameters change, the transmission line routing needs to be adjusted; if the site coordinate parameters change, the substation site needs to be re-determined.

[0209] In practice, the multidimensional survey feature vector is fed into an updated parameter adjustment network. After calculation and processing within the network, a revised set of optimized power project parameters is obtained. Based on the path planning parameters and site coordinate parameters contained in this set, tools such as Geographic Information Systems (GIS) are used to adjust the power facility deployment plan. For example, in one city's power project, the multidimensional survey feature vector was reprocessed based on the updated parameter adjustment network to obtain a revised set of optimized power project parameters. If changes in the path planning parameters were detected, the transmission line route was adjusted using GIS tools to better reflect current conditions.

[0210] Step S1000: The adjusted deployment plan is logically bound to the operation monitoring data set to generate an update instruction set. The update instruction set is used to automatically trigger the weight correction process of the optimization decision model according to the real-time monitoring value of the electromagnetic radiation intensity in subsequent real-time monitoring.

[0211] Binding the adjusted deployment plan to the operational monitoring data set through joint control logic involves associating the adjusted deployment plan information, such as transmission line routing results, substation site coordinates, and electromagnetic interference suppression strategies, with the real-time operational monitoring data set, establishing a dynamic control logic. This binding allows the deployment plan to be adjusted promptly based on changes in operational monitoring data.

[0212] Generating an update instruction set involves generating a series of instructions based on the joint control logic. These instructions are used to automatically trigger the weight correction process of the optimization decision model based on the real-time monitoring values ​​of electromagnetic radiation intensity during subsequent real-time monitoring. If the real-time monitoring values ​​of electromagnetic radiation intensity show an abnormality, the update instruction set automatically triggers the weight correction process of the optimization decision model, updating and adjusting the model to ensure the safe and stable operation of the power facilities.

[0213] During specific implementation, the joint control logic code can be written in a programming language to associate the adjusted deployment plan with the operational monitoring data set. An update instruction set is generated based on the joint control logic and stored in the system. During the subsequent real-time monitoring process, the system will monitor the real-time monitoring value of the electromagnetic radiation intensity in real time. When the value exceeds the preset safety threshold, the system will automatically execute the update instruction set and trigger the weight correction process of the optimization decision model. For example, in a power project near a substation, the adjusted deployment plan is bound to the operational monitoring data set through joint control logic to generate an update instruction set. When the real-time monitoring shows that the electromagnetic radiation intensity exceeds the safety threshold, the system automatically triggers the weight correction process of the optimization decision model, updates the model, adjusts the electromagnetic interference suppression strategy, and ensures that the electromagnetic radiation intensity returns to a safe range.

[0214] As an embodiment, after generating the power facility deployment plan for the target area according to the power engineering optimization parameter set in step S400, the method further includes the step of dynamic path adjustment during the construction phase:

[0215] Step S1100: collecting terrain scanning data of the construction equipment in the target area in real time. The terrain scanning data includes real-time elevation change values ​​on the construction machinery's travel path and geological rock stratum fissure detection results.

[0216] Real-time terrain scanning data collected by construction equipment within the target area is used to monitor changes in the target area's terrain during construction. Real-time elevation changes along the construction machinery's path reflect the undulations of the terrain. By monitoring these values, it is possible to detect unexpected terrain changes during construction, such as sudden steep slopes or low-lying areas. Geological rock fracture detection results can help determine the geological stability of the construction area. If fractures are detected, adjustments to the construction path may be necessary to avoid potential geological hazards.

[0217] In practice, construction equipment can be equipped with terrain scanning devices, such as laser scanners and radar, to collect real-time elevation data along the construction machinery's path. Simultaneously, geological exploration equipment, such as geological radar and borehole sampling equipment, can be used to inspect the geology and rock formations in the construction area and detect cracks in the strata. For example, during the construction of a power project in a mountainous area, laser scanners mounted on construction machinery can collect real-time elevation changes along the path, while geological radar can be used to detect cracks in the strata. This provides accurate terrain data for dynamic path adjustments during the construction phase.

[0218] Step S1200: Input the terrain scanning data into the pre-trained feature extraction network to generate a real-time terrain feature vector for the construction area, and compare the difference with the terrain parameter sub-vector in the deployment plan to identify the offset area between the construction path and the original terrain features.

[0219] The terrain scan data is fed into a pre-trained feature extraction network, which extracts and maps features from the scan data to generate a real-time terrain feature vector for the construction area. This vector contains information about the current terrain characteristics of the construction area, such as terrain relief and geological stability.

[0220] Difference comparison with the terrain parameter subvectors in the deployment plan involves comparing the real-time terrain feature vectors of the construction area with the terrain parameter subvectors used when the deployment plan was originally generated, identifying any discrepancies between the two. This difference comparison can identify areas where the construction path deviates from the original terrain features, indicating areas where the terrain has changed during construction.

[0221] In specific implementation, the terrain scanning data is formatted and preprocessed according to the input requirements of the pre-trained feature extraction network, and then input into the network. After calculation and processing, the network outputs the real-time terrain feature vector of the construction area. A vector comparison algorithm is used to compare the real-time terrain feature vector of the construction area with the terrain parameter sub-vector in the deployment plan element by element to find areas with large differences and mark them as offset areas between the construction path and the original terrain features. For example, in the construction of a power project in a city, the terrain scanning data collected in real time is input into the pre-trained feature extraction network to generate the real-time terrain feature vector of the construction area. By comparing the difference with the terrain parameter sub-vector in the deployment plan, it is found that the terrain undulation of a certain construction section is significantly different from the original plan, and the section is marked as an offset area.

[0222] Step S1300: Based on the position coordinates of the offset area, the path planning parameters in the optimization decision model are called to generate a local path correction instruction, which includes an alternative path coordinate set for bypassing the crack area and a slope adaptive adjustment angle.

[0223] Based on the position coordinates of the offset area, the path planning parameters in the optimization decision model are called to generate local path correction instructions. According to the position information of the offset area between the identified construction path and the original terrain features, the corresponding path planning parameters are obtained from the optimization decision model to generate local path correction instructions for the offset area.

[0224] The correction instructions include the coordinates of an alternative route to bypass the fractured area and a slope adaptation adjustment angle. The alternative route coordinates for bypassing the fractured area refer to the coordinates of the replanned transmission line route to avoid geological fractures in the offset area. The slope adaptation adjustment angle adjusts the slope of the transmission line based on the terrain gradient in the offset area to ensure safe and stable operation of the transmission line under the new terrain conditions.

[0225] In the specific implementation, the corresponding path planning parameters are searched in the optimization decision model according to the position coordinates of the offset area. Using the path planning algorithm, combined with the terrain scanning data and the geological rock fracture detection results, an alternative path coordinate set for bypassing the fracture area is generated. At the same time, the slope adaptability adjustment angle is calculated according to the terrain slope change in the offset area. The alternative path coordinate set and the slope adaptability adjustment angle are combined into a local path correction instruction. For example, in the construction of a power project in a mountainous area, when a geological rock fracture is identified in a certain area, the path planning parameters in the optimization decision model are called according to the position coordinates of the area to generate an alternative path coordinate set for bypassing the fracture area, and the slope adaptability adjustment angle is calculated to form a local path correction instruction.

[0226] Step S1400: topological connection verification is performed on the alternative path coordinate set and the transmission line path planning result in the deployment plan to ensure the curvature continuity and electromagnetic radiation superposition value consistency of the corrected path endpoints and the unadjusted path segments.

[0227] Topological connectivity verification is performed between the alternative path coordinate set and the transmission line path planning results in the deployment plan to ensure the coherence and consistency between the revised transmission line path and the original planned path. Topological connectivity verification focuses on the curvature continuity and electromagnetic radiation superposition consistency between the revised path endpoints and the unadjusted path segments.

[0228] Curvature continuity means that the curvature change at the connection point between the modified path endpoint and the unmodified path segment should be smooth, avoiding sudden turns or bends to ensure the stability and safety of the transmission line. Electromagnetic radiation superposition value consistency means that after the modified path and the unmodified path segment are connected, their electromagnetic radiation superposition value must meet the original planning requirements to ensure the stability of the electromagnetic environment.

[0229] In specific implementation, a geographic information system (GIS) and electromagnetic simulation software are used to verify the topological connection between the alternative path coordinate set and the transmission line path planning results in the deployment plan. GIS is used to analyze the spatial relationship between the modified path endpoints and the unadjusted path segments, calculate the curvature change, and ensure curvature continuity. Electromagnetic simulation software is used to simulate the electromagnetic radiation superposition after the modified path is connected with the unadjusted path segment to verify the consistency of the electromagnetic radiation superposition value. For example, during the construction of a power project in a city, the generated alternative path coordinate set and the original transmission line path planning results were topologically verified. GIS analysis found that the curvature changes at the path connection points were smooth. Electromagnetic simulation software was used to simulate and verify that the electromagnetic radiation superposition value met the requirements, indicating that the modified path meets the topological connection requirements.

[0230] Step S1500: Update the construction coordinate mapping rules in the power facility deployment plan based on the verification results, and synchronize the updated rules to the navigation control system of the construction equipment to drive the construction machinery to perform high-precision paving operations according to the corrected path.

[0231] Updating the construction coordinate mapping rules in the power facility deployment plan based on the verification results means that if the topology connection verification passes, the corrected path coordinate information is updated to the construction coordinate mapping rules in the power facility deployment plan. The construction coordinate mapping rules are used to convert the planned transmission line path into actual construction coordinate information to guide construction machinery.

[0232] Synchronizing the updated rules with the construction equipment's navigation control system involves transmitting the updated construction coordinate mapping rules to the equipment's navigation control system, enabling the equipment to obtain the latest construction path information. Driving the construction machinery to perform high-precision laying operations along the revised path involves the equipment automatically adjusting its route based on the updated rules in the navigation control system, laying the transmission line along the revised path, ensuring high precision and accuracy.

[0233] During implementation, the verified alternative path coordinate set is updated to the construction coordinate mapping rules to generate an updated rule file. Wireless communication technology is then used to transmit the updated rule file to the navigation control system of the construction equipment. Upon receiving the updated rules, the navigation control system of the construction equipment automatically adjusts the navigation route, driving the construction machinery to lay the transmission line along the corrected path. For example, in the construction of a large-scale power project, after topological connectivity verification, the corrected path coordinate information is updated to the construction coordinate mapping rules. The updated rules are then synchronized to the navigation control system of the construction equipment via wireless communication, allowing the construction machinery to accurately lay the transmission line along the corrected path, improving construction efficiency and quality.

[0234] As an implementation method, the method provided in the embodiment of the present invention further includes the step of optimizing electromagnetic joint control during the operation phase, specifically including:

[0235] Step S1600: After the power facilities in the target area are put into operation, electromagnetic radiation monitoring data around the substation and load fluctuation data of the transmission line are continuously collected to generate a real-time monitoring data set during the operation phase.

[0236] After the power facilities in the target area are put into operation, continuous collection of electromagnetic radiation monitoring data around substations and transmission line load fluctuation data is conducted to provide real-time insights into the electromagnetic environment and load conditions during the operation of the power facilities. This electromagnetic radiation monitoring data around substations can reflect changes in electromagnetic radiation intensity generated during substation operation. By monitoring this data, abnormal electromagnetic radiation can be detected promptly and appropriate measures can be taken to control it. Transmission line load fluctuation data reflects the load variations of transmission lines over different time periods. Understanding load fluctuation patterns can help rationally allocate power resources and improve the operational efficiency of transmission lines.

[0237] Generating a real-time monitoring data set during the operation phase involves integrating continuously collected electromagnetic radiation monitoring data from the substation perimeter and transmission line load fluctuation data to form a data set containing a variety of operational information. This data set provides data support for subsequent electromagnetic coordinated control optimization.

[0238] In practice, multiple electromagnetic monitoring points can be set up around substations, using specialized electromagnetic monitoring equipment to collect real-time electromagnetic radiation intensity data. Load sensors can be installed on transmission lines to collect real-time current and voltage data, calculating load fluctuation data. The collected electromagnetic radiation monitoring data and transmission line load fluctuation data are collated and stored to generate a real-time monitoring dataset for the operational phase. For example, in a city's power grid, electromagnetic monitoring points distributed around substations and load sensors on transmission lines continuously collect data to generate a real-time monitoring dataset for the operational phase. This provides comprehensive and accurate data for optimizing electromagnetic coordinated control of power facilities during the operational phase.

[0239] Step S1700: Input the real-time monitoring data set into the pre-trained feature extraction network, extract the electromagnetic intensity sub-vector and load distribution sub-vector during the operation phase, and perform dynamic matching analysis with the electromagnetic interference suppression strategy in the deployment plan.

[0240] The real-time monitoring dataset is fed into a pre-trained feature extraction network, which extracts and maps features from the dataset. The network extracts the operational phase electromagnetic intensity subvector and the load distribution subvector from the dataset. The operational phase electromagnetic intensity subvector contains characteristic information about the electromagnetic radiation intensity around the substation, while the load distribution subvector reflects the distribution of load on the transmission lines.

[0241] Dynamic matching analysis with the EMI suppression strategy in the deployment plan compares and analyzes the extracted operational-phase electromagnetic intensity subvectors and load distribution subvectors with the originally formulated EMI suppression strategy. This dynamic matching analysis determines whether the current electromagnetic environment and load conditions meet the requirements of the EMI suppression strategy and whether the strategy needs to be adjusted.

[0242] In implementation, the real-time monitoring dataset is formatted and preprocessed according to the input requirements of a pre-trained feature extraction network before being fed into the network. After calculation and processing, the network outputs a sub-vector representing the electromagnetic intensity during the operational phase and a sub-vector representing the load distribution. A matching algorithm is then used to compare and analyze these sub-vectors with the electromagnetic interference suppression strategy in the deployment plan to identify discrepancies and potential issues. For example, in an industrial park power project, the real-time monitoring dataset was fed into a pre-trained feature extraction network to extract the sub-vector representing the electromagnetic intensity during the operational phase and the sub-vector representing the load distribution. Dynamic matching analysis with the electromagnetic interference suppression strategy in the deployment plan revealed that the electromagnetic radiation intensity during a certain period exceeded the specified range, necessitating adjustment to the strategy.

[0243] Step S1800: Identify the frequency band peak distribution area that exceeds the preset safety range in the electromagnetic intensity sub-vector, and generate incremental shielding equipment deployment instructions based on the interference suppression parameters in the optimization decision model. The instructions include the installation coordinates of the newly added shielding device and the operating frequency band adjustment parameters.

[0244] Identifying the distribution of frequency band peaks in electromagnetic intensity subvectors that exceed the preset safety range is accomplished by analyzing the electromagnetic intensity subvectors during operation to identify the frequency bands and corresponding distribution areas where electromagnetic radiation intensity exceeds the preset safety range. The preset safety range is a range of electromagnetic radiation intensity determined based on electromagnetic radiation safety standards and the operational requirements of power facilities. Exceeding this range may pose a hazard to personnel and equipment.

[0245] Incremental shielding device deployment instructions are generated based on the interference suppression parameters in the optimization decision model. This is done by combining the interference suppression parameters in the optimization decision model with information about the peak distribution areas of frequency bands that exceed the preset safety interval. The instructions include the installation coordinates of the new shielding devices and operating frequency adjustment parameters. The installation coordinates of the new shielding devices refer to the specific locations where the shielding devices need to be installed to suppress electromagnetic radiation outside the safety interval. The operating frequency adjustment parameters adjust the operating frequency of the shielding devices based on the frequency bands outside the safety interval to more effectively suppress electromagnetic radiation.

[0246] In specific implementations, a data analysis algorithm is used to process the electromagnetic intensity subvectors and identify frequency band peak distribution areas that exceed the preset safety interval. Based on the interference suppression parameters in the optimization decision model and the location information of the area, the installation coordinates of the new shielding device and the operating frequency band adjustment parameters are calculated to generate incremental shielding equipment deployment instructions. For example, in a power project near a substation, through analysis of the electromagnetic intensity subvectors during the operation phase, it was found that the electromagnetic radiation intensity of a certain frequency band exceeded the preset safety interval and was mainly distributed in a certain area of ​​the substation. Based on the interference suppression parameters in the optimization decision model, an incremental shielding equipment deployment instruction is generated to determine the installation of a new shielding device in this area and adjust its operating frequency band to effectively suppress electromagnetic radiation.

[0247] Step S1900: According to the line load rate fluctuation characteristics in the load distribution subvector, the substation coverage radius weight in the deployment plan is adjusted, and the topological connection priority of the surrounding transmission lines is recalculated.

[0248] Adjusting the substation coverage radius weights in the deployment plan based on the fluctuations in the line load factor within the load distribution subvectors involves analyzing the fluctuations in the transmission line load factors within the load distribution subvectors to determine whether the substation coverage needs to be adjusted. If the load factors of certain transmission lines are consistently high, the coverage radius weights of the corresponding substations may need to be increased to ensure that the substations can better serve these lines.

[0249] Recalculating the topological connection priorities of surrounding transmission lines involves adjusting the substation coverage radius weights and then re-determining the connection priorities of surrounding transmission lines based on the new weights and the topological structure of the transmission lines. Transmission lines with higher connection priorities receive higher priority in power distribution and fault handling.

[0250] In the specific implementation, statistical analysis methods are used to analyze the fluctuation characteristics of the line load rate in the load distribution subvector, and the substation coverage radius weight in the deployment plan is adjusted based on the analysis results. Then, using graph theory algorithms and power system analysis methods, combined with the adjusted weights and the topological structure of the transmission lines, the topological connection priority of the surrounding transmission lines is recalculated. For example, in a city's power network, by analyzing the load distribution subvector, it was found that the load rate of the transmission lines in a certain area continued to increase, so the coverage radius weight of the substation in this area was increased. After recalculating the topological connection priority of the surrounding transmission lines, it was determined that the connection priority of some lines needed to be increased to ensure the rational distribution of power and the stable operation of the system.

[0251] Step S2000: Integrate the incremental shielding equipment deployment instructions and the updated topology connection priority into an operation optimization parameter set, synchronize it to the substation control center and line dispatching system, and adjust the shielding equipment working mode and line load distribution strategy in real time to ensure that the electromagnetic radiation intensity and load efficiency continue to meet the constraints of the power engineering optimization parameter set.

[0252] Integrating the incremental shielding device deployment instructions and the updated topology connection priorities into an operational optimization parameter set combines the incremental shielding device deployment instructions with the recalculated transmission line topology connection priorities to form a parameter set containing multiple optimization information. This parameter set integrates optimization strategies for both electromagnetic interference suppression and line load distribution.

[0253] Synchronization with the substation control center and line dispatching system involves transmitting the operational optimization parameter set to the substation control center and line dispatching system, enabling these systems to access the latest optimization information. Real-time adjustment of the shielding device operating mode and line load distribution strategy involves the substation control center adjusting the shielding device operating mode in real time, such as turning the shielding device on or off and adjusting its power, based on the incremental shielding device deployment instructions in the operational optimization parameter set. The line dispatching system adjusts the line load distribution strategy in real time based on the updated topological connection priorities to rationally allocate power resources.

[0254] By adjusting the shielding equipment's operating mode and line load distribution strategy in real time, the intensity of electromagnetic radiation and load efficiency are ensured to continuously comply with the constraints of the power engineering optimization parameter set. This means that during the operation of power facilities, the intensity of electromagnetic radiation is always controlled within a safe range, while the load distribution of transmission lines is reasonable, which can improve the operating efficiency and stability of the power system. For example, in a large-scale power project, the incremental shielding equipment deployment instructions and the updated topology connection priorities are integrated into an operation optimization parameter set and synchronized to the substation control center and line dispatching system. The substation control center adjusts the shielding equipment's operating mode according to the instructions, effectively suppressing electromagnetic radiation; the line dispatching system adjusts the line load distribution strategy according to the updated priority, improving the load efficiency of the power system and ensuring that the intensity of electromagnetic radiation and load efficiency continuously comply with the constraints of the power engineering optimization parameter set.

[0255] Based on the foregoing embodiments, an embodiment of the present invention provides a power engineering survey data processing device. The various units included in the device, and the various modules included in each unit, can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0256] Figure 2 A schematic diagram of the structure of a power engineering survey data processing device provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the power engineering survey data processing device 200 includes:

[0257] Data acquisition module 210 is used to acquire a multi-source survey data set for the target area, the multi-source survey data set including geological and topographic data, electromagnetic interference data, and equipment layout data. The electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of the power facilities in the target area, and the equipment layout data is used to indicate the transmission line topology and substation locations in the target area.

[0258] A feature mapping module 220 is configured to perform joint feature mapping on a multi-source survey data set using a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, wherein the multi-dimensional survey feature vector includes a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector;

[0259] A parameter generation module 230 is configured to input the multi-dimensional survey feature vector into an optimization decision model for iterative parameter adjustment to generate a set of optimized power engineering parameters for the target area, wherein the optimization decision model is trained based on a mapping relationship between historical survey data and verified optimization results;

[0260] The solution generation module 240 is used to generate a power facility deployment solution for the target area based on the power engineering optimization parameter set. The deployment solution includes the transmission line path planning results, substation site selection coordinates and electromagnetic interference suppression strategy.

[0261] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided by the embodiment of the present invention can be used to perform the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present invention, please refer to the description of the method embodiment of the present invention for understanding.

Claims

1. A method for processing power engineering survey data, characterized in that: The method comprises: Acquiring a multi-source survey data set of a target area, the multi-source survey data set including geological and topographic data, electromagnetic interference data, and equipment layout data, wherein the electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of power facilities in the target area, and the equipment layout data is used to indicate the transmission line topology and substation locations in the target area; Performing joint feature mapping on the multi-source survey data set through a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, wherein the multi-dimensional survey feature vector includes a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector; The multidimensional survey feature vector is input into the optimization decision model for iterative parameter adjustment to generate the power engineering optimization parameter set of the target area, wherein the optimization decision model is trained based on the mapping relationship between historical survey data and verification optimization results; specifically, the optimization decision model includes a parameter adjustment network and a verification feedback network, and the multidimensional survey feature vector is nonlinearly transformed by the parameter adjustment network to generate an initial optimization parameter set, wherein the initial optimization parameter set includes path planning parameters, site selection coordinate parameters and interference suppression parameters; the verification feedback network is called to perform simulated deployment verification on the initial optimization parameter set to generate a parameter adjustment feedback signal, wherein the simulated deployment verification includes calculation of the matching degree between the transmission path and the terrain, analysis of the overlap rate of the substation coverage range and prediction of the electromagnetic interference suppression effect; the weight coefficient of the parameter adjustment network is updated according to the parameter adjustment feedback signal, and the nonlinear transformation and simulated deployment verification are repeatedly performed until the initial optimization parameter set meets the preset deployment constraint conditions; the initial optimization parameter set that meets the deployment constraint conditions is determined as the power engineering optimization parameter set; A power facility deployment plan for the target area is generated based on the power engineering optimization parameter set, wherein the deployment plan includes a transmission line path planning result, a substation site selection coordinate, and an electromagnetic interference suppression strategy.

2. The method according to claim 1, characterized in that The performing joint feature mapping on the multi-source survey data set by a pre-trained feature extraction network to generate a multi-dimensional survey feature vector includes: Performing elevation gradient analysis on the geological and topographic data to extract terrain relief characteristics and geological stability characteristics, and fusing the terrain relief characteristics and geological stability characteristics into the terrain parameter sub-vector based on a preset terrain coding structure; Performing spectral decomposition on the electromagnetic interference data to obtain electromagnetic radiation intensity distribution maps in different frequency bands, extracting peak intensity features and spatial attenuation features of each frequency band through sliding convolution kernels, and superimposing the peak intensity features and spatial attenuation features according to frequency bands to generate the electromagnetic intensity subvectors; Performing topological structure analysis on the equipment layout data, identifying connection nodes of the transmission line and coverage radius of the substation, and generating the layout topology subvector based on node connection density and coverage radius weight; The terrain parameter sub-vector, the electromagnetic intensity sub-vector and the layout topology sub-vector are spliced ​​according to a preset dimensional alignment rule to obtain the multi-dimensional survey feature vector.

3. The method according to claim 1, characterized in that The parameter adjustment network includes a fusion structure of a multilayer perceptron and an attention mechanism. The parameter adjustment network performs a nonlinear transformation on the multidimensional survey feature vector to generate an initial optimization parameter set, including: Inputting the terrain parameter subvector into the first hidden layer of the multilayer perceptron for weight distribution to obtain a terrain influence weight coefficient; Performing cross-attention calculation on the electromagnetic intensity sub-vector and the layout topology sub-vector to generate an electromagnetic-layout correlation feature; Performing weighted aggregation on the electromagnetic-layout correlation features based on the terrain influence weight coefficient to generate a comprehensive decision feature; Performing linear mapping on the comprehensive decision features through the output layer of the multilayer perceptron to generate the initial optimization parameter set; The calling of the verification feedback network to perform simulated deployment verification on the initial optimization parameter set to generate a parameter adjustment feedback signal includes: generating a virtual transmission path according to the path planning parameters, and calculating a matching score between the virtual transmission path and the geological stability characteristics in the terrain parameter subvector; Generating a virtual substation coverage area according to the site selection coordinate parameters, and analyzing the overlap rate between the virtual substation coverage area and the coverage range of existing power facilities; Predicting an electromagnetic radiation intensity attenuation curve of the target area based on the interference suppression parameter, and calculating a deviation value between the attenuation curve and a preset electromagnetic safety threshold; The parameter adjustment feedback signal is generated according to the matching score, the overlap rate and the deviation value, wherein the parameter adjustment feedback signal includes a path adjustment direction, a coordinate offset and an interference suppression correction coefficient.

4. The method according to claim 1, wherein The pre-trained feature extraction network is trained by the following steps: Acquire a historical survey dataset, the historical survey dataset including topographic data, electromagnetic data, and equipment layout data for a plurality of historical regions, and a verified optimization parameter set corresponding to each historical region; Performing data enhancement processing on the historical survey data set to generate an expanded training sample set, wherein the data enhancement processing includes random rotation of terrain data, noise injection of electromagnetic data, and perturbation of layout data nodes; Constructing an initial feature extraction network, and inputting the expanded training sample set into the initial feature extraction network to perform feature extraction, thereby generating a prediction optimization parameter set; Calculating the mean square error loss between the predicted optimization parameter set and the verified optimization parameter set, and updating the parameters of the initial feature extraction network based on a gradient descent algorithm until the mean square error loss converges to a preset threshold; The initial feature extraction network after parameter update is determined as the pre-trained feature extraction network.

5. The method according to claim 4, characterized in that The performing data enhancement processing on the historical survey data set to generate an expanded training sample set includes: Performing a random rotation transformation on the terrain data to generate a rotated terrain elevation map, and adding randomly generated geological fracture simulation features to the rotated terrain elevation map; injecting Gaussian white noise into the electromagnetic data to generate a noisy electromagnetic spectrum, and smoothing the noisy electromagnetic spectrum by frequency domain filtering; Randomly disconnecting and reconnecting the transmission line nodes in the equipment layout data to generate an equipment layout diagram after topological structure variation; The rotated terrain elevation map, the noisy electromagnetic spectrum map, and the equipment layout map after topological structure variation are combined into new training samples and added into the expanded training sample set.

6. The method according to claim 1, characterized in that Generating the electric power facility deployment plan for the target area according to the electric power engineering optimization parameter set includes: Extracting an initial transmission line coordinate point set based on the path planning parameters in the power engineering optimization parameter set, and identifying coordinate points in the coordinate point set that overlap with steep slope areas or geological fault zones in combination with the elevation gradient distribution characteristics in the terrain parameter subvector; Performing electromagnetic interference intensity verification on the overlapping coordinate points, calling peak intensity distribution data of the corresponding area in the electromagnetic intensity sub-vector, and screening coordinate points whose peak intensity exceeds a safety threshold as high-risk path nodes; Performing path detour optimization on the high-risk path nodes, generating an avoidance path correction trajectory based on the geological stability characteristics in the terrain parameter subvector, and smoothly connecting the endpoints of the correction trajectory with the unadjusted initial coordinate point set to form the transmission line path planning result; Generate a set of candidate substation locations based on the site selection coordinate parameters in the power engineering optimization parameter set, and calculate the coverage efficiency of each candidate location for surrounding lines and the electromagnetic radiation suppression requirement score based on the coverage radius weight in the layout topology subvector and the spatial attenuation characteristics of the electromagnetic intensity subvector; The substation site coordinates are selected according to the comprehensive weight value of the coverage efficiency and the suppression demand score, and the shielding equipment installation density and orientation parameters matching the site coordinates are generated based on the interference suppression parameters in the power engineering optimization parameter set to form the electromagnetic interference suppression strategy; The transmission line path planning results, substation site selection coordinates and electromagnetic interference suppression strategy are spatially topologically associated to generate a power facility deployment plan that includes construction coordinate mapping rules and electromagnetic protection joint control logic, wherein the joint control logic is used to dynamically adjust the shielding equipment working parameters according to real-time electromagnetic data during the substation operation phase.

7. The method according to claim 6, characterized in that The performing of path detour optimization on the high-risk path node and generating an avoidance path correction trajectory according to the geological stability characteristics in the terrain parameter subvector includes: Extracting the terrain relief characteristics of the area where the high-risk path node is located, generating a contour distribution map centered on the node, and determining the boundary of the detour area based on the direction of change of the contour curvature; Retrieving peak intensity distribution data of a corresponding area in the electromagnetic intensity sub-vector, excluding sub-areas whose electromagnetic radiation intensity exceeds a preset threshold within the detourable area, and generating an electromagnetic safety detour range; Based on the superposition of the terrain undulation characteristics and the electromagnetic safety detour range, a detour channel model that allows path correction is constructed, wherein the model includes the maximum allowable slope and electromagnetic radiation safety range within the channel; Generate multiple alternative path trajectories based on the circuitous channel model, and calculate the deviation angle, cumulative slope change and electromagnetic radiation mean of each trajectory from the original path; The alternative trajectory with the deviation angle less than the preset tolerance, the smallest cumulative slope change, and the lowest mean electromagnetic radiation value is selected as the avoidance path correction trajectory, and the endpoints of the correction trajectory are connected to the unadjusted initial coordinate point set in a curvature continuous manner; The terrain constraint parameters and electromagnetic safety parameters involved in the avoidance path correction trajectory are encapsulated as path optimization rules and embedded in the dynamic adjustment logic of the transmission line path planning results, ensuring that when unsurveyed obstacles are encountered during the construction phase, the rules are reused to generate local correction instructions based on real-time terrain data.

8. A power engineering survey data processing device, characterized in that: The device comprises: a data acquisition module, configured to acquire a multi-source survey data set of a target area, the multi-source survey data set comprising geological and topographic data, electromagnetic interference data, and equipment layout data, wherein the electromagnetic interference data is used to describe the electromagnetic radiation intensity distribution of power facilities in the target area, and the equipment layout data is used to indicate the topology of transmission lines and substation locations in the target area; a feature mapping module, configured to perform joint feature mapping on the multi-source survey data set through a pre-trained feature extraction network to generate a multi-dimensional survey feature vector, wherein the multi-dimensional survey feature vector includes a terrain parameter sub-vector, an electromagnetic intensity sub-vector, and a layout topology sub-vector; a parameter generation module, configured to input the multidimensional survey feature vector into an optimization decision model for iterative parameter adjustment to generate a set of optimized parameters for the power engineering project in the target area, wherein the optimization decision model is trained based on a mapping relationship between historical survey data and verified optimization results; specifically, the optimization decision model includes a parameter adjustment network and a verification feedback network, wherein the multidimensional survey feature vector is subjected to a nonlinear transformation by the parameter adjustment network to generate an initial optimized parameter set, wherein the initial optimized parameter set includes path planning parameters, site selection coordinate parameters, and interference suppression parameters; calling the verification feedback network to perform simulated deployment verification on the initial optimized parameter set to generate a parameter adjustment feedback signal, wherein the simulated deployment verification includes calculation of the matching degree between the transmission path and the terrain, analysis of the overlap rate of the substation coverage range, and prediction of the electromagnetic interference suppression effect; updating the weight coefficient of the parameter adjustment network according to the parameter adjustment feedback signal, and repeatedly performing the nonlinear transformation and simulated deployment verification until the initial optimized parameter set meets the preset deployment constraints; and determining the initial optimized parameter set that meets the deployment constraints as the power engineering optimization parameter set; A solution generation module is used to generate a power facility deployment plan for the target area based on the power engineering optimization parameter set, wherein the deployment plan includes the transmission line path planning results, substation site selection coordinates and electromagnetic interference suppression strategy.

Images