An ant colony-genetic optimization algorithm-based power transmission line path planning method and system

Abstract

The application discloses a kind of transmission line path planning method and system based on ant colony-genetic optimization algorithm, first obtain the multi-source geospatial data of target area, and the multi-source geospatial data obtained are classified and quantitatively processed;Environmental cost evaluation index system is constructed, and the path environment comprehensive cost weight of target area is calculated using combination weighting model;Based on improved ant colony-genetic fusion algorithm, a path planning model is constructed, and the optimal transmission line path of the target area is output from the path planning model;Based on the optimal transmission line path of the target area, the optimal path, environmental cost distribution, convergence curve and engineering index are displayed.The method and system construct the transmission line channel environmental cost evaluation system of subjective and objective fusion, realize the scientific quantification of index weight, improve the path optimization precision, stability and smoothness by improving the ant colony-genetic fusion algorithm, so as to realize the integrated processing of multi-source geographic data and intelligent planning algorithm.

Description

Technical Field

[0001] This invention relates to the field of power grid engineering planning technology, and in particular to a method and system for power transmission line path planning based on ant colony-genetic optimization algorithm. Background Technology

[0002] Current power transmission line corridor planning mainly relies on manual surveys and experience-based judgment. Some systems use traditional ant colony algorithms, genetic algorithms, or simple path search methods for path planning. The above-mentioned existing technical solutions have the following drawbacks: Environmental cost weights are assigned in a single way, which is highly subjective and lacks a quantitative model that integrates subjective and objective factors; traditional ant colony algorithms are prone to premature convergence, have weak global search capabilities, many path detours, and poor smoothness; single algorithms cannot take into account both global optimization and local refinement, resulting in insufficient stability of planning results; and the integration of remote sensing data, GIS spatial analysis, and intelligent algorithms has not been achieved, leading to insufficient engineering implementation.

[0003] In view of this, the present invention is hereby proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for power transmission line path planning based on an ant colony-genetic optimization algorithm, in order to solve the aforementioned technical problems existing in the prior art. The method and system of this invention achieve scientific quantification of indicator weights by constructing a subjective and objective integrated environmental cost evaluation system for power transmission lines. By improving the ant colony-genetic fusion algorithm, the accuracy, stability, and smoothness of path optimization are enhanced, thereby realizing the integrated processing of multi-source geographic data and intelligent planning algorithms.

[0005] The objective of this invention is achieved through the following technical solution: A transmission line path planning method based on ant colony-genetic optimization algorithm, the method comprising: Step 1: Acquire multi-source geospatial data of the target area, and classify and quantify the acquired multi-source geospatial data; Step 2: Construct an environmental cost evaluation index system and use a combined weighting model to calculate the comprehensive environmental cost weight of the target area. Step 3: Construct a path planning model based on the improved ant colony-genetic fusion algorithm. Input the path environment comprehensive cost weight obtained in Step 2 into the constructed path planning model, and output the optimal power transmission line path in the target area from the path planning model. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone update, direction guidance and path smoothing mechanism. Step 4: Based on the optimal transmission line path for the target area obtained in Step 3, display the optimal path, environmental cost distribution, convergence curve, and engineering indicators.

[0006] A power transmission line path planning system based on an ant colony-genetic optimization algorithm, the system comprising: The data acquisition module acquires multi-source geospatial data of the target area and performs classification and quantification processing on the acquired multi-source geospatial data. The cost quantification module constructs an environmental cost evaluation index system and uses a combined weighting model to calculate the comprehensive environmental cost weight of the target area. The intelligent path planning module constructs a path planning model based on an improved ant colony-genetic fusion algorithm. The comprehensive cost weight of the path environment obtained in step 2 is input into the constructed path planning model, and the path planning model outputs the optimal power transmission line path in the target area. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone update, direction guidance and path smoothing mechanism. The results output module displays the optimal path, environmental cost distribution, convergence curve, and engineering indicators based on the obtained optimal transmission line path for the target area.

[0007] Compared with existing technologies, the method and system provided by this invention achieve scientific quantification of indicator weights by constructing a subjective and objective integrated environmental cost evaluation system for power transmission channels. By improving the ant colony-genetic fusion algorithm, the accuracy, stability and smoothness of path optimization are improved, thereby realizing the integrated processing of multi-source geographic data and intelligent planning algorithms. Attached Figure Description

[0008] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of the power transmission line path planning method based on ant colony-genetic optimization algorithm provided in an embodiment of the present invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them, and do not constitute a limitation on the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0011] First, the following explanations are provided for the terms that may be used in this article: The term "and / or" means that either or both can be achieved simultaneously. For example, X and / or Y means that it includes both "X" or "Y" as well as the three cases of "X and Y".

[0012] The terms "comprising," "including," "containing," "having," or other similar semantic descriptions should be interpreted as non-exclusive inclusion. For example, including a technical feature element (such as raw material, component, ingredient, carrier, dosage form, material, size, part, component, mechanism, device, step, process, method, reaction conditions, processing conditions, parameter, algorithm, signal, data, product or article of manufacture, etc.) should be interpreted as including not only the expressly listed technical feature element, but also other technical feature elements that are not expressly listed and are well-known in the art.

[0013] The term "composed of" excludes any technical features not expressly listed. When used in a claim, it closes the claim to exclude all technical features other than those expressly listed, except for associated conventional impurities. If the term appears only in a clause of a claim, it limits the claim to the elements expressly listed in that clause; elements recited in other clauses are not excluded from the overall claim.

[0014] The technical solution provided by this invention will be described in detail below. Contents not described in detail in the embodiments of this invention belong to prior art known to those skilled in the art. For example... Figure 1 The diagram shows a flowchart of a power transmission line path planning method based on an ant colony-genetic optimization algorithm provided in an embodiment of the present invention. The method includes: Step 1: Acquire multi-source geospatial data of the target area, and classify and quantify the acquired multi-source geospatial data; This step specifically involves acquiring satellite remote sensing imagery, digital elevation model (DEM) data, land use data, and road vector data for the target area. The acquired data was radiometrically calibrated, orthorectified, registered, and coordinate unified using Geographic Information System (GIS) tools. Object-oriented classification is used to classify land features, including: buildings, cultivated land, forest land, grassland, water bodies, roads, and railways; By overlaying elevation and slope data, the data is rasterized and reclassified to form a target classification result for cost calculation.

[0015] In practice, the planning area is selected according to the project scope, and satellite imagery and DEM data are downloaded through the GIS platform; the imagery is stitched, classified and graded in the geographic information system software; the avoidance level and cost level are set according to the power transmission line engineering specifications, and an environmental cost base map with uniform resolution is generated.

[0016] Step 2: Construct an environmental cost evaluation index system and use a combined weighting model to calculate the comprehensive environmental cost weight of the target area. Specifically, this step involves constructing a four-layered environmental cost evaluation index system that includes natural factors, social factors, engineering factors, and planning avoidance factors. The subjective weights are calculated using fuzzy hierarchical analysis, the objective weights are calculated using principal component analysis, and the feature importance weights are calculated using the random forest algorithm. The final comprehensive environmental cost weight is obtained by combining the subjective weight, objective weight, and feature importance weight with the minimum difference.

[0017] In practical implementation, the traditional analytic hierarchy process (AHP) can decompose complex cost assessment problems into target, criterion, and indicator layers. However, the construction of its pairwise comparison matrices relies heavily on the absolute judgments of experts, easily introducing subjective cognitive biases. To fully accommodate the ambiguity and hesitation of experts in judging the importance of complex engineering indicators, this embodiment introduces the fuzzy analytic hierarchy process (FAHP). This method constructs fuzzy complementary judgment matrices using a scale of 0.1 to 0.9 and completes the consistency transformation of the matrix based on corresponding mathematical transformation rules, thereby reducing the interference of extreme values ​​assigned by some experts on the final weighting results. The process of calculating subjective weights using the fuzzy analytic hierarchy process (FAHP) is as follows: Suppose that a certain level contains The evaluation indicators are compared pairwise using scaling methods to determine their importance, thereby constructing a... fuzzy complementary matrix of order , is represented as: (1) To ensure the logical consistency of the matrix, the matrix The elements inside satisfy and complementary constraints ; To eliminate potential transitive conflicts in the original scoring, a matrix is ​​extracted. The sum of elements in each row And accordingly, the fuzzy complementary matrix Transformed into a fuzzy consistent matrix with rigorous logic. The conversion formula is: (2) in, Represents the elements in the fuzzy consistency matrix; This represents a column of elements in a fuzzy complementary matrix; Based on fuzzy consistency matrix The row sum normalization method is used to solve for the subjective basis weights of each evaluation index relative to the previous level. , is represented as: (3) This yields the subjective weight vector of the evaluation indicators for this layer. The superscript T is the transpose symbol; To rigorously verify the effectiveness of the above mathematical transformation, a characteristic matrix is ​​constructed. The internal elements of this feature matrix Defined as: (4) in , These represent the elements in the i-th row and j-th column of the subjective weight vector matrix, respectively. Based on this, the consistency index of the evaluation indicators for this layer is calculated. , is represented as: (5) Based on conventional engineering thresholds, when consistency indicators are met At that time, it is determined that the expert judgment matrix has satisfactory consistency; Through bottom-up, layer-by-layer calculations, the final output is a set of subjective comprehensive weights for each bottom-level evaluation indicator relative to the total cost target. , is represented as: (6).

[0018] To reduce the unavoidable reliance on subjective experience in subjective weighting, this example introduces Principal Component Analysis (PCA) to uncover the objective laws governing the engineering data ontology. PCA, while preserving the original data information to the greatest extent possible, eliminates collinearity interference between indicators through orthogonal transformations, condensing the high-dimensional indicator group into a few independent principal components. Then, objective weights are mapped based on the variance and dispersion of the data. The calculation of objective weights using PCA specifically includes: Based on the investigation and collection of objective data from n sets of historical projects, an original evaluation space matrix is ​​constructed. , is represented as: (7) In the formula, n is the number of engineering samples; The number of evaluation indicators; This represents the original data for the nth sample and the pth indicator. To eliminate differences in dimensions and orders of magnitude among different indicators, the original evaluation space matrix is ​​first analyzed. After standardization, the mean of each evaluation index is 0 and the variance is 1, resulting in the covariance matrix. , is represented as: (8) in, This represents the standardized data for the i-th sample and the j-th indicator; This represents the standardized data of the i-th sample and the k-th indicator; For covariance matrix Perform eigenvalue decomposition to extract eigenvalues ​​that are arranged in a non-decreasing order. And the corresponding orthogonal eigenvectors, to quantify the information carrying capacity of each principal component, the variance contribution rate of the j-th principal component is defined. Represented as: (9) Then, the cumulative information contribution rate of the top k principal components is determined. , is represented as: (10) In engineering practice, the cumulative information contribution rate is usually extracted. The first k principal components are used as the effective feature set after dimensionality reduction.

[0019] Each principal component is ranked according to its contribution rate. By performing a weighted linear combination, a comprehensive evaluation vector containing the distribution density of objective information is reconstructed. , is represented as: (11) In the formula, These are the first k principal component vectors selected. denoted as the objective score of the j-th evaluation indicator; the superscript T is the transpose symbol. For the comprehensive evaluation vector Perform normalization to extract the objective weight vector that reflects the original distribution pattern of the data. , is represented as: (12) That is, to obtain the objective weight set .

[0020] In practical implementation, neither FAHP nor PCA can effectively quantify the impact of individual indicators on the nonlinear response variable of transmission line construction cost. Therefore, this example introduces the Random Forest (RF) algorithm based on the Bagging ensemble concept to quantify the feature importance of each indicator. This algorithm generates multiple decision regression trees through bootstrap sampling and uses an out-of-bag (OOB) error measurement mechanism to intuitively reveal the sensitivity and importance of each indicator in the real decision-making environment through variable permutation. The Random Forest (RF) algorithm is used to calculate the feature importance weights, specifically including: Assume the random forest algorithm generates a total of The regression tree, targeting the first There are 100 trees, and each tree contains 100 trees. Each indicator utilizes the corresponding out-of-bag sample subset. Conduct blind testing and calculate the prediction mean square error. , is represented as: (13) In the formula, This represents the true response value of the sample. These are the model's predicted values; The basic out-of-bag error sequence obtained by traversing the entire forest is as follows: (14) To determine the importance of the j-th feature (independent variable), a perturbation is introduced: keeping other feature columns unchanged, the data in the j-th column of the out-of-bag samples are randomly shuffled and re-introduced into the forest for prediction, thereby capturing the permuted error matrix. , is represented as: (15) If a certain indicator is crucial, disrupting its data will inevitably lead to a rapid increase in the model's prediction error. Based on this principle, a variable importance score based on error increment is defined. , is represented as: (16) In the formula, This is the standard deviation of the error increment, used to smooth out fluctuation differences between different trees; Score the importance of this variable Perform global normalization to extract weight allocations that possess machine learning intelligence features. , is represented as: (17) This establishes the set of feature importance weights. .

[0021] The above subjective weights It demonstrates expert experience and objective weighting. Reflects objective data patterns and feature importance weights By exploring the characteristic relationships among various indicators, and in order to break through the limitations of single-dimensional observation, this example combines subjective and objective weighting methods with feature-based weighting methods to determine the weights, ensuring that the comprehensive weights are more scientific and reasonable.

[0022] The final comprehensive environmental cost weight is obtained by combining the subjective weight, objective weight, and feature importance weight with the minimum difference, specifically including: Assume there are a total of Each indicator defines the final combined weight. It is a linear combination of subjective weights, objective weights, and feature importance weights: (18) To ensure the closed nature of the weights, the combination coefficients... , , Normalized geometric constraints must be satisfied: (19) To find the most stable allocation coefficients, the sum of squared differences between the three weight vectors during the fusion evolution process must be minimized. This leads to the construction of a pairwise difference coupling equation system, expressed as: (20) The combination coefficients can be obtained by solving a system of simultaneous nonlinear equations. , , Substitute it into formula (18) and perform normalization correction to obtain the final combined weights of each underlying evaluation index. : (twenty one) Final environmental cost overall weighting This will provide a data foundation for calculating the spatial cost of subsequent path planning algorithms.

[0023] In its specific implementation, this application's embodiments decompose complex environmental impact factors into quantifiable indicators through a hierarchical, modular, and subjective-objective integration approach, significantly improving the systematicness, completeness, and stability of the evaluation system. Fuzzy numbers can effectively accommodate the uncertainty of expert judgment, principal component analysis eliminates data redundancy and linear correlation, and random forests mine the importance of nonlinear features. The combination of these three methods makes the weighting results more in line with engineering practice, avoiding the one-sidedness brought about by a single weighting method, and making the quantification of environmental costs more accurate, reliable, and engineering-convincing.

[0024] Step 3: Construct a path planning model based on the improved ant colony-genetic fusion algorithm (IACO-GA). Input the path environment comprehensive cost weights obtained in Step 2 into the constructed path planning model, and the path planning model outputs the optimal power transmission line path in the target area. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone update, direction guidance and path smoothing mechanisms. In this step, the Ant Colony Optimization (ACO) algorithm, also known as the ant algorithm, is a group-based heuristic optimization algorithm that simulates the foraging behavior of ants. The improved ant colony-genetic fusion algorithm (IACO-GA) introduced in this embodiment uses a two-stage optimization strategy. In the first stage, the genetic algorithm is used to efficiently explore a large-scale solution space and quickly generate a batch of high-quality path solutions, providing excellent initial directions and prior information for subsequent searches. In the second stage, guided by the output of the genetic algorithm, the improved ant colony algorithm is launched to conduct in-depth development in the focused potential high-quality areas. Through its powerful positive feedback and distributed search capabilities, the path is refined and optimized, thereby balancing the algorithm's global exploration and local development capabilities, and finally outputting a power transmission channel scheme with low overall cost and good smoothness.

[0025] The process of constructing a path planning model based on the improved ant colony-genetic fusion algorithm (IACO-GA) is as follows: (1) Path encoding and population initialization To achieve flexible representation of paths of variable length, variable-length indexing is used. A path from the starting point S to the ending point E is encoded as an ordered set of path point indices, for example... The initial population is generated through random paths. Starting from the starting point S, the next node is randomly selected from the neighborhood grid of non-obstacles. This process is iterated until the destination E is reached, thus generating n initial paths. The initial population is set as shown in the following formula: (twenty two) In the formula, the path in the population Considered as a single chromosome; (2) Design of multi-constraint fitness function The fitness function is the core of guiding population evolution, and its design must fully reflect the actual engineering constraints and economic objectives of transmission line planning. The designed fitness function... Taking into account multiple factors such as path length, obstacle avoidance, continuity, and overall cost, it can be expressed as: (twenty three) In the formula, , , and These are weighting factors set to balance different objectives; The calculated comprehensive environmental cost; The smaller the value, the lower the overall path cost and the better the individual quality; Path length cost Defined as: (twenty four) In the formula, Indicates adjacent path nodes and Spatial distance between them; Collision penalties for obstacles or planned avoidance zones Defined as: (25) In the formula, Indicates the number of avoidance zones; The penalty constant; Let q be the radius of influence of the q-th avoidance zone; This is the minimum distance between the path and the center or boundary of the q-th avoidance zone; when the path enters the avoidance zone or the safe distance is insufficient, the penalty term increases, otherwise this term is 0; Safety gap penalty Defined as: (26) In the formula, To penalize the growth rate; This represents the distance between the i-th path segment and the nearest avoidance area; Indicates the ideal safety clearance distance; when When, the penalty increases; when At that time, the penalty item is 0; (3) Genetic Algorithm Operation a. Selection Operator Using a roulette wheel selection method based on fitness ratios, individuals The probability of being selected to enter the mating pool Inversely proportional to its fitness, this mechanism ensures that superior pathways have a higher probability of passing on genes to the next generation, expressed as: (27) Expected number of copies for: (28) For the expected number of copies Round down to get the actual number of copies. b. Cross operator Selected individuals are randomly paired, and at a randomly chosen intersection point, they exchange portions of their path sequences (with a crossover probability). (control) to generate new paths that combine characteristics of the parent generation; c. Random mutation With a small probability Randomly changing one or more path points among individuals introduces random perturbation; this operation can increase population diversity, help the algorithm escape local optima, and prevent premature convergence. (4) Improved Ant Colony Algorithm Optimization Based on the initial path provided by the genetic algorithm, the ant colony algorithm is improved as follows: Pheromonic imbalance initialization: gradient distribution from start to finish enhances directional guidance; Adaptive dynamic pheromone update: automatically adjusts based on solution quality to avoid premature convergence; Comprehensive heuristic function: integrates distance, direction, and corner constraints to improve smoothness; Path smoothing: Jump connection detection to eliminate redundant inflection points; Parameter adaptive: Parameters are dynamically adjusted during iteration; (5) Iteration Termination and Output When the maximum number of iterations or the convergence condition is met, the globally optimal transmission line path is output.

[0026] In its specific implementation, this application embodiment employs a two-level fusion algorithm to achieve efficient and stable optimization under complex geographical environments, large-scale grids, and multiple constraints, resulting in shorter paths, fewer corners, lower costs, and greater engineering practicality. In this application embodiment, the comprehensive fitness function is represented as a comprehensive cost function, comprehensively considering path length, environmental costs, and corner penalties, making the optimization objective more aligned with the actual needs of power transmission line projects.

[0027] According to the transmission line corridor planning method described in the embodiments of this application, a high-precision planning environment is constructed through multi-source data fusion, environmental costs are scientifically quantified through combined weighting models, and efficient, stable, and high-quality path optimization is achieved through improved ant colony-genetic fusion algorithms. The entire method is completely data-driven, objective, and efficient, and can significantly improve the intelligence and digitalization level of transmission line corridor planning. It is applicable to complex scenarios such as urban areas, mountains, hills, and ecologically sensitive areas.

[0028] Step 4: Based on the optimal transmission line path for the target area obtained in Step 3, display the optimal path, environmental cost distribution, convergence curve, and engineering indicators.

[0029] It is worth noting that the contents not described in detail in the embodiments of the present invention belong to the prior art known to those skilled in the art.

[0030] Based on the above method, this invention also provides a power transmission line path planning system based on an ant colony-genetic optimization algorithm, the system comprising: The data acquisition module acquires multi-source geospatial data of the target area and performs classification and quantification processing on the acquired multi-source geospatial data. The cost quantification module constructs an environmental cost evaluation index system and uses a combined weighting model to calculate the comprehensive environmental cost weight of the target area. The intelligent path planning module constructs a path planning model based on an improved ant colony-genetic fusion algorithm. The comprehensive cost weight of the path environment is input into the constructed path planning model, and the path planning model outputs the optimal power transmission line path in the target area. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone updates, direction guidance and path smoothing mechanisms. The results output module displays the optimal path, environmental cost distribution, convergence curve, and engineering indicators based on the obtained optimal transmission line path for the target area.

[0031] The specific implementation process of each module in the above system is described in the above method embodiments.

[0032] In summary, the method and system described in the embodiments of the present invention achieve accurate quantification of environmental costs through combined weighting, reducing subjective bias; improve global optimization capability and convergence stability through improved ant colony-genetic fusion algorithm; path smoothing and corner constraints significantly reduce engineering construction costs; and can directly connect to GIS and remote sensing data, making it highly practical for engineering applications and effectively solving the problems of high cost, low efficiency, and poor accuracy in traditional planning.

[0033] Multi-scenario simulation results show that the improved ant colony-genetic fusion algorithm reduces the overall path cost by 13.2% to 30.4% compared with the traditional ant colony algorithm under different scales and complexities, reduces the average number of path corners by more than 20%, reduces the number of convergence iterations by 15%, significantly reduces the standard deviation of cost, and significantly enhances the overall convergence speed, path quality and operational stability.

[0034] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. The information disclosed in the background section is intended only to enhance the understanding of the overall background technology of the present invention and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art.

Claims

1. A power transmission line path planning method based on ant colony-genetic optimization algorithm, characterized in that, The method includes: Step 1: Acquire multi-source geospatial data of the target area, and classify and quantify the acquired multi-source geospatial data; Step 2: Construct an environmental cost evaluation index system and use a combined weighting model to calculate the comprehensive environmental cost weight of the target area. Step 3: Construct a path planning model based on the improved ant colony-genetic fusion algorithm. Input the path environment comprehensive cost weight obtained in Step 2 into the constructed path planning model, and output the optimal power transmission line path in the target area from the path planning model. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone update, direction guidance and path smoothing mechanism. Step 4: Based on the optimal transmission line path for the target area obtained in Step 3, display the optimal path, environmental cost distribution, convergence curve, and engineering indicators.

2. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 1, characterized in that, In step 1, satellite remote sensing images, digital elevation model (DEM) data, land use data, and road vector data of the target area are acquired; Geographic Information System (GIS) tools are used to perform radiometric calibration, orthorectification, registration, and coordinate unification on the acquired data. Object-oriented classification is used to classify land features, including: buildings, cultivated land, forest land, grassland, water bodies, roads, and railways; By overlaying elevation and slope data, the data is rasterized and reclassified to form a target classification result for cost calculation.

3. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 1, characterized in that, In step 2, an environmental cost evaluation index system with a four-layer structure including natural factors, social factors, engineering factors, and planning avoidance factors is constructed. The subjective weights are calculated using fuzzy hierarchical analysis, the objective weights are calculated using principal component analysis, and the feature importance weights are calculated using the random forest algorithm. The final comprehensive environmental cost weight is obtained by combining the subjective weight, objective weight, and feature importance weight with the minimum difference.

4. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 3, characterized in that, The subjective weights are calculated using the fuzzy analytic hierarchy process, specifically as follows: Suppose that a certain level contains The evaluation indicators are compared pairwise using scaling methods to determine their importance, thereby constructing a... fuzzy complementary matrix of order , is represented as: （1） matrix The elements inside satisfy and complementary constraints ; Extracting the matrix The sum of elements in each row And accordingly, the fuzzy complementary matrix Transformed into a fuzzy consistent matrix with rigorous logic. The conversion formula is: （2） in, Represents the elements in the fuzzy consistency matrix; This represents a column of elements in a fuzzy complementary matrix; Based on fuzzy consistency matrix The row sum normalization method is used to solve for the subjective basis weights of each evaluation index relative to the previous level. , is represented as: （3） This yields the subjective weight vector of the evaluation indicators for this layer. The superscript T is the transpose symbol; Construct the characteristic matrix The internal elements of this feature matrix Defined as: （4） in , These represent the elements in the i-th row and j-th column of the subjective weight vector matrix, respectively. Based on this, the consistency index of the evaluation indicators for this layer is calculated. , is represented as: （5） When the consistency index is met At that time, it is determined that the expert judgment matrix has satisfactory consistency; Through bottom-up, layer-by-layer calculations, the final output is a set of subjective comprehensive weights for each bottom-level evaluation indicator relative to the total cost target. , is represented as: （6）。 5. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 4, characterized in that, The objective weights are calculated using principal component analysis, specifically including: Based on the investigation and collection of objective data from n sets of historical projects, an original evaluation space matrix is ​​constructed. , is represented as: （7） In the formula, n is the number of engineering samples; The number of evaluation indicators; This represents the original data for the nth sample and the pth indicator. First, the original evaluation space matrix After standardization, the mean of each evaluation index is 0 and the variance is 1, resulting in the covariance matrix. , is represented as: （8） in, This represents the standardized data for the i-th sample and the j-th indicator; This represents the standardized data of the i-th sample and the k-th indicator; For covariance matrix Perform eigenvalue decomposition to extract eigenvalues ​​that are arranged in a non-decreasing order. And the corresponding orthogonal eigenvectors, to quantify the information carrying capacity of each principal component, the variance contribution rate of the j-th principal component is defined. Represented as: （9） Then, the cumulative information contribution rate of the top k principal components is determined. , is represented as: （10） Each principal component is ranked according to its contribution rate. By performing a weighted linear combination, a comprehensive evaluation vector containing the distribution density of objective information is reconstructed. , is represented as: （11） In the formula, These are the first k principal component vectors selected. denoted as the objective score of the j-th evaluation indicator; the superscript T is the transpose symbol. For the comprehensive evaluation vector Perform normalization to extract the objective weight vector that reflects the original distribution pattern of the data. , is represented as: （12） That is, to obtain the objective weight set .

6. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 5, characterized in that, The random forest algorithm is used to calculate feature importance weights, specifically including: Assume the random forest algorithm generates a total of The regression tree, targeting the first There are 100 trees, and each tree contains 100 trees. Each indicator utilizes the corresponding out-of-bag sample subset. Conduct blind testing and calculate the prediction mean square error. , is represented as: （13） In the formula, This represents the true response value of the sample. These are the model's predicted values; The basic out-of-bag error sequence obtained by traversing the entire forest is as follows: （14） To determine the importance of the j-th feature, a perturbation is introduced: keeping other feature columns unchanged, the data in the j-th column of the out-of-bag samples are randomly shuffled and re-introduced into the forest for prediction, thereby capturing the permuted error matrix. , is represented as: （15） Define variable importance scores based on error increments , is represented as: （16） In the formula, This is the standard deviation of the error increment, used to smooth out fluctuation differences between different trees; Score the importance of this variable Perform global normalization to extract weight allocations that possess machine learning intelligence features. , is represented as: （17） This establishes the set of feature importance weights. .

7. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 6, characterized in that, The process of combining subjective weights, objective weights, and feature importance weights with minimum difference to obtain the final comprehensive environmental cost weight specifically includes: Assume there are a total of Each indicator defines the final combined weight. It is a linear combination of subjective weights, objective weights, and feature importance weights: （18） To ensure the closed nature of the weights, the combination coefficients... , , Normalized geometric constraints must be satisfied: （19） To find the most stable allocation coefficients, the sum of squared differences between the three weight vectors during the fusion evolution process must be minimized. This leads to the construction of a pairwise difference coupling equation system, expressed as: （20） The combination coefficients can be obtained by solving a system of simultaneous nonlinear equations. , , Substitute it into formula (18) and perform normalization correction to obtain the final combined weights of each underlying evaluation index. : （21） Final environmental cost overall weighting This will provide a data foundation for calculating the spatial cost of subsequent path planning algorithms.

8. The power transmission line path planning method based on ant colony-genetic optimization algorithm according to claim 1, characterized in that, In step 3, the process of constructing the path planning model based on the improved ant colony-genetic fusion algorithm is as follows: (1) Path encoding and population initialization To achieve flexible representation of paths of variable length, variable-length indexing is used. A path from the starting point S to the ending point E is encoded as an ordered set of path point indices. The initial population is generated through random paths. Starting from the starting point S, the next node is randomly selected from the neighborhood grid of non-obstacles. This process is iterated until the ending point E is reached, thus generating n initial paths. The initial population is set as shown in the following formula: （22） In the formula, the path in the population Considered as a single chromosome; (2) Design of multi-constraint fitness function The designed fitness function Taking into account multiple factors such as path length, obstacle avoidance, continuity, and overall cost, it can be expressed as: （23） In the formula, , , and These are weighting factors set to balance different objectives; The calculated comprehensive environmental cost; The smaller the value, the lower the overall path cost and the better the individual quality; Path length cost Defined as: （24） In the formula, Indicates adjacent path nodes and Spatial distance between them; Collision penalties for obstacles or planned avoidance zones Defined as: （25） In the formula, Indicates the number of avoidance zones; The penalty constant; Let q be the radius of influence of the q-th avoidance zone; This is the minimum distance between the path and the center or boundary of the q-th avoidance zone; when the path enters the avoidance zone or the safe distance is insufficient, the penalty term increases, otherwise this term is 0; Safety gap penalty Defined as: （26） In the formula, To penalize the growth rate; This represents the distance between the i-th path segment and the nearest avoidance area; Indicates the ideal safety clearance distance; when When, the penalty increases; when At that time, the penalty item is 0; (3) Genetic Algorithm Operation a. Selection Operator Using a roulette wheel selection method based on fitness ratios, individuals The probability of being selected to enter the mating pool It is inversely proportional to its fitness, expressed as: （27） Expected number of copies for: （28） For the expected number of copies Round down to get the actual number of copies. b. Cross operator Selected individuals are randomly paired, and their partial path sequences are exchanged at randomly selected intersections to generate new paths that retain characteristics of their parents. c. Random mutation With a small probability Randomly change one or more path points in an individual to introduce random perturbation; (4) Improved Ant Colony Algorithm Optimization Based on the initial path provided by the genetic algorithm, the ant colony algorithm is improved as follows: Pheromonic imbalance initialization: gradient distribution from start to finish enhances directional guidance; Adaptive dynamic pheromone update: automatically adjusts based on solution quality to avoid premature convergence; Comprehensive heuristic function: integrates distance, direction, and corner constraints to improve smoothness; Path smoothing: Jump connection detection to eliminate redundant inflection points; Parameter adaptive: Parameters are dynamically adjusted during iteration; (5) Iteration Termination and Output When the maximum number of iterations or the convergence condition is met, the globally optimal transmission line path is output.

9. A power transmission line path planning system based on ant colony-genetic optimization algorithm, characterized in that, The system includes: The data acquisition module acquires multi-source geospatial data of the target area and performs classification and quantification processing on the acquired multi-source geospatial data. The cost quantification module constructs an environmental cost evaluation index system and uses a combined weighting model to calculate the comprehensive environmental cost weight of the target area. The intelligent path planning module constructs a path planning model based on an improved ant colony-genetic fusion algorithm. The comprehensive cost weight of the path environment obtained in step 2 is input into the constructed path planning model, and the path planning model outputs the optimal power transmission line path in the target area. The improved ant colony-genetic fusion algorithm is a fusion algorithm that introduces adaptive pheromone update, direction guidance and path smoothing mechanism. The results output module displays the optimal path, environmental cost distribution, convergence curve, and engineering indicators based on the obtained optimal transmission line path for the target area.

Images