Intelligent optimization design platform for transmission line foundation based on multi-objective algorithm

Abstract

The present invention provides an intelligent optimization design platform for power transmission line foundations based on a multi-objective algorithm, relating to the technical field of power transmission line foundation design. The platform includes obtaining data on factors influencing target locations; obtaining evaluation factors for selecting foundation designs; constructing a foundation type selection model based on a random forest, inputting influencing factor data, evaluation factors, and corresponding weights, and outputting a score for each foundation type; optimizing the dimensional parameters of the selected foundation type, and obtaining the optimal material selection ratio based on the performance of different foundation materials. Through efficient data processing capabilities, scientific evaluation indicators, intelligent decision-making models, and advanced optimization design processes, the present invention provides a new solution for modern power transmission projects.

Description

Technical Field

[0001] The present invention relates to the technical field of transmission line foundation design, and in particular to an intelligent optimization design platform for transmission line foundations based on a multi-objective algorithm. Background Art

[0002] The use of transmission line foundations dates back to the early 20th century. With the development of the electric power industry, transmission line technology has gradually matured, and foundation design and materials have also evolved. Initially, transmission lines relied on simple wooden piles or concrete columns, which had poor load-bearing capacity and durability. In the late 20th century, as electricity demand increased, foundation design gradually became standardized, resulting in a relatively comprehensive set of design standards and construction specifications.

[0003] Current foundation design often relies on engineers' experience and lacks scientific calculation methods. This can lead to inappropriate design, compromising the safety and economic viability of foundations. In extreme weather conditions, such as strong winds, or complex geological conditions, existing design solutions are insufficient to provide ideal stability. The industry's design process still relies too heavily on manual labor and lacks sufficient support from automated and intelligent technologies. Furthermore, much potential information cannot be effectively utilized, hindering the scientific nature of decision-making. Summary of the Invention

[0004] The present invention provides a transmission line foundation intelligent optimization design platform based on a multi-objective algorithm to solve the defects existing in the prior art.

[0005] The present invention provides a transmission line foundation intelligent optimization design platform based on a multi-objective algorithm, comprising:

[0006] The data acquisition and processing module is used to obtain the influencing factor data of the target transmission line foundation position and pre-process the influencing factor data to obtain pre-processed data.

[0007] The selection index determination module is used to conduct a comprehensive analysis of the pre-processed data, obtain the evaluation factors for selecting the transmission line foundation design, and determine the weight of each evaluation factor according to the hierarchical analysis method.

[0008] The selection model construction module is used to build a transmission line foundation type selection model based on random forest. It inputs influencing factor data, evaluation factors and corresponding weights, outputs the score of each transmission line foundation type, and selects the transmission line foundation type with the highest score as the final selection.

[0009] The foundation design optimization module is used to optimize the size parameters of the selected transmission line foundation type based on evaluation factors using genetic algorithms, and to obtain the optimal material selection ratio based on the performance of different foundation materials.

[0010] According to the intelligent optimization design platform for transmission line foundations based on a multi-objective algorithm provided by the present invention, the influencing factor data includes geological survey data, and the geological survey data includes the soil type at the target transmission line foundation location, the thickness of various types of soil layers, the soil density, internal friction angle, cohesion and compression modulus.

[0011] According to the multi-objective algorithm-based intelligent optimization design platform for power transmission line foundations provided by the present invention, the influencing factor data also includes superstructure load data, environmental data, and tension data. The superstructure load data represents the shape and total weight of the superstructure of the power transmission line foundation. The environmental data includes wind force data and wind direction data at the target power transmission line foundation location. The tension data represents the tension of the wires at both ends of the target power transmission line foundation.

[0012] According to the intelligent optimization design platform for power transmission line foundation based on the multi-objective algorithm provided by the present invention, the process of preprocessing the influencing factor data includes:

[0013] Check and remove duplicates from influencing factor data.

[0014] The mean filling method is used to fill the missing values ​​in the influencing factor data.

[0015] The influencing factor data are standardized and data of different dimensions are converted into a unified standard.

[0016] The standardized geological survey data, superstructure load data, environmental data and tension data are merged into a comprehensive data set as preprocessing data.

[0017] According to the intelligent optimization design platform for power transmission line foundations based on a multi-objective algorithm provided by the present invention, the evaluation factors include foundation bearing capacity requirements, and the process of obtaining the foundation bearing capacity requirements includes:

[0018] Extract geodetic survey data, superstructure load data, environmental data, and tension data for the target transmission line foundation location.

[0019] The total weight in the superstructure load data is used as the vertical load.

[0020] According to the structural shape of the superstructure and combined with the wind force data and wind direction data in the environmental data, the wind load on the superstructure of the target transmission line foundation is calculated, and the action angle of the wind load is obtained.

[0021] Calculate the difference in wire tension data at both ends of the target transmission line foundation to obtain the tension load and the angle of action of the tension load.

[0022] The wind load and tension load are decomposed to obtain the horizontal component of wind load, the vertical component of wind load, the horizontal component of tension load and the vertical component of tension load.

[0023] The horizontal component of wind load, the vertical component of wind load, the horizontal component of tension load and the vertical component of tension load are synthesized to obtain the resultant load, which is used as the foundation bearing capacity requirement.

[0024] According to the intelligent optimization design platform for power transmission line foundations based on a multi-objective algorithm provided by the present invention, the evaluation factors also include settlement control requirements. The process of obtaining the settlement control requirements includes:

[0025] The soil compression coefficient and consolidation characteristics of the soil layer at the target transmission line foundation location are obtained based on geological survey data.

[0026] The sensitivity to uneven settlement is calculated based on the superstructure load data of the target transmission line foundation and the foundation bearing capacity requirements.

[0027] The finite element analysis method is used to obtain the settlement and settlement difference of the target transmission line foundation within the foundation bearing capacity requirements.

[0028] Determine the allowable range of settlement according to the preset standards and obtain the settlement control requirements.

[0029] According to the transmission line foundation intelligent optimization design platform based on the multi-objective algorithm provided by the present invention, the process of determining the weight of each evaluation factor includes:

[0030] Transmission line foundation types and evaluation factors are stratified into target, criterion, and solution layers. The target layer is used to determine the optimal transmission line foundation design objectives. The criterion layer defines evaluation factors, including bearing capacity requirements and settlement control requirements. The solution layer provides design options for different transmission line foundation types.

[0031] The relative importance of the evaluation factors is compared and a judgment matrix is ​​constructed. Each value in the judgment matrix represents the importance of the evaluation factors.

[0032] The consistency test of the judgment matrix is ​​performed by calculating the maximum eigenvalue and consistency index of the judgment matrix.

[0033] The judgment matrix is ​​normalized to obtain the weight of each evaluation factor.

[0034] According to the intelligent optimization design platform for transmission line foundation based on a multi-objective algorithm provided by the present invention, the process of constructing a transmission line foundation type selection model based on a random forest includes:

[0035] Collect historical data of transmission line foundation design, including historical geological survey data, historical superstructure load data, historical environmental data and historical tension data.

[0036] A comprehensive analysis of historical data is conducted to obtain historical evaluation factors for transmission line foundation design, and the weight of each historical evaluation factor is determined.

[0037] Each set of historical data, historical evaluation factors and the basic type of transmission lines corresponding to the weights are taken as a set of data to construct a data set, and the data set is divided into a training set and a test set.

[0038] Randomly extract sample data from the training set, and extract the historical influencing factor characteristics and historical evaluation factor characteristics in the sample data.

[0039] Build a basic decision tree and divide the sample data into different sub-nodes in the decision tree until the depth of the tree reaches a preset threshold.

[0040] The process of constructing basic decision trees is repeated according to the preset number of decision trees to obtain a random forest.

[0041] According to the intelligent optimization design platform for transmission line foundations based on a multi-objective algorithm provided by the present invention, the process of optimizing the size parameters of the selected transmission line foundation type using a genetic algorithm includes:

[0042] Set optimization objectives, which include minimizing foundation settlement and maximizing foundation bearing capacity.

[0043] The initial size parameters of the transmission line foundation type and the evaluation factors of the target transmission line foundation are collected, and the evaluation function is constructed in combination with the optimization objective.

[0044] The initial size parameter is expressed as a genetic code and the initial population is randomly generated.

[0045] The roulette wheel selection method is used to determine the next generation of parents, and a crossover operation is performed to generate a new generation of size parameter individuals. The size parameters are randomly mutated to increase the diversity of the optimization search.

[0046] The process of crossover and random mutation is repeated until the preset number of iterations is met.

[0047] The fitness value of each size parameter individual is calculated according to the evaluation function, and the size parameter solution with the highest fitness value is obtained.

[0048] According to the intelligent optimization design platform for power transmission line foundations based on a multi-objective algorithm provided by the present invention, the process of obtaining the optimal material selection ratio includes:

[0049] Set the objective function and constraints. The objective function includes maximizing the comprehensive performance of the material and minimizing the overall material cost. The constraints include the bearing capacity requirements of the transmission line foundation.

[0050] Collect technical parameters of transmission line foundation materials, including compressive strength and tensile strength.

[0051] A linear programming model is constructed to obtain the material ratio scheme for the transmission line foundation based on the objective function, constraints and technical parameters of the foundation materials.

[0052] The intelligent optimization design platform for power transmission line foundations, based on a multi-objective algorithm, provided by this invention, obtains and preprocesses data on various factors affecting transmission line foundations, ensuring that the design process is based on accurate and reliable information. This reduces design deviations caused by insufficient experience or inaccurate assumptions, thereby improving overall design reliability. By extracting evaluation factors for foundation bearing capacity and settlement control and assigning weights to these factors using the analytic hierarchy process (AHP), this platform ensures comprehensive design objectives, taking into account both structural safety and in-service performance, forming a balanced objective system that lays the foundation for subsequent decision-making. Using the random forest algorithm, the model efficiently evaluates the performance of different foundation types and outputs a score by inputting the influencing factors and evaluation factor weights derived from a comprehensive analysis. This avoids overfitting and more accurately reflects the adaptability of various foundation types to diverse environments and loading conditions compared to traditional methods. This reduces the subjectivity of manual judgment, resulting in more reasonable foundation type selection and significantly improving project quality. A genetic algorithm is used to optimize the dimensional parameters of the selected foundation types. With its powerful global optimization capabilities, the genetic algorithm effectively explores the design space and finds the optimal dimensional parameter combination. By integrating multiple objectives, including structural safety, cost-effectiveness, and material efficiency, the optimal design is achieved. Based on the properties of different foundation materials, the optimal material selection and proportioning are determined, improving the performance and durability of the structure and, to a certain extent, reducing the construction cost. Working together, the entire design platform improves the efficiency of transmission line foundation design, enabling engineers to more quickly respond to design requirements and changing site conditions, improving the economic efficiency of the project. Data-driven decision-making ensures the most appropriate foundation is selected under different conditions, reducing potential safety hazards caused by inappropriate design. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 It is a structural diagram of a basic intelligent optimization design platform for power transmission lines based on a multi-objective algorithm provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0056] The following combination Figure 1 The present invention describes a transmission line basic intelligent optimization design platform based on a multi-objective algorithm.

[0057] Figure 1 It is a structural diagram of a basic intelligent optimization design platform for power transmission lines based on a multi-objective algorithm provided by an embodiment of the present invention.

[0058] like Figure 1 As shown, the transmission line foundation intelligent optimization design platform based on the multi-objective algorithm provided by the embodiment of the present invention includes a data acquisition and processing module, a selection index determination module, a selection model construction module and a basic design optimization module.

[0059] The data acquisition and processing module is used to obtain the influencing factor data of the target transmission line foundation position, which includes geological survey data, superstructure load data, environmental data and tension data, and preprocess the influencing factor data to obtain preprocessed data.

[0060] Geological survey data includes soil type, thickness of various soil layers, soil density, internal friction angle, cohesion, and compression modulus at the target transmission line foundation location. Superstructure load data indicates the shape and total weight of the transmission line foundation superstructure. Environmental data includes wind force and direction data at the target transmission line foundation location. Tensile force data indicates the tension in the wires at both ends of the target transmission line foundation.

[0061] The process of preprocessing influencing factor data includes:

[0062] Check and remove duplicates from influencing factor data.

[0063] The mean filling method is used to fill the missing values ​​in the influencing factor data.

[0064] The influencing factor data are standardized and data of different dimensions are converted into a unified standard.

[0065] The standardized geological survey data, superstructure load data, environmental data and tension data are merged into a comprehensive data set as preprocessing data.

[0066] In this embodiment, professional equipment including a drill rig and a sampler are equipped to adjust the drilling depth according to the designed depth of the pile foundation and the geological conditions. The drilling method is used to drill at the expected foundation location to obtain soil samples and conduct on-site tests. The collected soil samples are sent to the laboratory for relevant physical and mechanical property tests, including: determining the soil type through visual observation and standard classification methods. The thickness of different soil layers is measured by recording the stratification of the soil samples through drilling. The dry weight and volume of the soil samples are measured, and the weight per unit volume is calculated. The shear strength of the soil samples is measured by standard test methods such as direct shear test or triaxial test, and the internal friction angle and cohesion are obtained. The compression modulus is obtained by measuring the stress-strain relationship of the soil under specific stress conditions through compression test.

[0067] Based on the transmission line tower design, including tower type, member height, and layout, load calculations are performed using structural analysis software such as SAP2000 and ANSYS. The weight of the tower itself, conductors, and other ancillary equipment, such as lightning rods and monitoring equipment, is taken into account and combined. Structural mechanics analysis simulates dynamic and static loads on the foundation to evaluate the stability of the pile foundation design.

[0068] Obtain historical and real-time weather data from nearby weather monitoring stations. This includes: Wind speed data: including maximum and average wind speeds. Wind direction data: Use a wind vane or weather station equipment to record wind direction.

[0069] Tension sensors are installed at the wires at both ends of the transmission line to monitor wire tension in real time. Strain gauges can be mounted directly on conductor accessories to monitor changes in wire strain. Digital tensiometers directly read and record wire tension and are connected to a data acquisition system for real-time data upload. After transmission line construction is completed, on-site inspections are conducted using specialized equipment for acceptance testing to ensure the stability of the wires under load.

[0070] The selection index determination module is used to conduct a comprehensive analysis of the pre-processed data to obtain the evaluation factors for selecting the transmission line foundation design. The evaluation factors include the foundation bearing capacity requirements and settlement control requirements, and the weight of each evaluation factor is determined according to the hierarchical analysis method.

[0071] The process of obtaining foundation bearing capacity requirements includes:

[0072] Extract geodetic survey data, superstructure load data, environmental data, and tension data for the target transmission line foundation location.

[0073] The total weight in the superstructure load data is used as the vertical load.

[0074] According to the structural shape of the superstructure, combined with the wind force data and wind direction data in the environmental data, the wind load on the superstructure of the target transmission line foundation is calculated, and the action angle of the wind load is obtained. The formula is expressed as:

[0075]

[0076] Where, represents wind load, represents the drag coefficient, represents air density, V represents wind speed, Indicates the frontal area.

[0077] Calculate the difference in wire tension data at both ends of the target transmission line foundation to obtain the tension load and the angle of action of the tension load.

[0078] The wind load and tension load are decomposed to obtain the horizontal component of wind load, the vertical component of wind load, the horizontal component of tension load and the vertical component of tension load.

[0079] The horizontal component of wind load, the vertical component of wind load, the horizontal component of tension load and the vertical component of tension load are synthesized to obtain the resultant load, which is used as the foundation bearing capacity requirement. The formula is expressed as follows:

[0080]

[0081]

[0082]

[0083]

[0084]

[0085] Where, represents wind load, represents the horizontal component of wind load, represents the vertical component of wind load, represents the horizontal component of the tension load, represents the tension load, represents the vertical component of the tension load, represents the resultant load, represents the angle of action of wind load, Indicates the angle at which the tension load acts.

[0086] The process of obtaining settlement control requirements includes:

[0087] The soil compression coefficient and consolidation characteristics of the soil layer at the target transmission line foundation location are obtained based on geological survey data.

[0088] The sensitivity to uneven settlement is calculated based on the superstructure load data of the target transmission line foundation and the foundation bearing capacity requirements.

[0089] The finite element analysis method is used to obtain the settlement and settlement difference of the target transmission line foundation within the foundation bearing capacity requirements.

[0090] Determine the allowable range of settlement according to the preset standards and obtain the settlement control requirements.

[0091] The process of determining the weight of each evaluation factor includes:

[0092] Transmission line foundation types and evaluation factors are stratified into target, criterion, and solution layers. The target layer is used to determine the optimal transmission line foundation design objectives. The criterion layer defines evaluation factors, including bearing capacity requirements and settlement control requirements. The solution layer provides design options for different transmission line foundation types.

[0093] The relative importance of the evaluation factors is compared and a judgment matrix is ​​constructed. Each value in the judgment matrix represents the importance of the evaluation factors.

[0094] By calculating the maximum eigenvalue and consistency index of the judgment matrix, the consistency test of the judgment matrix is ​​performed. The formula is expressed as:

[0095]

[0096]

[0097] Where, represents the maximum eigenvalue of the judgment matrix, represents the consistency index, represents the random consistency index, represents the consistency ratio, and n represents the number of evaluation factors.

[0098] If the consistency ratio CR is less than 0.1, the judgment matrix has acceptable consistency.

[0099] The judgment matrix is ​​normalized to obtain the weight of each evaluation factor.

[0100] The selection model construction module is used to build a transmission line foundation type selection model based on random forest. It inputs influencing factor data, evaluation factors and corresponding weights, outputs the score of each transmission line foundation type, and selects the transmission line foundation type with the highest score as the final selection.

[0101] The process of building a random forest-based transmission line foundation type selection model includes:

[0102] Collect historical data of transmission line foundation design, including historical geological survey data, historical superstructure load data, historical environmental data and historical tension data.

[0103] A comprehensive analysis of historical data is conducted to obtain historical evaluation factors for transmission line foundation design, and the weight of each historical evaluation factor is determined.

[0104] Each set of historical data, historical evaluation factors and the basic type of transmission lines corresponding to the weights are taken as a set of data to construct a data set, and the data set is divided into a training set and a test set.

[0105] Randomly extract sample data from the training set, and extract the historical influencing factor characteristics and historical evaluation factor characteristics in the sample data.

[0106] Build a basic decision tree and divide the sample data into different sub-nodes in the decision tree until the depth of the tree reaches a preset threshold.

[0107] The process of constructing basic decision trees is repeated according to the preset number of decision trees to obtain a random forest.

[0108] In this embodiment, each set of historical data, including historical influencing factors, historical evaluation factors, and the corresponding transmission line infrastructure type, is labeled to form labeled data for supervised learning. The dataset is divided into a training set and a test set. The training set is used for model training, and the test set is used for model validation.

[0109] Randomly sample data from the training set to build a decision tree. Random forest reduces overfitting through multiple sampling and improves the predictive power of the model.

[0110] The historical influencing factor characteristics and historical evaluation factor characteristics in the sample data are extracted as input data for subsequent decision tree construction.

[0111] Combine the extracted features and use the selected partitioning criteria to split the sample. Split until the preset tree depth is reached. The preset tree depth can be 5 to 15 layers.

[0112] The decision tree is created repeatedly for a predetermined number of times. Each tree uses a different random sample and random features, thus forming a random forest.

[0113] For each basis type, a vote or score aggregation is performed using each decision tree in the random forest. Each decision tree outputs a predicted category based on the input features, and the score for each basis type is ultimately determined by majority vote.

[0114] Based on the scores output by the random forest algorithm, the transmission line foundation type with the highest score is selected as the final choice.

[0115] Use the test set to evaluate the constructed random forest model, calculate the accuracy, and judge the model performance.

[0116] The model parameters, including the number of trees, maximum depth, and minimum number of sample splits, were adjusted through grid search to optimize the model performance.

[0117] The foundation design optimization module is used to optimize the size parameters of the selected transmission line foundation type based on the evaluation factors using a genetic algorithm, and to obtain the optimal material selection ratio based on the performance of different foundation materials.

[0118] The process of optimizing the dimensional parameters of the selected transmission line foundation type using the genetic algorithm includes:

[0119] Set optimization objectives, which include minimizing foundation settlement and maximizing foundation bearing capacity.

[0120] The initial size parameters of the transmission line foundation type and the evaluation factors of the target transmission line foundation are collected, and the evaluation function is constructed in combination with the optimization objective.

[0121] The initial size parameter is expressed as a genetic code and the initial population is randomly generated.

[0122] The roulette wheel selection method is used to determine the next generation of parents, and a crossover operation is performed to generate a new generation of size parameter individuals. The size parameters are randomly mutated to increase the diversity of the optimization search.

[0123] The process of crossover and random mutation is repeated until the preset number of iterations is met.

[0124] The fitness value of each size parameter individual is calculated according to the evaluation function, and the size parameter solution with the highest fitness value is obtained.

[0125] The process of obtaining the optimal material selection ratio includes:

[0126] Set the objective function and constraints. The objective function includes maximizing the comprehensive performance of the material and minimizing the overall material cost. The constraints include the bearing capacity requirements of the transmission line foundation.

[0127] Collect technical parameters of transmission line foundation materials, including compressive strength and tensile strength.

[0128] A linear programming model is constructed to obtain the material ratio scheme for the transmission line foundation based on the objective function, constraints and technical parameters of the foundation materials.

[0129] In summary, this embodiment provides an intelligent optimization design platform for transmission line foundations based on a multi-objective algorithm. By acquiring and preprocessing data on various factors affecting transmission line foundations, the platform ensures that the design process is based on accurate and reliable information, reduces design deviations caused by insufficient experience or inaccurate assumptions, and improves overall design reliability. By extracting evaluation factors for foundation bearing capacity and settlement control and assigning weights to these factors using the analytic hierarchy process (AHP), the platform ensures comprehensive design objectives, considering both structural safety and in-service performance. This creates a balanced objective system, laying the foundation for subsequent decision-making. Using the random forest algorithm, the model efficiently evaluates the performance of different foundation types and outputs a score by inputting the influencing factors and evaluation factor weights derived from a comprehensive analysis. Random forest avoids overfitting and more accurately reflects the adaptability of various foundation types to diverse environments and loading conditions compared to traditional methods. This reduces the subjectivity of manual judgment, resulting in a more rational selection of foundation types and significantly improving project quality. A genetic algorithm is used to optimize the dimensional parameters of the selected foundation types. With its powerful global optimization capabilities, the genetic algorithm effectively explores the design space and finds the optimal dimensional parameter combination. By integrating multiple objectives, including structural safety, cost-effectiveness, and material efficiency, the optimal design is achieved. Based on the properties of different foundation materials, the optimal material selection and proportioning are determined, improving the performance and durability of the structure and, to a certain extent, reducing the construction cost. Working together, the entire design platform improves the efficiency of transmission line foundation design, enabling engineers to more quickly respond to design requirements and changing site conditions, improving the economic efficiency of the project. Data-driven decision-making ensures the most appropriate foundation is selected under different conditions, reducing potential safety hazards caused by inappropriate design.

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0131] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A transmission line foundation intelligent optimization design platform based on a multi-objective algorithm, characterized by: include: A data acquisition and processing module is used to obtain influencing factor data of the target transmission line foundation position and preprocess the influencing factor data to obtain preprocessed data; A selection index determination module is used to perform a comprehensive analysis on the pre-processed data, obtain evaluation factors for selecting the transmission line foundation design, and determine the weight of each evaluation factor according to the hierarchical analysis method; A selection model building module is used to build a transmission line foundation type selection model based on random forest, input the influencing factor data, the evaluation factors and the corresponding weights, output the score of each transmission line foundation type, and select the transmission line foundation type with the highest score as the final selection; The process of building a transmission line foundation type selection model includes: Collecting historical data for transmission line foundation design, the historical data including historical geological survey data, historical superstructure load data, historical environmental data, and historical tension data; Performing a comprehensive analysis on the historical data to obtain historical evaluation factors for the transmission line foundation design, and determining a weight for each of the historical evaluation factors; Taking each set of the historical data, the historical evaluation factors, and the basic type of transmission lines corresponding to the weights as a set of data, constructing a data set, and dividing the data set into a training set and a test set; Randomly extracting sample data from the training set, and extracting historical influencing factor features and historical evaluation factor features from the sample data; Constructing a basic decision tree and dividing the sample data into different sub-nodes in the decision tree until the depth of the tree reaches a preset threshold; Repeat the process of building basic decision trees according to the preset number of decision trees to obtain a random forest; The foundation design optimization module is used to optimize the size parameters of the selected transmission line foundation type using a genetic algorithm based on the evaluation factors, and obtain the optimal material selection ratio based on the performance of different foundation materials.

2. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The influencing factor data includes geological survey data, which includes the soil type, thickness of various types of soil layers, soil density, internal friction angle, cohesion and compression modulus at the target transmission line foundation location.

3. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The influencing factor data also includes superstructure load data, environmental data and tension data. The superstructure load data represents the shape and total weight of the superstructure of the transmission line foundation; the environmental data includes wind force data and wind direction data at the target transmission line foundation location; the tension data represents the tension data on the target transmission line foundation, which refers to the quantitative index data of various mechanical loads borne by the conductors, towers and foundation structures during operation.

4. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The process of preprocessing the influencing factor data includes: Checking and removing duplicates in the influencing factor data; The missing values ​​in the influencing factor data are filled using the mean filling method; Standardize the influencing factor data and convert data of different dimensions into a unified standard; The standardized geological survey data, superstructure load data, and environmental data are merged into a comprehensive data set as preprocessing data.

5. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The evaluation factors include foundation bearing capacity requirements, and the process of obtaining the foundation bearing capacity requirements includes: Extract geological survey data, superstructure load data, and environmental data of the target transmission line foundation location; The total weight in the superstructure load data is used as the vertical load; Calculating the wind load on the superstructure of the target transmission line foundation according to the structural shape of the superstructure and combining the wind force data and wind direction data in the environmental data, and obtaining the action angle of the wind load; Calculating the difference in wire tension data at both ends of the target transmission line foundation to obtain a tension load, and obtaining the action angle of the tension load; Decomposing the wind load and the tension load to obtain a horizontal component of the wind load, a vertical component of the wind load, a horizontal component of the tension load, and a vertical component of the tension load; The horizontal component of the wind load, the vertical component of the wind load, the horizontal component of the tension load and the vertical component of the tension load are synthesized to obtain a load resultant force, which is used as the basic bearing capacity requirement.

6. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The evaluation factors also include settlement control requirements. The process of obtaining the settlement control requirements includes: Obtain the soil compression coefficient and consolidation characteristics of the target transmission line foundation location based on geological survey data; Calculate the sensitivity of differential settlement based on the superstructure load data of the target transmission line foundation and the foundation bearing capacity requirements; Using the finite element analysis method, obtain the settlement and settlement difference of the target transmission line foundation under the foundation bearing capacity requirements; Determine the allowable range of settlement according to the preset standards and obtain the settlement control requirements.

7. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The process of determining the weight of each of the evaluation factors includes: The transmission line foundation types and the evaluation factors are layered, including a target layer, a criterion layer, and a scheme layer; the target layer is used to determine the optimal transmission line foundation design target; the criterion layer is used to define the evaluation factors, including bearing capacity requirements and settlement control requirements; and the scheme layer is used to provide different transmission line foundation type design schemes; Comparing the relative importance of the evaluation factors and constructing a judgment matrix, wherein each value in the judgment matrix represents the importance of the evaluation factors; Performing a consistency test on the judgment matrix by calculating the maximum eigenvalue and consistency index of the judgment matrix; The judgment matrix is ​​normalized to obtain the weight of each evaluation factor.

8. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The process of optimizing the dimensional parameters of the selected transmission line foundation type using the genetic algorithm includes: Setting optimization objectives, wherein the optimization objectives include minimizing foundation settlement and maximizing foundation bearing capacity; Collecting initial size parameters of the transmission line foundation type and evaluation factors of the target transmission line foundation, and constructing an evaluation function in combination with the optimization objective; The initial size parameter is expressed as a gene code, and an initial population is randomly generated; The roulette wheel selection method is used to determine the next generation of parents, and a crossover operation is performed to generate a new generation of size parameter individuals, and the size parameters are randomly mutated to increase the diversity of the optimization search; Repeat the crossover and random mutation process until the preset number of iterations is met; The fitness value of each size parameter individual is calculated according to the evaluation function to obtain the size parameter solution with the highest fitness value.

9. The intelligent optimization design platform for power transmission line foundation based on multi-objective algorithm according to claim 1 is characterized in that: The process of obtaining the optimal material selection ratio includes: Setting objective functions and constraints, wherein the objective functions include maximizing comprehensive material performance and minimizing overall material costs; and the constraints include the bearing capacity requirements of the transmission line foundation; Collecting technical parameters of transmission line foundation materials, including compressive strength and tensile strength; A linear programming model is constructed to obtain a material ratio scheme for the transmission line foundation based on the objective function, the constraint conditions and the technical parameters of the basic materials.

Images