Green low-carbon power transmission tower multi-objective intelligent optimization design system
Patent Information
- Application Number
- CN202611207639.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-11
- Publication Date
- 2026-10-30
AI Technical Summary
[0004]本发明的目的在于解决传统铁塔设计安全、造价、碳排放指标难以协同均衡、优化求解效率低的问题，而提出面向绿色低碳的输电铁塔多目标智能优化设计系统
本发明通过多源数据标准化处理与铁塔构件分层编码，统一整合气象、地形、材料及碳排放数据，压缩无效设计解空间，提升建模基础数据的完整性与可信度；
Smart Images
Figure CN123013674A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power transmission tower structure optimization and low-carbon engineering technology, specifically a multi-objective intelligent optimization design system for power transmission towers oriented towards green and low-carbon technologies. Background Technology
[0002] Transmission towers are the core load-bearing components of high-voltage transmission lines. Traditional tower design processes often employ a single-index, step-by-step verification model. Designers prioritize meeting structural safety code limits and then roughly estimate steel usage, lacking a unified quantitative framework to coordinate the three core indicators of safety, cost, and carbon emissions. Existing design methods can only calculate component load-bearing capacity and project cost separately, without establishing a quantitative calculation system for carbon emissions throughout the entire life cycle. It is difficult to quantify the carbon footprint of all stages, from steel selection and structural lightweighting to later operation and maintenance and recycling. At the same time, existing optimization algorithms do not consider the inherent conflict and balance among safety, economy, and low-carbon objectives, and lack a collaborative solution mechanism adapted to the mixed variables of tower topology and cross-section, making it impossible to output a multi-objective equilibrium optimal solution. This design model easily leads to uneven distribution of component safety margins and large redundancy in steel materials, making it difficult to fully explore the carbon reduction potential brought about by structural lightweighting and failing to meet the current development needs of green and low-carbon power grid construction.
[0003] To address the aforementioned shortcomings, a technical solution is provided. Summary of the Invention
[0004] The purpose of this invention is to solve the problems of difficulty in achieving a coordinated balance between safety, cost, and carbon emission indicators in traditional power transmission tower design, as well as the low efficiency of optimization solutions. In response, this invention proposes a multi-objective intelligent optimization design system for green and low-carbon power transmission towers.
[0005] The objective of this invention can be achieved through the following technical solutions: A multi-objective intelligent optimization design system for green and low-carbon power transmission towers includes: Multi-source data acquisition module: Collects multi-source data on meteorology, topography, steel mechanics and carbon emissions and performs standardized preprocessing; encodes mixed variables for the layered components of the iron tower; and constructs a structural design gene matrix with topological constraints. Finite element stress analysis module: Reads the structural design gene matrix, generates a three-dimensional finite element model of the transmission tower, completes multi-condition stress solution, and calculates the component safety margin and overall safety uniformity index; Multi-objective collaborative optimization solution module: Constructs a coupled model of three objectives: safety, economy, and low carbon, and combines the Kriging surrogate model with the objective conflict sensitivity genetic algorithm for iteration to output the Pareto optimal solution set; Full life cycle low-carbon accounting module: calculates carbon emissions for each optimization scheme in stages, introduces weight reduction and material substitution coefficients to correct carbon emissions, and updates solution set attribute parameters; 3D visualization design module: Reconstructs the 3D model of the tower based on the optimized solution set, renders layered cloud maps of safety, cost, and carbon emissions, calculates multi-objective decision distances to screen the optimal compromise solution, and encrypts and outputs design data packages compatible with engineering software.
[0006] Furthermore, the specific operation steps of the multi-source data acquisition module include: Collect annual and hourly historical time-series data of wind load, ice thickness time series at different return periods, and DEM data of topographic elevation along the line in the corridor area of the target transmission line, and import them into a standardized preprocessing unit to complete missing value completion, outlier data removal, and dimension normalization. It constitutes a material performance parameter library, and is equipped with a carbon emission factor database covering the entire process of steel smelting, rolling, anti-corrosion coating, recycling and regeneration; Space meteorological load data, topographic parameters, material mechanical parameters, and carbon emission factor parameters are spliced and fused to construct a dimensionally aligned, unified data vector across the entire domain. Each dimension parameter of the vector carries a source identifier and confidence weight. When there is a conflict between multiple sources, the data with the higher confidence weight is given priority, and the conflict identifier is recorded for subsequent verification. The transmission tower is disassembled into three levels: tower leg section, tower body section, and tower head section. A set of topological variables is defined for each section, and discrete-continuous hybrid variable coding is performed on the load-bearing components.
[0007] Furthermore, the specific operation steps of the multi-source data acquisition module also include: A composite performance evaluation index for steel is constructed by introducing a material carbon strength weighting coefficient and combining the steel yield strength and the carbon emission factor per unit mass of steel. The composite performance evaluation index of steel is used as a material coding segment to generate a structural design gene matrix. Each row of the gene matrix corresponds to a complete design scheme of the iron tower, and each column corresponds to the topology code of each section, the component section code, the material code, and the connection node code in turn. A topological adjacency constraint matrix is added to the outside of the gene matrix. After encoding, a structured structural design gene matrix is output, which serves as the driving data source for finite element modeling.
[0008] Furthermore, the specific operation steps of the finite element stress analysis module are as follows: The structural design gene matrix generated by the multi-source data acquisition module is read, and the topology code, section code, material code, and node connection code are analyzed based on the parametric modeling engine to generate a three-dimensional pole system finite element model of the power transmission tower. The static load case analysis, overall stability buckling analysis, and dynamic response analysis under pulsating wind excitation are carried out in sequence to solve and output the axial force, end moment, slenderness ratio, nodal displacement, and stability coefficient of all members. Distinguish between four stress forms of members: axial tension, axial compression, tension-bending, and compression-bending; solve the ultimate bearing capacity of members based on the stress type and the corresponding section stability coefficient and bearing capacity calculation formula; define the safety factor of a single member by combining the ratio of the absolute value of the design value of the internal force under actual action; and convert the safety factor of a single member into the safety margin of the member. Kriging interpolation is used to generate the global safety margin field matrix, and the overall structural safety uniformity index is calculated.
[0009] Furthermore, the specific operation steps of the multi-objective collaborative optimization solution module are as follows: A safety objective function is constructed using a safety uniformity index; the construction economic objective function is obtained by summing the costs of steel materials, component cutting and welding, and land and water transportation for all components of the entire tower; and a low-carbon objective function is constructed that includes carbon emissions at each stage of the entire life cycle, from production and construction to operation and maintenance and recycling deduction. By combining the safety objective function, the economic construction objective function, and the low-carbon objective function, a three-objective coupled optimization model is constructed, and the Kriging surrogate model combined with the genetic algorithm is used to find the optimal solution. Calculate the target conflict sensitivity factor, and adaptively adjust the population crossover and mutation probabilities based on the conflict sensitivity factor; When there are no updates to the Pareto front for 20 consecutive generations and the change in the value of each objective function is lower than the preset threshold, convergence is determined, and the entire Pareto optimal solution set is output.
[0010] Furthermore, the specific operation steps of the full life cycle low-carbon accounting module are as follows: For each set of tower design schemes in the Pareto optimal solution set, retrieve the component-level carbon emission inventory database; For the component transportation process, the complete transportation route is divided into multiple segments, including highway transportation, ordinary road transportation, and waterway transportation. The carbon emissions of the component transportation process are calculated using the segmented integral method. A carbon elasticity adjustment coefficient is introduced, and the carbon emissions during the operation and maintenance phase of the tower are corrected by combining the overall relative weight reduction ratio of the tower. Introducing a material substitution ratio coefficient, the replacement ratio of ordinary steel with low-carbon high-strength steel and recycled steel in the scheme is determined; Calculate the carbon emission difference of alternative materials, and determine whether to implement total carbon emission deduction or offset the carbon emission savings corresponding to the reduction in steel consumption after substitution with the carbon emission increase of the material itself based on the carbon emission difference. Complete the full life cycle carbon emission accounting for all schemes in the Pareto optimal solution set, and write the corrected carbon emission parameters back to the attributes of each scheme.
[0011] Furthermore, the specific operation steps of the 3D visualization design module are as follows: Read all design parameters of the Pareto optimal solution set after carbon emission correction, analyze the gene matrix based on the Unity3D engine to reconstruct the three-dimensional model of the tower, and allocate gradient colors according to the optimization focus to distinguish each scheme; set up multi-layer rendering layers that can be turned on and off and have adjustable transparency, and overlay a safety margin color cloud layer, a carbon emission value heat layer, and a construction cost distribution sensitivity layer. Construct a multi-objective decision distance index to calculate the Euclidean distance between each scheme and the ideal optimal solution, and select the equilibrium compromise scheme with the smallest distance; It encapsulates all parameters to generate AES-256 encrypted data packets, includes modification logs, outputs files compatible with multiple engineering drawing formats, and supports full-process data traceability.
[0012] Compared with the prior art, the beneficial effects of the present invention are: This invention integrates meteorological, topographical, material, and carbon emission data through multi-source data standardization processing and hierarchical coding of tower components, compresses the invalid design solution space, and improves the integrity and reliability of the basic modeling data. This invention uses a three-objective coupled optimization model and an objective conflict adaptive genetic algorithm to simultaneously consider safety, cost, and low-carbon requirements, and outputs a multi-objective equilibrium Pareto solution set, fully exploring the potential for lightweighting and carbon reduction. This invention utilizes refined carbon accounting throughout the entire lifecycle and layered 3D visualization rendering to intuitively compare the indicators of various schemes, automatically select the optimal balanced scheme, and realize the design, accounting, and output of carbon data. Figure 1 Integration enhances the efficiency of intelligent design for low-carbon steel towers. Attached Figure Description
[0013] Figure 1 This is the overall system block diagram of the present invention. Detailed Implementation
[0014] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0015] Example: like Figure 1 As shown, the multi-objective intelligent optimization design system for green and low-carbon power transmission towers includes a multi-source data acquisition module, a finite element stress analysis module, a multi-objective collaborative optimization solution module, a full life-cycle low-carbon accounting module, and a three-dimensional visualization design module.
[0016] Multi-source data acquisition module: Historical time-series data of wind load, ice thickness at different return periods, and DEM data of terrain elevation along the target transmission line corridor area were collected from measured data and archived meteorological stations. These data were then imported into a standardized preprocessing unit to complete missing value completion, outlier removal, and dimensional normalization. Specifically, missing value completion employed a multiple interpolation method, iteratively completing the missing data by constructing a regression model between the missing data and other complete data dimensions. Outlier removal used the Laida criterion to remove data points deviating from the mean by more than three standard deviations. Dimensional normalization employed the min-max standardization method, linearly mapping all data dimensions to the [0,1] interval. The system retrieves the yield strength, tensile strength, elastic modulus, and fatigue performance of steel structures, low-carbon high-strength steel, and low-carbon alloy steel to form a material performance parameter database. It is also equipped with a carbon emission factor database covering the entire process of steel smelting, rolling, anti-corrosion coating, and recycling. The carbon emission factor database adopts the Chinese life cycle basic database or industry standard database, such as the "Building Carbon Emission Calculation Standard". Space meteorological load data, topographic parameters, material mechanical parameters, and carbon emission factor parameters are spliced and fused to construct a dimensionally aligned, unified data vector across the entire domain. Each dimension of the vector carries a source identifier and a confidence weight. The confidence weight is assigned hierarchically based on the data source type: the confidence weight for measured meteorological station data is set to 0.95, for satellite remote sensing inversion data it is set to 0.85, for archived statistical data it is set to 0.75, and the industry standard recommended default value is set to 0.65. When there is a conflict between multiple sources of data, the one with the higher confidence weight is given priority, and the conflict identifier is recorded for subsequent verification. Implement layered coding for transmission towers: The transmission tower is broken down into three levels: tower leg section, tower body section, and tower head section. A set of topological variables is independently defined for each section, including topological selection variables such as the arrangement of web members, the angle of diagonal members, and the height of inter-section members. For each load-bearing component of the tower, a discrete-continuous hybrid variable coding is implemented. The discrete coding bits correspond to the national standard steel section type number, while the continuous coding bits are the section thickness fine-tuning factor. The section thickness fine-tuning factor ranges from 0.90 to 1.10, with a step size of 0.005. Multiplying the section thickness fine-tuning factor by the standard nominal section thickness yields the actual section thickness of the component, enabling fine-tuning of the section dimensions. Introducing a material carbon strength weighting factor Combined with the yield strength of steel Carbon emission factor per unit mass of steel Constructing evaluation indicators for composite steel properties: ,in, The value range is 0.6-1.4, with a default value of 1.0, and is set by the designer based on the low-carbon policy guidelines of the project location; Using this composite evaluation index as a material coding segment, a structural design gene matrix is generated. Each row of the gene matrix corresponds to a complete tower design scheme, and each column corresponds sequentially to the topology code, component section code, material code, and connection node code for each segment. A topological adjacency constraint matrix is added outside the gene matrix. Square formation, among which, The total number of tower members, matrix elements , Indicating rods With rods Connectable This indicates that the rods cannot be connected; The constraints include: the number of members connected to the same node does not exceed the preset maximum number, the angle between adjacent members is not less than the preset minimum allowable angle, the ratio of inter-joint height to inter-joint width is within a preset range, and no fourth member should converge at the intersection of intersecting diagonal members; for example, the number of members connected to the same node does not exceed 6, the angle between adjacent members is not less than 15°, and the ratio of inter-joint height to inter-joint width is between 0.5 and 2.0; the constraint matrix filters out invalid gene combinations that cannot be processed, assembled, or fail under stress in engineering, compresses the invalid solution space of the algorithm, and improves the computational efficiency of subsequent optimization iterations; After encoding, a structured structural design gene matrix is output, which serves as the driving data source for finite element modeling.
[0017] Finite element stress analysis module: The system reads the structural design gene matrix generated by the multi-source data acquisition module, and automatically parses the topology code, section code, material code, and node connection code based on the parametric modeling engine to automatically generate three-dimensional pole system finite element models of transmission towers in batches. The parametric modeling engine is implemented based on ANSYS APDL secondary development, using the structural design gene matrix as the input driving file and calling the ANSYS core solver to complete the preprocessing modeling. The model automatically matches the boundary conditions of regional wind load, icing load, and terrain-added bending moment load in the unified data vector. The finite element solver is invoked to sequentially perform static load case analysis, overall stability buckling analysis, and dynamic response analysis under pulsating wind excitation, and outputs the axial force, end moment, slenderness ratio, nodal displacement, and stability coefficient of all members. Based on the steel structure design code, four types of stress are distinguished in members: axial tension, axial compression, tension-bending, and compression-bending. The axial force and bending moment of the members are obtained from finite element analysis, and the slenderness ratio is calculated using the calculated length of the members. ,in, Calculate the length of the component. The radius of gyration of the component section; The ultimate bearing capacity of a component is calculated by matching the component's stress type with the corresponding section stability coefficient and bearing capacity calculation formula. The safety factor for a single structural member is defined as the ratio of the ultimate bearing capacity of the member to the absolute value of the design value of the actual acting internal force, i.e.: ,in, The design value of the internal force of the component under actual action; An exponential mapping rule is used to construct a safety margin mapping function, which transforms the safety factor into a range of values. Safety margin of components The calculation formula is: ,in, The target safety factor, as specified in the power transmission tower standard, is set to 2.0. The closer the safety margin value is to 1, the closer the component's safety factor is to the design objective. Using the three-dimensional coordinates of each component As interpolation nodes, the Kriging space interpolation algorithm is used to determine the safety margin of discrete components. Interpolation calculations are used to generate a safety margin field matrix that is continuously distributed throughout the entire tower area. The overall structural safety uniformity index is calculated by iterating through the margin values of all components. The calculation formula is as follows: ,in, This is the average safety margin for all components; The closer the safety uniformity index is to 1, the more uniform the safety margin distribution of each component of the tower.
[0018] Multi-objective collaborative optimization solution module: Safety uniformity index output by the finite element stress analysis module Constructing the structural safety objective function , A smaller value indicates better overall safety and uniformity of the tower. The economic objective function for construction is obtained by summing the costs of all steel materials used in the entire tower structure, the costs of component cutting and welding, and the costs of land and water transportation. Construct a low-carbon objective function that includes carbon emissions at each stage of the entire life cycle. The expression is: ,in, This refers to carbon emissions during the steel production and component manufacturing stages. Carbon emissions during the on-site assembly and construction phase of the iron tower. The carbon emissions during the long-term operation and maintenance inspection of the tower are calculated based on one inspection per year within the design service life of 50 years. This refers to the carbon offset generated from the recycling and reuse of steel after the steel towers are scrapped and dismantled. The steel recycling reduction factor is set to 0.6. United A three-objective coupled optimization model is established, and a hybrid optimization architecture combining a Kriging surrogate model and a genetic algorithm is used for iterative optimization. During the iteration process, non-dominated sorting is performed on individuals within the population to divide them into Pareto levels, and a conflict sensitivity factor is calculated between any two objectives. ,in, Indicates the first The degree of conflict between the two optimization objectives, b and c. These refer to two different objective functions in a three-objective coupled optimization model; This paper proposes an adaptive dynamic adjustment of the crossover and mutation probabilities of a genetic algorithm population based on a conflict sensitivity factor. Traditional adaptive genetic algorithms adjust probability parameters based on the difference between individual fitness and the average fitness of the population. This step further introduces a target conflict dimension: target conflict sensitivity. The higher the solution set region, i.e. In regions with low target conflict, higher crossover and mutation probabilities are configured to increase the sample search density; in regions with low target conflict, i.e. In regions where the mutation probability is low, the mutation probability is reduced to 0.01-0.02, preserving high-quality individuals; the specific adaptive rule is as follows: , ,in, , representing the baseline probability, These represent the maximum and minimum conflict sensitivity values in the current population, respectively. When the convergence criteria are met, i.e., there are no updates to the Pareto front for 20 consecutive generations and the change in the objective function is less than the preset convergence threshold, the complete Pareto optimal solution set is output.
[0019] Full life cycle low-carbon accounting module: For each set of tower design schemes in the Pareto optimal solution set, a pre-built component-level carbon emission inventory database is retrieved. Each specification of the tower in the database is bound to an independent and unique carbon emission identification code. The identification code is associated with four types of basic carbon emission parameters: tower material, cross-sectional dimensions, processing technology, and place of origin. For the inter-regional transportation of components, the complete transportation route is divided into multiple segments: highway transportation, ordinary road transportation, and waterway transportation. The carbon emissions of the component transportation segment are calculated using a segmented integral method. The calculation formula is: ,in, For the number of transport segments, For the first Segment route transportation distance, For the self-weight of a single component, For the first The carbon emission factor corresponding to each transportation mode is determined based on relevant industry standards, with typical values being: approximately [value missing] for road transportation. Railway transportation Waterway transportation ; Introducing a carbon elasticity adjustment coefficient Combined with the overall relative weight reduction ratio of the iron tower Dynamically adjust carbon emissions during the operation and maintenance of lightweight towers to eliminate the carbon emission reduction effect caused by the reduced inspection frequency after structural weight reduction: ,in, Actual carbon emissions from operation and maintenance after weight reduction correction; carbon elasticity adjustment coefficient The physical meaning is the percentage reduction in carbon emissions during the operation and maintenance phase corresponding to a 1% reduction in structural weight. The value range is 0.2-0.4, with a default value of 0.3; Further introduce material substitution ratio coefficient Determine the replacement ratio of ordinary steel with low-carbon high-strength steel and recycled steel in the plan; material replacement ratio coefficient. Defined as: ,in, This refers to the total mass of components made of low-carbon high-strength steel or recycled steel in the current design. The total mass of all components of the iron tower; Low-carbon high-strength steels (such as Q390, Q420, Q460, etc.) can reduce weight by 15%-30% compared to ordinary Q235 steel under the same load-bearing capacity, but their carbon emission factor per unit mass is higher, resulting in a significant difference in carbon emissions between the alternative materials. Calculate as follows: ,in, Carbon emission factor per unit mass of the benchmark material (ordinary Q235 steel) Carbon emission factor per unit mass of alternative materials (low-carbon high-strength steel or recycled steel); like Then deduct from total carbon emissions ;like In this case, a comprehensive assessment of the net carbon emission effect is required. Specifically, the carbon emission savings corresponding to the reduction in steel consumption after substitution should be offset against the increase in carbon emissions from the material itself. After completing the refined low-carbon accounting of all Pareto solutions, the corrected carbon emission data will be synchronously written back to the attribute parameters of each Pareto solution and pushed to the 3D visualization design module.
[0020] 3D visualization design module: The system reads all design parameters from the Pareto optimal solution set after carbon emission correction, and drives the 3D visualization engine to realize parametric 3D reconstruction modeling of the tower. The 3D visualization engine is developed based on the Unity3D platform. It takes the structural design gene matrix as input and automatically generates the 3D solid model of the tower by analyzing the spatial coordinates, cross-section type and material properties of each member. Different Pareto optimization schemes are assigned gradient color schemes for gradient color coding, including red to represent safety-oriented schemes, blue to represent economy-oriented schemes, and green to represent low-carbon-oriented schemes, so as to intuitively distinguish the optimization focus of various design schemes. A layer overlay rendering mechanism is established: a safety margin color cloud layer is sequentially overlaid on the 3D solid model of the iron tower, with red, yellow, and green gradients representing the margin from low to high; a carbon emission value heat map layer uses red, orange, and blue gradients to represent carbon emissions from high to low; a construction cost distribution sensitivity map layer uses warm and cool color gradients to represent costs from high to low; multiple layers are transparently blended and displayed, with the transparency of each layer adjustable from 0-100%, and any layer can be turned on or off individually to view the distribution pattern of a single indicator; Constructing a multi-objective decision distance index This is used to quantify the degree of deviation of any given set of solutions from the ideal optimal solution. ,in, The ideal optimal target values were obtained by optimizing the three objectives of safety, economy, and low carbon separately. Decision distance for traversing all Pareto solutions ,filter The compromise solution corresponding to the minimum value is the system's recommended optimal design solution. This solution has the closest combined Euclidean distance to the three ideal optimal points in the multi-objective space, representing the best compromise balance point among the three objectives. The system integrates the topology parameters, cross-sectional dimensions, material types, node parameters, safety margin data, carbon emission ledgers, and cost details of the recommended solutions into a unified encrypted design data package. This data package is encrypted using the AES-256 encryption algorithm and includes a complete parameter modification log, recording the timestamp of each parameter adjustment, the operator, and the values before and after the modification. It can interface with construction drawing automatic generation software to output fabrication and construction drawings, with output formats compatible with common engineering drawing formats such as DXF and DWG. Furthermore, it enables full-process data traceability and version tracking based on the data package identifier, ultimately forming a multi-dimensional decision support interface that combines visualization, multi-dimensional comparison, intelligent solution recommendation, and engineering implementation capabilities, completing the entire closed-loop process for low-carbon optimization design of transmission towers.
[0021] The above description is merely a specific embodiment of this application, but the scope of protection of this application 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 this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A multi-objective intelligent optimization design system for green and low-carbon power transmission towers, characterized in that, include: Multi-source data acquisition module: Collects multi-source data on meteorology, topography, steel mechanics and carbon emissions and performs standardized preprocessing; encodes mixed variables for the layered components of the iron tower; and constructs a structural design gene matrix with topological constraints. Finite element stress analysis module: Reads the structural design gene matrix, generates a three-dimensional finite element model of the transmission tower, completes multi-condition stress solution, and calculates the component safety margin and overall safety uniformity index; Multi-objective collaborative optimization solution module: Constructs a coupled model of three objectives: safety, economy, and low carbon, and combines the Kriging surrogate model with the objective conflict sensitivity genetic algorithm for iteration to output the Pareto optimal solution set; Full life cycle low-carbon accounting module: calculates carbon emissions for each optimization scheme in stages, introduces weight reduction and material substitution coefficients to correct carbon emissions, and updates solution set attribute parameters; 3D visualization design module: Reconstructs the 3D model of the tower based on the optimized solution set, renders layered cloud maps of safety, cost, and carbon emissions, calculates multi-objective decision distances to screen the optimal compromise solution, and encrypts and outputs design data packages compatible with engineering software.
2. The multi-objective intelligent optimization design system for green and low-carbon power transmission towers according to claim 1, characterized in that, The specific operation steps of the multi-source data acquisition module include: Collect annual and hourly historical time-series data of wind load, ice thickness time series at different return periods, and DEM data of topographic elevation along the line in the corridor area of the target transmission line, and import them into a standardized preprocessing unit to complete missing value completion, outlier data removal, and dimension normalization. It constitutes a material performance parameter library, and is equipped with a database of carbon emission factors for the entire process of steel smelting, rolling, anti-corrosion coating, recycling and regeneration; Space meteorological load data, topographic parameters, material mechanical parameters, and carbon emission factor parameters are spliced and fused to construct a dimensionally aligned, unified data vector across the entire domain. Each dimension parameter of the vector carries a source identifier and confidence weight. When there is a conflict between multiple sources, the data with the higher confidence weight is given priority, and the conflict identifier is recorded for subsequent verification. The transmission tower is disassembled into three levels: tower leg section, tower body section, and tower head section. A set of topological variables is defined for each section, and discrete-continuous hybrid variable coding is performed on the load-bearing components.
3. The multi-objective intelligent optimization design system for green and low-carbon power transmission towers according to claim 2, characterized in that, The specific operation steps of the multi-source data acquisition module also include: A composite performance evaluation index for steel is constructed by introducing a material carbon strength weighting coefficient and combining the steel yield strength and the carbon emission factor per unit mass of steel. The composite performance evaluation index of steel is used as a material coding segment to generate a structural design gene matrix. Each row of the gene matrix corresponds to a complete design scheme of the iron tower, and each column corresponds to the topology code of each section, the component section code, the material code, and the connection node code in turn. A topological adjacency constraint matrix is added to the outside of the gene matrix. After encoding, a structured structural design gene matrix is output, which serves as the driving data source for finite element modeling.
4. The multi-objective intelligent optimization design system for green and low-carbon transmission towers according to claim 1, characterized in that, The specific operation steps of the finite element stress analysis module are as follows: The structural design gene matrix generated by the multi-source data acquisition module is read, and the topology code, section code, material code, and node connection code are analyzed based on the parametric modeling engine to generate a three-dimensional pole system finite element model of the power transmission tower. The static load case analysis, overall stability buckling analysis, and dynamic response analysis under pulsating wind excitation are carried out in sequence to solve and output the axial force, end moment, slenderness ratio, nodal displacement, and stability coefficient of all members. Distinguish between four types of stress on a member: axial tension, axial compression, tension-bending, and compression-bending. The ultimate bearing capacity of a component is calculated by matching the cross-sectional stability coefficient and bearing capacity formula with the component stress type. The safety factor of a single component is defined by combining the ratio of the absolute value of the design value of the internal force under actual action, and the safety factor of a single component is converted into the safety margin of the component. Kriging interpolation is used to generate the global safety margin field matrix, and the overall structural safety uniformity index is calculated.
5. The multi-objective intelligent optimization design system for green and low-carbon transmission towers according to claim 1, characterized in that, The specific operation steps of the multi-objective collaborative optimization solution module are as follows: A safety objective function is constructed using a safety uniformity index; the construction economic objective function is obtained by summing the costs of steel materials, component cutting and welding, and land and water transportation for all components of the entire tower; and a low-carbon objective function is constructed that includes carbon emissions at each stage of the entire life cycle, from production and construction to operation and maintenance and recycling deduction. By combining the safety objective function, the economic construction objective function, and the low-carbon objective function, a three-objective coupled optimization model is constructed, and the Kriging surrogate model combined with the genetic algorithm is used to find the optimal solution. Calculate the target conflict sensitivity factor, and adaptively adjust the population crossover and mutation probabilities based on the conflict sensitivity factor; When there are no updates to the Pareto front for 20 consecutive generations and the change in the value of each objective function is lower than the preset threshold, convergence is determined, and the entire Pareto optimal solution set is output.
6. The multi-objective intelligent optimization design system for green and low-carbon transmission towers according to claim 1, characterized in that, The specific operation steps of the full life cycle low-carbon accounting module are as follows: For each set of tower design schemes in the Pareto optimal solution set, retrieve the component-level carbon emission inventory database; For the component transportation process, the complete transportation route is divided into multiple segments, including highway transportation, ordinary road transportation, and waterway transportation. The carbon emissions of the component transportation process are calculated using the segmented integral method. A carbon elasticity adjustment coefficient is introduced, and the carbon emissions during the operation and maintenance phase of the tower are corrected by combining the overall relative weight reduction ratio of the tower. Introducing a material substitution ratio coefficient, the replacement ratio of ordinary steel with low-carbon high-strength steel and recycled steel in the scheme is determined; Calculate the carbon emission difference of alternative materials, and determine whether to implement total carbon emission deduction or offset the carbon emission savings corresponding to the reduction in steel consumption after substitution with the carbon emission increase of the material itself based on the carbon emission difference. Complete the full life cycle carbon emission accounting for all schemes in the Pareto optimal solution set, and write the corrected carbon emission parameters back to the attributes of each scheme.
7. The multi-objective intelligent optimization design system for green and low-carbon transmission towers according to claim 1, characterized in that, The specific operation steps of the 3D visualization design module are as follows: Read all design parameters of the Pareto optimal solution set after carbon emission correction, analyze the gene matrix based on the Unity3D engine to reconstruct the three-dimensional model of the tower, and allocate gradient colors according to the optimization focus to distinguish each scheme; set up multi-layer rendering layers that can be turned on and off and have adjustable transparency, and overlay a safety margin color cloud layer, a carbon emission value heat layer, and a construction cost distribution sensitivity layer. Construct a multi-objective decision distance index to calculate the Euclidean distance between each scheme and the ideal optimal solution, and select the equilibrium compromise scheme with the smallest distance; It encapsulates all parameters to generate AES-256 encrypted data packets, includes modification logs, outputs files compatible with multiple engineering drawing formats, and supports full-process data traceability.