Digital modeling steel structure multi-dimensional collaborative optimization design method and system

Abstract

The invention discloses a digital modeling steel structure multi-dimensional collaborative optimization design method and system, belongs to the technical field of steel structure design, and aims to solve the problems that multi-dimensional comprehensive consideration and automatic optimization tools are lacked, and complex multi-objective optimization requirements are difficult to quickly respond. Comprising the steps of establishing a full-parameterized digital model containing construction process parameters and environmental protection indexes, constructing a multi-objective evaluation system of structural safety, economical efficiency, construction feasibility and environmental influence, performing automatic optimization by adopting an improved multi-objective evolutionary algorithm, selecting 10 groups of candidate schemes, generating a visual interface, supporting human-computer interaction decision, and generating an optimization report. According to the method, multi-dimensional collaborative optimization is realized by constructing a multi-target evaluation system of structural safety, economy, construction feasibility and environmental influence, construction process parameters and environmental protection indexes are integrated through the digital modeling unit, it is ensured that factors of all parties are comprehensively considered in design decision, and the design efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of steel structure design, and specifically relates to a multi-dimensional collaborative optimization design method and system for steel structures based on digital modeling. Background Art

[0002] With the rapid development of my country's construction industry, new materials and technologies are increasingly being used. Steel structures, owing to their advantages such as structural stability, ease of installation, and excellent seismic resistance, are gaining widespread application. Compared with traditional concrete and masonry structures, steel structures are particularly suitable for the construction of large-span, super-high-rise buildings due to their light weight. They also offer advantages such as relatively short construction periods and recyclable materials. In the petrochemical, power, and logistics sectors, steel plant buildings and equipment supports are highly sought after for their flexibility and reusability. With advances in materials science and information technology, steel structure design is evolving towards higher performance, lower costs, and greater sustainability. However, in the actual design process, architects and engineers often face multi-dimensional optimization challenges, such as how to reduce costs, minimize energy consumption, and ensure structural stability and safety.

[0003] Steel structures are typically designed and optimized using methods based on computer-aided design (CAD) software. These methods assess the stability and safety of structures by setting different design parameters and applying finite element analysis (FEA) technology for performance simulation. However, traditional design methods focus solely on structural safety or economic efficiency, lacking comprehensive consideration of dimensions such as construction feasibility and environmental impact (such as carbon emissions). Furthermore, they lack automated optimization tools and rely on trial and error based on engineers' experience, making it difficult to quickly respond to complex multi-objective optimization needs and unable to effectively adapt to complex and changing engineering design requirements and environmental conditions.

[0004] Therefore, a digitally modeled multi-dimensional collaborative optimization design method and system for steel structures is needed to solve the problems in existing technologies such as the lack of multi-dimensional comprehensive considerations and the lack of automated optimization tools, making it difficult to quickly respond to complex multi-objective optimization needs. Summary of the Invention

[0005] The purpose of the present invention is to provide a digitally modeled multi-dimensional collaborative optimization design method and system for steel structures to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a digitally modeled multi-dimensional collaborative optimization design method for steel structures, comprising:

[0007] S1. Establish a fully parametric digital model including construction process parameters and environmental protection indicators;

[0008] S2. Construct a multi-objective evaluation system for structural safety, economy, construction feasibility, and environmental impact;

[0009] S3, using the improved multi-objective evolutionary algorithm for automatic optimization to select 10 groups of candidate solutions;

[0010] S4. Generate a visual interface and support human-computer interaction decision-making, and generate an optimization report.

[0011] It should be noted that the step S1 includes establishing a geometry-topology-property integrated model of the steel structure based on BIM technology, supporting dynamic binding of the size, material, and connection parameters of beams, columns, and node components;

[0012] Construction process parameters are introduced, and a built-in construction constraint rule library is included, including hoisting constraints and welding specifications. Hoisting constraints include the association of tower crane rated load, arm length, operating radius parameters with component weight and lifting point location; welding specifications include the binding of groove angle, weld grade, welder efficiency parameters with node structure;

[0013] Integrated environmental indicators include carbon emission parameters and resource consumption parameters. Carbon emission parameters include coupling with the life cycle assessment database to assign a carbon emission factor to each material and process. Resource consumption parameters include defining material recovery rates and renewable material ratio indicators.

[0014] Through deep integration with finite element analysis software through API interface, meshing, solution calculation and result return are automatically triggered after parameter modification.

[0015] It is further worth noting that step S2 includes constructing a structural safety target system, constructing an economic evaluation target system, constructing a construction feasibility evaluation target system, constructing an environmental impact assessment target system, and integrating a multi-target evaluation system. The structural safety target system, the economic evaluation target system, the construction feasibility evaluation target system, and the environmental impact assessment target system are integrated into a single multi-target evaluation system. The weighted summation method is used to integrate the multi-target functions into a single fitness function:

[0016] F total =w1F1+w2F2+w3F3+w4F4

[0017] Among them, w i is a dynamic weight, satisfying w1+w2+w3+w4=1,

[0018] In the conceptual design stage, w1=0.6, w2=0.3, w3=0.1, w4=0,

[0019] During the detailed design phase, w1=0.4, w2=0.3, w3=0.2, w4=0.1.

[0020] It should be further explained that step S3 includes adopting the improved NSGA-III algorithm, introducing a reference point mechanism, generating a uniformly distributed Pareto front solution in the hyperdimensional target space, and avoiding the clustering phenomenon of the solution set of the traditional algorithm;

[0021] The target weight is used as the algorithm input to dynamically adjust the fitness function during the evolution process;

[0022] Train the random forest model, predict the convergence speed of different parameter combinations based on historical optimization cases, and prioritize high-potential individuals;

[0023] Filter out the solutions that do not meet the hard constraints, retain the Pareto frontier solutions, and select 10 groups of candidate solutions.

[0024] As a preferred embodiment, step S4 includes presenting the optimization results in a three-dimensional scatter plot, where the axes correspond to safety, economy, and environment, respectively, and supports engineers to select a preferred solution by rotating the view;

[0025] Adjust target weights in real time and observe the dynamic offset of solution sets;

[0026] Developing virtual scenes based on the Unity engine allows engineers to check the lifting sequence and welding work space from a first-person perspective, simulate the impact of extreme weather on construction, and automatically adjust the work sequence;

[0027] Generate an optimization report including a parametric model, carbon inventory, and construction simulation video.

[0028] Furthermore, the invention concept of proposing a multi-dimensional collaborative optimization design method for steel structures using digital modeling is the same as that of the invention. This solution proposes a multi-dimensional collaborative optimization design system for steel structures using digital modeling, including:

[0029] Digital modeling unit, used to build a digital foundation for steel structure design and achieve dynamic association between design parameters and performance indicators;

[0030] The BIM parametric modeling module, based on the BIM platform, creates a 3D geometric model of the steel structure and supports dynamic binding of topological relationships, material properties, and load condition parameters. Digital design allows engineers to automatically update associated components by adjusting a single variable, reducing repetitive modeling work.

[0031] Construction process database, with a built-in construction constraint rule library, including lifting equipment parameters, welding process specifications, and on-site assembly sequence data;

[0032] A multi-dimensional objective function construction unit drives the collaborative optimization of multi-dimensional objectives through algorithms, replacing manual trial and error.

[0033] Safety objective function construction module defines stress ratio and displacement limit constraints based on FEA results to ensure that the structure meets regulatory requirements;

[0034] The economic objective function construction module establishes a cost model, including material unit price, processing fee, and transportation fee;

[0035] The construction feasibility objective function building module quantifies indicators such as the number of hoisting times, welding workload, and construction period;

[0036] An environmental impact objective function building module, coupled with a life cycle assessment database, calculates the carbon footprint of material production, construction, and demolition stages;

[0037] Dynamic adjustment module, introducing reference point mechanism, generates uniformly distributed Pareto front solutions in hyperdimensional objective space, avoiding the clustering phenomenon of solutions in traditional genetic algorithms in multi-objective optimization;

[0038] The multi-objective optimization module uses the improved NSGA-III algorithm to achieve collaborative optimization of structural safety, economy, construction feasibility, and environmental impact, and generates the Pareto frontier;

[0039] The visual decision-making module presents the optimization results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment respectively. It supports engineers to select preferred solutions by rotating the view and output an optimization report.

[0040] Compared with the prior art, the digital modeling steel structure multi-dimensional collaborative optimization design method and system provided by the present invention have at least the following beneficial effects:

[0041] By building a multi-objective evaluation system for structural safety, economy, construction feasibility, and environmental impact, multi-dimensional collaborative optimization is achieved. Construction process parameters and environmental indicators are integrated through digital modeling units to ensure that all aspects of factors are taken into full consideration in design decisions. Design efficiency is significantly improved through automated optimization and algorithm-driven design. Through a visual decision-making platform, engineers can interactively select the optimal solution, adjust target weights, and observe the dynamic offset of the solution set. VR construction simulation supports engineers in verifying decisions in a virtual environment, improving the accuracy and efficiency of decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of the digital modeling steel structure multi-dimensional collaborative optimization design method of the present invention;

[0043] Figure 2 This is a structural block diagram of the digitally modeled steel structure multi-dimensional collaborative optimization design system of the present invention. DETAILED DESCRIPTION

[0044] The present invention will be further described below with reference to the embodiments.

[0045] Reference Figure 1 As shown, the present invention provides a multi-dimensional collaborative optimization design method for steel structures based on digital modeling, including:

[0046] S1. Establish a fully parametric digital model including construction process parameters and environmental protection indicators;

[0047] S2. Construct a multi-objective evaluation system that includes structural safety, economy, construction feasibility, and environmental impact;

[0048] S3, using the improved multi-objective evolutionary algorithm for automatic optimization to select 10 groups of candidate solutions;

[0049] S4. Generate a visual interface and support human-computer interaction decision-making, and generate an optimization report.

[0050] Among them, step S1 includes establishing a geometry-topology-property integrated model of the steel structure based on BIM technology, supporting dynamic binding of parameters such as the size (such as section height h, flange width b), material, and connection method of components such as beams, columns, and nodes;

[0051] Construction process parameters are introduced, and a built-in construction constraint rule library is included, including lifting constraints and welding specifications. Lifting constraints include parameters such as tower crane rated load, arm length, and operating radius, which are associated with component weight and lifting point location; welding specifications include parameters such as groove angle, weld grade, and welder efficiency, which are bound to node structure;

[0052] Integrated environmental indicators include carbon emission parameters and resource consumption parameters. Carbon emission parameters include coupling the life cycle assessment (LCA) database to assign carbon emission factors to each material and process; resource consumption parameters include defining indicators such as material recycling rate and proportion of renewable materials;

[0053] Through the API interface, it is deeply integrated with the finite element analysis (FEA) software to automatically trigger meshing, solution calculation and result return (such as stress and displacement) after parameter modification.

[0054] Step S2 includes constructing a structural safety target system, constructing an economic evaluation target system, constructing a construction feasibility evaluation target system, constructing an environmental impact assessment target system, and integrating a multi-target evaluation system. The method for constructing the structural safety target system is as follows:

[0055] Based on the finite element analysis (FEA) results, the vonMises stress of key parts of the structure (such as beam-column nodes and support connections) is calculated and compared with the material allowable stress σ allowable By contrast, the stress ratio σ / σ is defined allowable ;

[0056] Calculate the maximum displacement of the structure δ and the code limit δ limit The ratio δ / δ limit ;

[0057] Evaluate the critical load P of the structure through eigenvalue buckling analysis or nonlinear stability analysis cr and design load P design The ratio P cr / P design ;

[0058] Define the security objective function:

[0059]

[0060] When F1≤1.0, the structure meets the safety requirements;

[0061] The method of constructing the economic evaluation target system is as follows:

[0062] Based on material unit price C steel and total weight M total , calculate the material cost C material =C steel ×M total ;

[0063] According to the complexity of the component (such as welding length L weld 、Number of bolts bolt ) and unit processing rate (such as welding rate C weld 、Bolt rate C bolt ), calculate the processing cost C fabrication =L weld ×C weld +N bolt ×C bolt ;

[0064] According to the component volume V member and transport distance D transport , calculate the transportation cost C transport =V member ×D transport ×C unit ;

[0065] Define the economic objective function:

[0066] F2=C material +C fabrication +C transpor t

[0067] Methods for constructing a construction feasibility evaluation target system:

[0068] According to the component weight M member and tower crane rated load M crane , calculate the number of hoisting times

[0069] According to the weld length L weld and welding efficiency E weld , calculate welding hours

[0070] Based on the Critical Path Method (CPM), simulate the construction sequence and calculate the total construction period E weld ;

[0071] Define the construction feasibility objective function;

[0072]

[0073] Among them, N max is the maximum number of lifting times allowed, T capacity T is the maximum daily working hours of the welding team. limit The contract duration;

[0074] Methods for constructing an environmental impact assessment target system:

[0075] Coupled with the life cycle assessment (LCA) database, calculate the material production E material 、Construction E construction 、Remove E demolition The total carbon emissions of the stage E total =E material +E constructoin +E demolition ;

[0076] Define the material recovery rate R recycle and the proportion of renewable materials R renewable , computing resource efficiency index F resource =R recycle ×R renewable ;

[0077] Define the environmental impact objective function:

[0078]

[0079] Among them, E baseline Benchmark carbon emissions for the industry;

[0080] Integrate into a multi-objective evaluation system, use the weighted summation method to integrate the multi-objective functions into a single fitness function:

[0081] F total =w1F1+w2F2+w3F3+w4F4

[0082] Among them, wi is a dynamic weight, satisfying w1+w2+w3+w4=1,

[0083] In the conceptual design stage, w1=0.6, w2=0.3, w3=0.1, w4=0,

[0084] During the detailed design phase, w1=0.4, w2=0.3, w3=0.2, w4=0.1.

[0085] Among them, step S3 includes adopting the improved NSGA-III algorithm, introducing the reference point mechanism, generating uniformly distributed Pareto front solutions in the hyperdimensional target space, and avoiding the clustering phenomenon of the solution set of the traditional algorithm;

[0086] The target weight is used as the algorithm input to dynamically adjust the fitness function during the evolution process;

[0087] Train the random forest model, predict the convergence speed of different parameter combinations based on historical optimization cases, and prioritize high-potential individuals;

[0088] Filter out the solutions that do not meet the hard constraints, retain the Pareto frontier solutions, and select 10 groups of candidate solutions.

[0089] It is understood that step S4 includes presenting the optimization results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment, respectively, to support engineers in selecting a preferred solution by rotating the view;

[0090] Adjust target weights in real time and observe the dynamic offset of solution sets;

[0091] Developing virtual scenes based on the Unity engine allows engineers to check the lifting sequence and welding work space from a first-person perspective, simulate the impact of extreme weather on construction, and automatically adjust the work sequence;

[0092] Generate an optimization report including a parametric model, carbon inventory, and construction simulation video.

[0093] The above work process shows that: by constructing a multi-objective evaluation system for structural safety, economy, construction feasibility, and environmental impact, multi-dimensional collaborative optimization is achieved; by integrating construction process parameters and environmental indicators through digital modeling units, it is ensured that all factors are comprehensively considered in design decisions; and through automated optimization and algorithm-driven design, design efficiency is significantly improved.

[0094] For further information, please refer to Figure 2 As shown in FIG, the invention concept of the multi-dimensional collaborative optimization design method of steel structure based on digital modeling is proposed. This solution proposes a multi-dimensional collaborative optimization design system for steel structure based on digital modeling, including:

[0095] Digital modeling unit, used to build a digital foundation for steel structure design and achieve dynamic association between design parameters and performance indicators;

[0096] The BIM parametric modeling module, based on the BIM platform, establishes a 3D geometric model of the steel structure, supporting dynamic binding of parameters such as topological relationships (such as beam-column connection nodes), material properties (such as steel strength grade), and load conditions (such as wind loads and seismic effects). Digital design allows engineers to automatically update associated components (such as connection plates and bolt layouts) by adjusting a single variable (such as beam section height), reducing repetitive modeling work.

[0097] Construction process database, with a built-in construction constraint rule library, including data such as lifting equipment parameters (such as tower crane lifting weight and arm length), welding process specifications (such as groove form and weld grade), and on-site assembly sequence;

[0098] Multi-dimensional objective function construction unit, which uses algorithms to drive multi-dimensional objective collaborative optimization, replacing manual trial and error. It includes safety objective function construction modules, economic objective function construction modules, construction feasibility objective function construction modules, and environmental impact objective function construction modules;

[0099] The safety objective function construction module defines constraints such as stress ratio and displacement limit based on FEA results to ensure that the structure meets regulatory requirements;

[0100] The economic objective function construction module establishes a cost model, including material unit price, processing fee, and transportation fee;

[0101] The construction feasibility objective function building module quantifies indicators such as the number of hoisting times, welding workload, and construction period;

[0102] An environmental impact objective function building module, coupled with a life cycle assessment (LCA) database, calculates the carbon footprint of material production, construction, and demolition stages;

[0103] Dynamic adjustment module, introducing a reference point mechanism, generates uniformly distributed Pareto front solutions in the hyperdimensional target space, avoiding the clustering of solutions in traditional genetic algorithms in multi-objective optimization; and automatically adjusts the target priority according to the design stage;

[0104] The multi-objective optimization module uses the improved NSGA-III algorithm to achieve collaborative optimization of structural safety, economy, construction feasibility, and environmental impact, and generates a Pareto frontier solution.

[0105] The visual decision-making module presents the optimization results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment respectively. It supports engineers to select preferred solutions by rotating the view and output an optimization report.

[0106] The usage process of the digitally modeled steel structure multi-dimensional collaborative optimization design system is as follows:

[0107] Step 1: Based on the BIM platform, users use the BIM parametric modeling module to create a 3D geometric model of the steel structure. This model is used to call the built-in construction constraint rule library from the construction process database, including data such as lifting equipment parameters, welding process specifications, and on-site assembly sequence, and associate it with the components in the BIM model.

[0108] Step 2: Through the multi-dimensional objective function construction unit, a multi-objective evaluation system of structural safety, economy, construction feasibility and environmental impact is automatically constructed. Each sub-module is responsible for defining specific evaluation objectives.

[0109] Step 3: The dynamic adjustment module automatically adjusts the target priority according to the design stage and dynamically adjusts the weights in the fitness function;

[0110] Step 4: The multi-objective optimization module uses the improved NSGA-III algorithm to generate uniformly distributed Pareto front solutions in the hyperdimensional objective space and ultimately selects 10 groups of candidate solutions;

[0111] Step 5: The visualization decision module presents the optimized results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment, respectively. Users can select preferred solutions by rotating the view, adjust target weights in real time, and observe the dynamic offset of the solution set.

[0112] Step 6: Generate an optimization report containing a parametric model, carbon emission inventory, and construction simulation video based on the user's preferred solution.

[0113] In summary, the advantages of the present invention are: by constructing a multi-objective evaluation system for structural safety, economy, construction feasibility, and environmental impact, multi-dimensional collaborative optimization is achieved; construction process parameters and environmental indicators are integrated through digital modeling units to ensure that design decisions take all factors into full consideration; through automated optimization and algorithm-driven, design efficiency is significantly improved; through a visual decision-making platform, engineers can interactively select the optimal solution, adjust target weights, and observe the dynamic offset of the solution set; VR construction simulation supports engineers in verifying decisions in a virtual environment, thereby improving the accuracy and efficiency of decisions.

[0114] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital modeling steel structure multi-dimensional collaborative optimization design method, characterized by: include: S1. Establish a fully parametric digital model including construction process parameters and environmental protection indicators; S2. Construct a multi-objective evaluation system for structural safety, economy, construction feasibility, and environmental impact; S3, using the improved multi-objective evolutionary algorithm for automatic optimization to select 10 groups of candidate solutions; S4. Generate a visual interface and support human-computer interaction decision-making, and generate an optimization report.

2. The digital modeling steel structure multi-dimensional collaborative optimization design method according to claim 1 is characterized by: The step S1 includes establishing a geometry-topology-attribute integrated model of the steel structure based on BIM technology, supporting dynamic binding of the size, material, and connection method parameters of beams, columns, and node components; Construction process parameters are introduced, and a built-in construction constraint rule library is included, including hoisting constraints and welding specifications. Hoisting constraints include the association of tower crane rated load, arm length, operating radius parameters with component weight and lifting point location; welding specifications include the binding of groove angle, weld grade, welder efficiency parameters with node structure; Integrated environmental indicators, including carbon emission parameters and resource consumption parameters. The carbon emission parameters include coupling the life cycle assessment database to assign a carbon emission factor to each material and process. Resource consumption parameters include defining material recycling rates and renewable material proportion indicators; Through deep integration with finite element analysis software through API interface, meshing, solution calculation and result return are automatically triggered after parameter modification.

3. The digital modeling steel structure multi-dimensional collaborative optimization design method according to claim 1 is characterized by: The step S2 includes constructing a structural safety target system, constructing an economic evaluation target system, constructing a construction feasibility evaluation target system, constructing an environmental impact evaluation target system, and integrating a multi-target evaluation system. The structural safety target system, the economic evaluation target system, the construction feasibility evaluation target system, and the environmental impact evaluation target system are integrated into a single multi-target evaluation system. The weighted summation method is used to integrate the multi-target functions into a single fitness function: F total =w1F1+w2F2+w3F3+w4F4 Among them, w i is a dynamic weight, satisfying w1+w2+w3+w4=1, In the conceptual design stage, w1=0.6, w2=0.3, w3=0.1, w4=0, During the detailed design phase, w1=0.4, w2=0.3, w3=0.2, w4=0.

1.

4. The digital modeling multi-dimensional collaborative optimization design method for steel structures according to claim 3 is characterized by: The step S3 includes adopting the improved NSGA-III algorithm, introducing a reference point mechanism, generating a uniformly distributed Pareto front solution in the hyperdimensional target space, and avoiding the clustering phenomenon of the solution set of the traditional algorithm; The target weight is used as the algorithm input to dynamically adjust the fitness function during the evolution process; Train the random forest model, predict the convergence speed of different parameter combinations based on historical optimization cases, and prioritize high-potential individuals; Filter out the solutions that do not meet the hard constraints, retain the Pareto frontier solutions, and select 10 groups of candidate solutions.

5. The digital modeling steel structure multi-dimensional collaborative optimization design method according to claim 4 is characterized by: Step S4 includes presenting the optimization results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment, respectively, to support engineers in selecting a preferred solution by rotating the view; Adjust target weights in real time and observe the dynamic offset of solution sets; Developing virtual scenes based on the Unity engine allows engineers to check the lifting sequence and welding work space from a first-person perspective, simulate the impact of extreme weather on construction, and automatically adjust the work sequence; Generate an optimization report including a parametric model, carbon inventory, and construction simulation video.

6. The digital modeling steel structure multi-dimensional collaborative optimization design system is used to implement the digital modeling steel structure multi-dimensional collaborative optimization design method according to any one of claims 1 to 5, characterized in that: include: Digital modeling unit, used to build a digital foundation for steel structure design and achieve dynamic association between design parameters and performance indicators; BIM parametric modeling module, based on the BIM platform, establishes a 3D geometric model of the steel structure and supports dynamic binding of topological relationships, material properties, and load condition parameters; Digital design allows engineers to automatically update associated components by adjusting a single variable, reducing repetitive modeling work; Construction process database, with a built-in construction constraint rule library, including lifting equipment parameters, welding process specifications, and on-site assembly sequence data; The multi-dimensional objective function construction unit uses algorithms to drive multi-dimensional objective collaborative optimization, replacing manual trial and error. It includes a safety objective function construction module, an economic objective function construction module, a construction feasibility objective function construction module, and an environmental impact objective function construction module. Safety objective function construction module defines stress ratio and displacement limit constraints based on FEA results to ensure that the structure meets regulatory requirements; The economic objective function construction module establishes a cost model, including material unit price, processing fee, and transportation fee; The construction feasibility objective function building module quantifies indicators such as the number of hoisting times, welding workload, and construction period; An environmental impact objective function building module, coupled with a life cycle assessment database, calculates the carbon footprint of material production, construction, and demolition stages; Dynamic adjustment module, introducing reference point mechanism, generates uniformly distributed Pareto front solutions in hyperdimensional objective space, avoiding the clustering phenomenon of solutions in traditional genetic algorithms in multi-objective optimization; The multi-objective optimization module uses the improved NSGA-III algorithm to achieve collaborative optimization of structural safety, economy, construction feasibility, and environmental impact, and generates the Pareto frontier; The visual decision-making module presents the optimization results in a three-dimensional scatter plot, with the axes corresponding to safety, economy, and environment respectively. It supports engineers to select preferred solutions by rotating the view and output an optimization report.

Images