Steel structure system based on intelligent optimization and real-time monitoring

Abstract

The invention discloses a steel structure system based on intelligent optimization and real-time monitoring, and the system comprises a multi-objective optimization module which carries out multi-objective optimization design based on a practical application scene of a structure, and a BIM model integration module which integrates geometric and mechanical characteristics and state data. And the real-time monitoring module is used for acquiring state parameters such as stress, temperature and humidity of key nodes of the steel structure in real time. The multi-target optimization module generates a global optimal design scheme by using finite element analysis and a multi-target optimization algorithm, the BIM model serves as a core platform of design, construction and operation and maintenance, and the real-time monitoring module realizes dynamic feedback of a structure state through a sensor network. The safety and accuracy of steel structure design are improved, the service life of the structure is prolonged, the maintenance cost is reduced, and the method is suitable for bridges, buildings and other complex steel structure projects.

Description

Technical Field

[0001] The present invention relates to the technical field of steel structure optimization design, and particularly to a steel structure system based on intelligent optimization and real-time monitoring. The present invention integrates multi-objective optimization algorithms, BIM models, and sensing technologies. Background Art

[0002] With the rapid development of social economy, steel structures are widely used in engineering projects such as bridges, factories, and high-rise buildings due to their advantages of light weight, high strength, short construction period, and recyclability. However, traditional steel structure design and construction methods have many deficiencies in practical applications.

[0003] Traditional steel structure construction relies on manual experience for component manufacturing and on-site assembly, resulting in low precision and low efficiency during the construction process. At the same time, real-time monitoring technology has not been introduced to dynamically manage key nodes during the construction process, making it easy for construction deviations to occur due to uncontrollable factors, increasing the quality risk and cost of the project. In addition, the degree of modularization and standardization of components is relatively low, unable to achieve efficient and rapid assembly, affecting the construction period and overall efficiency.

[0004] Existing steel structure operation and maintenance management methods mainly rely on periodic inspections and manual detections, with limited monitoring coverage, making it difficult to comprehensively control the operating state of steel structures. For example, hidden dangers such as fatigue cracks and local corrosion are difficult to detect in a timely manner, and these problems may lead to catastrophic consequences after deteriorating to a certain extent. In addition, real-time monitoring data and intelligent analysis technologies have not been effectively combined during the operation and maintenance process, making it difficult to optimize the maintenance plan in a timely manner, increasing the operation and maintenance cost.

[0005] In traditional steel structure projects, data in each stage of design, construction, and operation and maintenance are often stored independently, lacking a unified information sharing platform. For example, BIM (Building Information Model) data in the design stage fails to effectively serve the construction and operation and maintenance stages, resulting in poor information transmission and affecting the collaborative efficiency of each stage. This information island phenomenon restricts the realization of the full life cycle management of steel structures.

[0006] In recent years, the development of technologies such as Building Information Model (BIM), multi-objective optimization algorithms, and sensor networks has provided the possibility for the integrated management of steel structure design, construction, and operation and maintenance. The BIM model can intuitively present the geometric information, mechanical properties, and status data of the structure. The multi-objective optimization algorithm can generate a globally optimal design scheme by synthesizing multi-dimensional performance requirements, while the sensor network can achieve real-time monitoring and status assessment of steel structures. However, there is currently no systematic framework to integrate the above technologies into the full life cycle management of steel structures. Summary of the Invention

[0007] The objective of the present invention is to make up for the deficiencies of the existing technologies, and to provide a steel structure system based on intelligent optimization and real-time monitoring, so as to improve the overall efficiency and performance in the design, construction, and operation and maintenance stages of steel structures.

[0008] The present invention is realized through the following technical solutions:

[0009] A steel structure system based on intelligent optimization and real-time monitoring, the system comprising:

[0010] Generate a multi-objective optimization design plan according to the actual application scenario, integrate it into the BIM model, and output the optimized plan for the target design stage;

[0011] According to the requirements of construction nodes, guide the manufacturing of modular components and the layout of sensors, and output a rapid assembly plan for the target construction stage;

[0012] According to the real-time monitoring data monitored by the implementation monitoring system, analyze the structural operation status and generate a maintenance plan, and output a dynamic maintenance plan for the target operation and maintenance stage.

[0013] The multi-objective optimization design plan includes:

[0014] According to the stress distribution, fatigue life, and anti-corrosion performance requirements of the steel structure, use a multi-objective optimization algorithm to generate a globally optimal design plan;

[0015] Integrate the optimization results into the BIM model through a 3D modeling tool to form a visual design model;

[0016] Output the global parameters of the optimized design stage.

[0017] The process of the multi-objective optimization algorithm includes problem modeling, objective function definition, constraint conditions, optimization variables, algorithm selection, optimization process, and output results;

[0018] The problem modeling is: define the optimization problem of the steel structure as a multi-objective optimization problem, with objectives including stress distribution, fatigue life, and anti-corrosion performance; the stress distribution includes minimizing the maximum stress and stress gradient of the structure; the fatigue life includes maximizing the fatigue life; the anti-corrosion performance includes maximizing the anti-corrosion performance;

[0019] The objective function definition includes minimizing stress distribution, maximizing fatigue life, and maximizing anti-corrosion performance;

[0020] The constraint conditions include geometric constraints, material strength constraints, and construction technology constraints;

[0021] The optimization variables include geometric parameters, material parameters, and connection parameters;

[0022] The NSGA-II algorithm is selected, and the NSGA-II includes fast non-dominated sorting, crowding degree calculation, and elitist strategy;

[0023] For the fast non-dominated sorting, it efficiently sorts the solutions in the population to find all non-dominated solution sets, that is, Pareto front solutions; for the crowding degree calculation, by calculating the crowding distance between individuals, it ensures the uniform distribution of solutions on the Pareto front; for the elitist strategy, it retains the excellent solutions of the previous generation to prevent the loss of the optimal solution;

[0024] According to the constraint conditions and optimization variables, non-dominated sorting is performed on the individuals in the population, and the next generation of population is generated through selection, crossover, and mutation;

[0025] For the selection, the tournament selection method is used to select high-quality individuals from the current population;

[0026] For the crossover, crossover operations are performed on the selected individuals to generate new design solutions;

[0027] For the mutation, partial variables of the individuals are mutated to increase the population diversity; the size of the next generation of population is the same as that of the initial population, and the iterative optimization repeats the following steps until the preset conditions are met, and the objective function values of the new population are calculated; the steps are as follows:

[0028] Perform non-dominated sorting on the population and update the Pareto front solutions, and judge whether the stop conditions are met, that is, reaching the maximum number of iterations or the convergence of the objective function, and output the results. After the optimization is completed, the set of Pareto front solutions is output.

[0029] The calculation formula for minimizing the stress distribution is as follows:

[0030] f1(x)=max(σ i )(i=1,2,3,...,n)

[0031] In the formula, σ i is the stress of the i-th node, and x is the design variable;

[0032] The calculation formula for maximizing the fatigue life is as follows:

[0033]

[0034] In the formula, Δσ i is the stress amplitude, σ lim is the fatigue limit, and m is the material constant;

[0035] The calculation formula for maximizing the corrosion resistance is as follows:

[0036]

[0037] In the formula, Ccorr (x) is the corrosion rate, and t corr is the effective time of the structural anti-corrosion protection.

[0038] The geometric constraints include meeting the requirements of structural dimensions, shapes, and spatial layouts; the material strength constraints include that the stress at each node shall not exceed the yield strength of the material; the construction process constraints include that the connection and processing technologies of components meet the construction requirements.

[0039] The geometric parameters include the height, width, and thickness of the beam cross-section; the material parameters include the steel grade and coating type; the connection parameters include the number of bolts and the arrangement method.

[0040] The output Pareto front solution set, where each solution includes: geometric parameters and performance indicators;

[0041] The geometric parameters are the beam cross-section size and material thickness; the performance indicators are that the stress distribution is more uniform, the maximum stress value is reduced, the fatigue life is significantly improved, the anti-corrosion performance is enhanced, and the maintenance period is extended;

[0042] Select the optimal solution under different weight combinations according to the actual needs.

[0043] The rapid assembly plan in the construction stage includes:

[0044] Guiding the manufacturing process of modular components according to the BIM model to improve the accuracy and efficiency in the construction stage;

[0045] During the construction process, arranging multi-type sensors according to the importance of construction nodes for real-time monitoring of the mechanical properties of key nodes;

[0046] Outputting the sensor arrangement and modular construction data in the construction stage.

[0047] The real-time monitoring system includes:

[0048] Arranging MEMS pressure sensors, temperature sensors, and humidity sensors at key structural parts to collect multi-dimensional performance data of the structure operation;

[0049] Integrating the monitoring data using the BIM model, comparing with the performance model in the design stage, and outputting the alarm information of the abnormal state of the structure;

[0050] Providing performance optimization suggestions in the operation and maintenance stage through the analysis and feedback of the monitoring data.

[0051] The dynamic maintenance plan in the operation and maintenance stage includes:

[0052] Analyzing the operation state of the structure according to the stress, temperature, and humidity data monitored in real time;

[0053] Generate a dynamic maintenance plan according to the long-term operating performance requirements of the structure, and adjust the maintenance priorities of potential risk nodes;

[0054] Output real-time monitoring data and dynamic maintenance suggestions during the operation and maintenance phase.

[0055] The present invention utilizes a multi-objective optimization algorithm to comprehensively consider the stress distribution, fatigue life, and corrosion resistance of the structure, and generate a globally optimal design solution;

[0056] The present invention integrates the optimization results into the BIM model through a 3D modeling tool to generate a visual design solution, which serves as the core reference data during the construction phase and the operation and maintenance phase.

[0057] During the construction phase, it includes:

[0058] Modular component manufacturing: Guide the manufacturing and on-site assembly of modular components according to the BIM model to improve the construction accuracy and efficiency;

[0059] Sensor arrangement: Arrange sensors at key construction nodes to collect mechanical property data in real time and monitor the structural stability and stress distribution during the construction process.

[0060] During the operation and maintenance phase, it includes:

[0061] Real-time data analysis: Collect real-time operation data through sensors and analyze the stress state, deformation conditions, and environmental impact factors of the structure;

[0062] Dynamic maintenance plan: Generate a dynamic maintenance plan based on the real-time data analysis results, prioritize the maintenance and optimization of potential risk areas, and extend the service life of the structure.

[0063] The present invention realizes the full-process digital and intelligent management of the design, construction, and operation and maintenance of steel structures through the combination of a multi-objective optimization algorithm and a BIM model. In the design phase, it focuses on the global optimization of structural performance. In the construction phase, it focuses on efficient and precise assembly and real-time monitoring. In the operation and maintenance phase, it ensures the safety and long-term stability of the structure through real-time data feedback.

[0064] The present invention significantly improves the full-life cycle management ability of steel structure projects by simulating stress distribution and optimizing performance in the design phase, achieving efficient manufacturing and assembly of modular components in the construction phase, and making dynamic adjustments in combination with real-time monitoring data in the operation and maintenance phase.

[0065] The advantages of the present invention are as follows: By integrating multi-objective optimization algorithms, BIM models, and real-time monitoring technologies, the present invention constructs an intelligent management framework for the entire process of design, construction, and operation and maintenance. In the design stage, the present invention uses multi-objective optimization algorithms to balance stress distribution, fatigue life, and corrosion resistance, generates a globally optimal design solution, and integrates it into the BIM model; in the construction stage, through modular component manufacturing and sensor layout, the construction accuracy and efficiency are improved; in the operation and maintenance stage, through real-time monitoring data analysis and dynamic maintenance plan generation, the safety and service life of the steel structure are ensured.

[0066] The present invention can not only solve the pain points in the traditional design, construction, and operation and maintenance of steel structures, but also significantly reduce the cost of the entire project life cycle, improve the overall project efficiency, and provide new ideas and technical support for the intelligent development of steel structure projects.

[0067] By integrating multi-objective optimization algorithms, BIM models, and sensor networks, the present invention not only improves the safety and efficiency of steel structure design, but also can dynamically adjust the plan in the construction and operation and maintenance stages, reducing the cost of the entire life cycle. Compared with traditional methods, the system has significant advantages in structural performance optimization and intelligent management. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a diagram of a steel structure system based on intelligent optimization and its application method;

[0069] Figure 2 It is a flowchart of a multi-objective optimization algorithm;

[0070] Figure 3 It is a diagram of the yield strength table of steel;

[0071] Figure 4 It is a diagram of geometric parameters;

[0072] Figure 5 It is a diagram of material parameters;

[0073] Figure 6 It is a diagram of connection parameters;

[0074] Figure 7 It is a Pareto result diagram;

[0075] Figure 8 It is a flowchart of BIM model integration;

[0076] Figure 9 It is a flowchart of modular component manufacturing;

[0077] Figure 10 It is a flowchart of sensor layout;

[0078] Figure 11 It is a specific flowchart of real-time data analysis. Detailed implementation manners

[0079] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit this disclosure.

[0080] In all the examples shown and discussed herein, any specific value should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0081] It should be noted that: like reference numerals and letters denote like items in the following drawings; thus, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.

[0082] It should be noted that all actions of obtaining signals, information, or data in this application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and with the authorization given by the owner of the corresponding device.

[0083] Next, various embodiments and examples according to the present invention will be described with reference to the accompanying drawings.

[0084] As Figure 1 shown, a steel structure system based on intelligent optimization and real-time monitoring, the system includes:

[0085] Generate a multi-objective optimization design plan according to the actual application scenario, integrate it into the BIM model, and output the optimization plan at the target design stage;

[0086] Guide the manufacturing of modular components and the arrangement of sensors according to the construction node requirements, and output the rapid assembly plan at the target construction stage;

[0087] Analyze the structural operation status according to the real-time monitoring data monitored by the implementation monitoring system, generate a maintenance plan, and output the dynamic maintenance plan at the target operation and maintenance stage.

[0088] The multi-objective optimization design plan includes:

[0089] Generate a globally optimal design plan using a multi-objective optimization algorithm according to the stress distribution, fatigue life, and corrosion resistance requirements of the steel structure;

[0090] Integrate the optimization results into the BIM model through a 3D modeling tool to form a visual design model;

[0091] Output the global parameters at the optimized design stage.

[0092] In one example, the object of this embodiment is a whole, including problem modeling, objective function definition, constraints, optimization variables, algorithm selection, optimization process and output results, such as Figure 2 shown.

[0093] Step S201 : the problem is modeled, and the optimization problem of the steel structure is defined as a multi-objective optimization problem, where the objectives include stress distribution, fatigue life, and corrosion resistance.

[0094] The stress distribution includes minimizing the maximum stress and stress gradient of the structure to reduce local stress concentration; the fatigue life includes maximizing the fatigue life to ensure that the structure can withstand long-term load cycles without failure; the corrosion resistance includes maximizing the corrosion resistance to reduce the degradation of structural strength caused by corrosion.

[0095] Step S202 , according to the definition of the objective function, includes minimizing stress distribution, maximizing fatigue life, and maximizing corrosion resistance.

[0096] The stress distribution minimization calculation formula is as follows:

[0097] f1(x)=max(σ i )(i=1,2,3,...,n)

[0098] Where σ i is the stress at the i-th node, and x is the design variable.

[0099] The fatigue life maximization calculation formula is as follows:

[0100]

[0101] Where Δσ i is the stress amplitude, σ lim is the fatigue limit, m is the material constant;

[0102] The calculation formula for maximizing the corrosion resistance is as follows:

[0103]

[0104] Where C corr (x) is the corrosion rate, t corr The effective time of structural anti-corrosion protection.

[0105] Step S203: To ensure the feasibility of the design solution, the following constraints are set, including geometric constraints, material strength constraints, and construction process constraints;

[0106] The geometric constraints include meeting the requirements of structural dimensions, shapes, and spatial layouts; the material strength constraints include that the stress at each node shall not exceed the yield strength of the material, and the specific value of the yield strength of the material refers to Figure 3 the yield strength table of steel; the construction process constraints include that the connection and processing processes of components meet the construction requirements.

[0107] The optimization variables include geometric parameters, material parameters, and connection parameters. The geometric parameters include the height, width, and thickness of the beam cross-section, etc.; the material parameters include the steel grade and coating type; the connection parameters include the number and layout of bolts, etc. Each optimization variable refers to Figure 4 , Figure 5 , Figure 6 .

[0108] The optimization scheme of the specific steel beam-column structure of the present invention;

[0109] The geometric parameters include that the height of the beam cross-section is 600 mm, the width is 250 mm, the web thickness is 10 mm, and the flange thickness is 18 mm; the height of the column cross-section is 800 mm, the width is 350 mm, the web thickness is 12 mm, and the flange thickness is 22 mm. The material parameters include that the steel grade is Q345, the coating type is epoxy coating, and the thickness is 120 μm. The fireproof coating is an inorganic coating with a thickness of 15 mm. The connection parameters include that the bolt diameter is M20. The number of bolts is 6, the weld thickness is 10 mm, and the node connection method is a rigid connection.

[0110] Step S204, the optimization variables can be adjusted according to the specific project requirements and design objectives. If more refined calculations and optimizations are needed for a specific steel structure project, select according to Figure 4 , Figure 5 , Figure 6 the relevant parameters and requirements.

[0111] Step S205, perform a multi-objective optimization algorithm on the optimization variables. The multi-objective optimization algorithm uses NSGA-II. NSGA-II is a mature multi-objective optimization algorithm that can effectively solve complex multi-objective optimization problems in steel structure systems. Its characteristics include fast non-dominated sorting, crowding degree calculation, and elitist strategy.

[0112] The fast non-dominated sorting can efficiently sort the solutions in the population and find all non-dominated solution sets (Pareto front solutions),

[0113] The crowding degree calculation ensures the uniform distribution of solutions on the Pareto front by calculating the crowding distance between individuals.

[0114] The elitist strategy retains the excellent solutions of the previous generation to prevent the loss of the optimal solutions.

[0115] Step S206: According to the constraint conditions and the multi-objective optimization problem, perform non-dominated sorting on the individuals in the population to generate the next-generation population. The generation of the next-generation population includes selection, crossover, and mutation through the following operations.

[0116] For the selection, use the tournament selection method to select high-quality individuals from the current population.

[0117] For the crossover, perform a crossover operation (such as simulated binary crossover SBX) on the selected individuals to generate new design solutions.

[0118] For the mutation, mutate some variables of the individuals (such as fine-tuning the geometric dimensions) to increase the population diversity. The size of the next-generation population is the same as that of the initial population. Iterative optimization repeats the following steps until the preset conditions are met: Calculate the objective function values of the new population.

[0119] Perform non-dominated sorting on the population and update the Pareto front solutions, and determine whether the stop conditions are satisfied (such as reaching the maximum number of iterations or the convergence of the objective function), and output the results. After the optimization is completed, output the set of Pareto front solutions. Each solution includes: geometric parameters and performance indicators.

[0120] The geometric parameters, such as beam section dimensions, material thickness, etc.

[0121] The performance indicators include more uniform stress distribution, reduced maximum stress value, significantly improved fatigue life, enhanced corrosion resistance, and extended maintenance cycle.

[0122] The optimal solution under different weight combinations can be selected according to actual needs.

[0123] The optimization solution for the specific steel beam-column structure in this embodiment;

[0124] Initialize the population. Population size: Set the population size P, such as P = 100.

[0125] Design variable range: According to the geometric parameters, material parameters, and connection parameters of the steel structure design, randomly generate P solutions that meet the constraint conditions. Include geometric parameters: beam section height, width, thickness, etc. Material parameters: steel grade, coating type, etc. Connection parameters: number of bolts, layout method, etc. Each solution represents a steel structure design solution.

[0126] Calculate the objective function. For each individual x (i.e., a design solution), calculate the multi-objective function values including minimizing the maximum value of stress distribution, maximizing the fatigue life, and maximizing the corrosion resistance.

[0127] Non-dominated sorting divides the individuals in the population into multiple non-dominated levels according to the dominance relationship: Individual A dominates B if and only if: A is not worse than B in all objectives; A is better than B in at least one objective. Hierarchically allocate the population, put the non-dominated solutions into the first level (Pareto front), the sub-optimal solutions into the second level, and so on.

[0128] Crowding distance calculation: For the solutions in each non-dominated level, calculate their crowding distances, which represent the distribution density of the solutions in the objective space. Prefer solutions with larger crowding distances to avoid solutions concentrating in a certain area.

[0129] Select the next-generation population, elitist strategy: Combine the current population and the offspring population to get 2P individuals. Select the optimal solutions: Sort according to the non-dominated levels, and preferentially retain the solutions in the lower levels. Within the same level, sort according to the crowding distance, and preferentially select individuals with larger distances. Select the top P individuals from the combined population to form the next-generation population.

[0130] Perform crossover operation based on the population, use simulated binary crossover (SBX), randomly select two individuals from the population to generate two new design schemes.

[0131] For example, for design variables (x1, x2) and (y1, y2), generate new individuals through the following formula:

[0132] x'1 = 0.5×(x1 + y1), y'1 = 0.5×(x2 + y2)

[0133] Mutation operation: Randomly fine-tune some variables of the individuals to increase the population diversity. For example, adjust the beam section height or the bolt layout position.

[0134] Iterative optimization: Repeat steps to calculate the objective function, non-dominated sorting, select the next-generation population, and crossover and mutation until the preset number of iterations (e.g., G = 500) is reached and the change amount of the Pareto front solutions is less than the preset threshold, then the algorithm converges.

[0135] The output result, Pareto front solutions, outputs a set of design schemes that meet different weight requirements. Each scheme includes design variables and their objective values (stress distribution, fatigue life, corrosion resistance performance).

[0136] The designer's selection: According to the actual requirements, select the optimal design scheme from the Pareto front solutions, such as the scheme that minimizes the stress value or maximizes the life, as Figure 7 shown.

[0137] The rapid assembly scheme in the construction stage includes:

[0138] Guide the manufacturing process of modular components according to the BIM model to improve the accuracy and efficiency in the construction stage;

[0139] During the construction process, various types of sensors are arranged according to the importance of construction nodes to monitor the mechanical properties of key nodes in real time;

[0140] Output the sensor layout and modular construction data during the construction stage.

[0141] The real-time monitoring system includes:

[0142] MEMS pressure sensors, temperature sensors and humidity sensors are arranged at key structural parts to collect multi-dimensional performance data of the structure operation;

[0143] Integrate the monitoring data using the BIM model, compare it with the performance model in the design stage, and output the alarm information of the abnormal structure state;

[0144] Provide performance optimization suggestions for the operation and maintenance stage through the analysis and feedback of the monitoring data.

[0145] The dynamic maintenance plan for the operation and maintenance stage includes:

[0146] Analyze the operation state of the structure according to the stress, temperature and humidity data monitored in real time;

[0147] Generate a dynamic maintenance plan according to the long-term operation performance requirements of the structure, and adjust the maintenance priority of potential risk nodes;

[0148] Output the real-time monitoring data and dynamic maintenance suggestions for the operation and maintenance stage.

[0149] Step S102, the integration based on the BIM model is divided into data preparation, BIM model construction, structural performance analysis, BIM and construction, operation and maintenance integration, output of BIM visual design, and final output. The specific steps are based on S301 - S305, as Figure 8 shown.

[0150] S301 is data preparation. After the NSGA-II optimization is completed, obtain the optimal design solution in the Pareto front solution. This solution includes: geometric parameters (such as beam section height, width, thickness), material parameters (such as steel grade, coating type), connection parameters (such as bolt arrangement method, weld thickness), select the target solution and select a suitable solution from multiple optimization solutions (Pareto front solutions) according to project requirements.

[0151] The S302 is BIM model construction, which includes establishing a BIM structural model, creating a three-dimensional model of the steel structure using BIM modeling software (such as Revit, Tekla Structures). According to the geometric parameters of the optimized design scheme, adjust the dimensions, materials, and connection methods of components such as beams, columns, and joints. Input the optimized geometric parameters into the BIM software, and adjust the dimensions and layout methods of components such as steel beams, steel columns, and joints. Use the IFC (Industry Foundation Classes) file format to import the optimized data into the BIM software to achieve parametric modeling. Perform parametric modeling through Dynamo (Revit plugin) or Grasshopper (Rhino plugin) to directly generate the optimized model. In the BIM environment, call structural analysis software (such as SAP2000, ETABS, ANSYS) to conduct secondary verification of the optimized scheme to ensure that the requirements for stress, fatigue life, and corrosion resistance are met.

[0152] The S303 is structural performance analysis. Conduct structural performance simulation. In the BIM environment, call structural analysis software (such as SAP2000, ETABS, ANSYS) to conduct secondary verification of the optimized scheme to ensure that the requirements for stress, fatigue life, and corrosion resistance are met. Combine FEA (finite element analysis) calculations: maximum stress point distribution displacement analysis, stability check, and adjust the BIM model. If the simulation analysis results show that the structural performance does not meet the requirements, adjust the BIM model parameters, modify the cross-sectional dimensions of local components. Re-optimize the material selection and connection methods. Re-iterate the multi-objective optimization algorithm and update the BIM model. Combine FEA (finite element analysis) calculations: maximum stress point distribution, displacement analysis, stability check. Adjust the BIM model. If the simulation analysis results show that the structural performance does not meet the requirements, adjust the BIM model parameters: modify the cross-sectional dimensions of local components. Re-optimize the material selection and connection methods, re-iterate the multi-objective optimization algorithm and update the BIM model.

[0153] The S304 is the integration of BIM with construction and operation and maintenance, which includes converting the BIM model data into construction drawings and exporting them in DWG and PDF formats for on-site construction use. Combine BIM 5D (schedule + cost) to generate a simulation of the steel structure construction progress and optimize the construction plan. Arrange sensors in the BIM environment to mark the key structural nodes (high stress areas, fatigue-sensitive areas) and provide a sensor arrangement plan: MEMS pressure sensors: monitor the stress changes of beams and columns. Temperature and humidity sensors: monitor the impact of the environment on the steel structure. Accelerometers: monitor vibration and deformation conditions. In the operation and maintenance stage, integrate the Internet of Things (IoT) data interface in the BIM model: combine the sensor data to update the stress and deformation status in the BIM model in real time. Through digital twin technology, achieve remote monitoring and intelligent maintenance.

[0154] The S305 is to output BIM visual design. The visual solution outputs a 3D model display to generate a three-dimensional visual design solution for project managers and construction teams to refer to. BIM data management: Use Revit and Navisworks for collaborative design to ensure data sharing in each stage. Virtual reality (VR) simulation: Combine BIM VR technology (such as Enscape and UnrealEngine) for pre-construction assessment to optimize the construction process.

[0155] The final output includes the final results of BIM optimization integration, the optimized BIM steel structure model (3D visual design), construction drawings and construction progress simulation, sensor layout plan, structural performance analysis report, and digital twin operation and maintenance system. This process ensures that the optimized steel structure solution is seamlessly integrated into the BIM environment, improves construction accuracy, reduces operation and maintenance risks, and realizes the full life cycle management of the steel structure.

[0156] Step S103, according to the modular component manufacturing, it is divided into design and optimization, component manufacturing, pre-assembly and quality inspection, transportation and on-site installation, construction monitoring and BIM feedback. The specific steps are based on S401 - S405, as Figure 9 shown.

[0157] The S401 is design and optimization, including parametric modeling. According to the results of the BIM model and multi-objective optimization algorithm, determine the geometric parameters of the steel structure components (such as the dimensions and connection methods of beams and columns). Use Revit and TeklaStructures for component splitting and three-dimensional modeling. Standardized component division: According to building codes and manufacturing standards, define standardized types of steel structure components, such as: H-shaped steel beams, box-shaped steel columns, truss members, and gusset plates, and determine the connection methods of standardized components (bolt connection, welding).

[0158] Generate construction manufacturing drawings from production drawings and data exports, including: steel structure processing drawings (DWG format), welding process drawings, bolt connection layout drawings, and bill of materials (BOM), and generate numerical control codes (NC files) through CNC numerical control processing for direct use by processing equipment.

[0159] S402 is component manufacturing, including material preparation, procurement of steel such as Q345, Q390, Q420, etc. that meet the design standards. After the steel arrives at the factory, quality inspections are carried out: chemical composition analysis, yield strength and tensile strength tests, welding performance inspections, steel component processing, cutting, and steel plate processing using laser cutting, plasma cutting or flame cutting. Shaping: bending and rolling to form prefabricated components of beams, columns, and trusses. Drilling: using a numerically controlled drilling machine for high-precision bolt hole processing. Welding: using automatic welding equipment for weld processing to ensure the connection strength. Ultrasonic flaw detection of welds to ensure welding quality. Surface treatment: sandblasting to remove the oxide layer and impurities. Anti-corrosion coatings (such as epoxy coatings, hot-dip galvanizing) to improve the anti-corrosion performance. Fireproof coatings (such as inorganic fireproof coatings).

[0160] S403 is pre-assembly and quality inspection of component manufacturing. Component pre-assembly includes factory pre-assembly testing: carrying out dry assembly to check the matching degree and connection accuracy between components. After pre-assembly is completed, mark the component numbers for quick on-site installation. The quality inspection includes geometric dimension inspection: using a coordinate measuring machine (CMM) to measure the dimensions of components to ensure that the machining accuracy error is within ±1 mm. Strength testing: carrying out weld flaw detection and torque testing to ensure that bolt connections meet the design requirements. Surface treatment inspection:

[0161] Using a coating thickness detector to test the thickness of anti-corrosion coatings and fireproof coatings

[0162] S404 is transportation and on-site installation, including transportation plan. According to the size and weight of modular components, select appropriate transportation methods: Super-large components: transported by heavy flatbed trucks. Standardized components: transported by containers to improve transportation efficiency. Components are numbered before transportation and accompanied by installation guides. On-site installation and hoisting positioning: using tower cranes or crawler cranes for component hoisting. Quick connection: using high-strength bolts or welding methods for installation: Bolt connection: torque control to ensure that the pre-tightening force meets the specification requirements. Weld connection: carrying out flaw detection after on-site welding. Installation error adjustment: using a laser rangefinder for positioning to ensure that the installation accuracy error does not exceed ±2 mm. Using a coating thickness detector to test the thickness of anti-corrosion coatings and fireproof coatings.

[0163] S405 is construction monitoring and BIM feedback. For construction monitoring, in the BIM model, the construction progress is monitored in real time: the installation status of components is tracked through RFID sensors. The pre-tightening force of bolts and the temperature of welds are monitored in combination with IoT devices. For the BIM model feedback, during the construction process, the BIM model is updated in combination with on-site data: the installation accuracy of components is recorded, and the subsequent construction plan is adjusted. When installation deviations are found, the design errors are corrected immediately. Lifting and positioning: A tower crane or crawler crane is used for component lifting. Quick connection: High-strength bolts or welding methods are used for installation: Bolt connection: Torque control is carried out to ensure that the pre-tightening force meets the specification requirements. Welding connection: Nondestructive testing is carried out after on-site welding. Installation error adjustment: A laser rangefinder is used for positioning to ensure that the installation accuracy error does not exceed ±2 mm. The thickness of the anti-corrosion coating and fireproof coating is tested using a coating thickness detector

[0164] Step S104 is divided into sensor type selection, sensor layout planning, sensor installation implementation, sensor calibration and data acquisition, and monitoring data analysis according to the sensor layout process. The specific steps are based on S501 - S505, as Figure 10 shown

[0165] S501 is design and optimization. First, sensor type selection is carried out, and the monitoring objectives are determined, including stress monitoring: used to evaluate the stress state of the steel structure and avoid local stress concentration. Deformation monitoring: used to monitor the displacement and deformation of the structure under long-term loads. Environmental monitoring: monitoring environmental factors such as temperature, humidity, and corrosion rate that affect the steel structure

[0166] S502 is sensor layout planning, including the selection of key monitoring parts, among which are high-stress areas (such as beam-column connection nodes, mid-span positions). Fatigue-sensitive parts (such as long-span steel beams, the ends of cantilever beams). Areas with significant environmental impacts (such as coastal areas, chemical plants, etc., where corrosion is likely). The sensor layout is optimized based on the results of finite element analysis (FEA), and the nodes with the maximum stress and the most obvious deformation are selected. A point layout optimization algorithm is used to ensure uniform sensor distribution and complete data coverage. The minimum number of sensors is used to reduce installation and maintenance costs

[0167] The S503 is the implementation of sensor installation, including construction preparation and construction team training: ensuring that the installers are familiar with the sensor characteristics and installation requirements. Wiring and power supply: determining the power supply method (wired / wireless) of the sensor and planning the data transmission network. The steps of sensor installation are as follows: for strain sensor installation, surface treatment (grinding, cleaning) to ensure no oil stain. Using a special adhesive to paste or welding to fix the strain gauge. Connecting the signal wire and encapsulating the protective layer (waterproof, dustproof). For acceleration sensor installation, select an installation point with good rigidity to avoid signal interference. Using bolts to fix and ensure close contact with the structure. For displacement sensor installation, fix the sensor on a rigid bracket to ensure that the measurement reference remains unchanged. Using laser or LVDT technology to accurately monitor displacement changes.

[0168] For temperature and humidity sensor installation, select representative environmental areas (outdoor, beam-column joints). Using a sealed housing to prevent dust and moisture from affecting the sensor life. For corrosion sensor installation, select parts where corrosion may occur (humid areas, coastal environments) and use an electrochemical sensor to monitor the corrosion rate in real time.

[0169] The S504 is sensor calibration and data acquisition. Sensor calibration uses a static loading test to check the accuracy of strain and displacement measurements. Using a known acceleration signal to calibrate the vibration sensor. Verifying the accuracy of the temperature and humidity sensor through an environmental constant temperature chamber. The data acquisition system uses wireless data transmission (LoRa, NB-IoT) or wired optical fiber transmission. Setting the data sampling rate: low-frequency monitoring (environmental monitoring) - once per hour, medium-frequency monitoring (fatigue life analysis) - 10 times per minute, high-frequency monitoring (vibration monitoring) - 1000 times per second.

[0170] The S505 is monitoring data analysis, including data processing using the BIM+IoT platform to integrate the monitoring data with the BIM model for visual display. Using machine learning algorithms to predict the structural fatigue life and provide maintenance suggestions. The warning mechanism sets thresholds for stress, displacement, and environmental factors. If the data exceeds the limit, it automatically triggers a warning to notify the maintenance personnel.

[0171] Step S105, according to real-time data analysis, it is divided into data acquisition and preprocessing, data feature extraction and calculation, real-time data analysis and warning, data storage and operation and maintenance optimization. The specific steps are based on S601 - S604, as Figure 11 shown.

[0172] S601 is sensor data acquisition. Data sources: sensors such as strain, acceleration, displacement, temperature and humidity, corrosion rate, etc. Sampling frequency: Low-frequency monitoring (temperature and humidity, corrosion): 1 time per hour. Medium-frequency monitoring (fatigue life, stress): 10 times per minute. High-frequency monitoring (vibration, shock): 1000 times per second. Data transmission: Wireless methods: LoRa, NB-IoT, WiFi (remote transmission). Wired methods: optical fiber, Ethernet (high-speed and stable). Data storage: Use time-series databases (InfluxDB, TimescaleDB) to store historical data. Combine with the BIM database to associate sensor locations with the structural model. The data cleaning and preprocessing: Data denoising: Use wavelet transform to filter signal noise. Use moving average filtering to smooth short-term fluctuating data. Abnormal data elimination: Set the normal value range and eliminate over-limit or invalid data. Use the K-Means clustering algorithm to identify abnormal points.

[0173] S602 is data feature extraction and calculation, including stress analysis to calculate the stress time series of key structural points:

[0174]

[0175] Among them, σi is the stress, Fi is the measured force, and A is the cross-sectional area.

[0176] Monitor stress peaks and trends: Calculate the maximum stress at each monitoring point:

[0177] σ max =max(σ1,σ2...σ max )

[0178] Calculate the stress gradient of the structure:

[0179]

[0180] The Gσ reflects the severity of stress changes.

[0181] The fatigue life analysis calculates fatigue damage:

[0182]

[0183] Among them, Ni is the number of load cycles, and Nf is the fatigue life under the corresponding stress amplitude. Use Miner’s Rule to evaluate the cumulative fatigue damage.

[0184] The predicted fatigue life:

[0185]

[0186] Among them, Lf is the remaining fatigue life

[0187] Calculating the deflection of the deformed monitoring beam:

[0188]

[0189] Among them, w is the uniformly distributed load, L is the beam length, E is the elastic modulus, and I is the moment of inertia of the cross-section. Monitoring the displacement of the node: calculating the maximum displacement δmax and setting the threshold δlimit. If δmax > δlimit, an alarm is triggered.

[0190] Due to the influence of environmental factors, calculating the influence of temperature and humidity changes on the steel structure:

[0191] ΔL = αLΔT

[0192] Among them, α is the coefficient of thermal expansion, L is the structural length, and ΔT is the temperature change.

[0193] Monitoring the corrosion rate:

[0194]

[0195] Among them, ΔW is the mass loss, A is the affected area, and t is the time.

[0196] The S6,03 is for real-time data analysis and early warning, including early warning rules and setting thresholds:

[0197] The normal range of stress (MPa) < 200, the warning threshold is 200 - 250, and the alarm threshold > 250;

[0198] The normal range of displacement (mm) < 5, the warning threshold is 5 - 10, and the alarm threshold > 10;

[0199] The normal range of fatigue damage < 0.3, the warning threshold is 0.3 - 0.7, and the alarm threshold > 0.7;

[0200] The normal range of corrosion rate (mm / year) < 0.1, the warning threshold is 0.1 - 0.3, and the alarm threshold > 0.3;

[0201] The triggered alarm mechanism includes a yellow warning: the indicator is approaching the limit, prompting manual inspection. A red alarm: the indicator exceeds the limit, automatically notifying the maintenance personnel. The data visualization combines with the BIM model to achieve a three-dimensional display of real-time monitoring data: color marking: green (normal), yellow (warning), red (alarm).

[0202] Trend analysis: line charts and bar charts show the change trends of historical data

[0203] S604 is data storage and operation and maintenance optimization, including storage and data integration. Short-term storage (real-time data): stored in InfluxDB for fast access. Long-term storage (historical data): stored in PostgreSQL / Hadoop for subsequent analysis. BIM integration: associate monitoring data with the BIM model to achieve dynamic structural health management. The maintenance decision-making optimizes predictive maintenance: uses machine learning (LSTM, XGBoost) to predict future stress change trends. Based on historical data, intelligently adjust the maintenance plan. Intelligent operation and maintenance suggestions: combine BIM data to automatically generate a steel structure maintenance plan. Calculate the optimal maintenance time window to reduce maintenance costs and improve safety.

Claims

1. A steel structure system based on intelligent optimization and real-time monitoring, characterized in that, The system includes: Generate a multi-objective optimization design plan according to the actual application scenario, integrate it into the BIM model, and output the optimized plan for the target design stage; Guide the manufacturing of modular components and the layout of sensors according to the construction node requirements, and output the rapid assembly plan for the target construction stage; Analyze the structural operation status based on the real-time monitoring data monitored by the implementation monitoring system, generate a maintenance plan, and output the dynamic maintenance plan for the target operation and maintenance stage.

2. The steel structure system based on intelligent optimization and real-time monitoring according to claim 1, wherein, The multi-objective optimization design plan includes: Generate a globally optimal design plan using a multi-objective optimization algorithm according to the stress distribution, fatigue life, and corrosion resistance requirements of the steel structure; Integrate the optimization results into the BIM model through a 3D modeling tool to form a visual design model; Output the global parameters of the optimized design stage.

3. A steel structure system based on intelligent optimization and real-time monitoring according to claim 2, characterized in that, The process of the multi-objective optimization algorithm includes problem modeling, objective function definition, constraint conditions, optimization variables, algorithm selection, optimization process, and output results; The problem modeling is as follows: Define the optimization problem of the steel structure as a multi-objective optimization problem, with objectives including stress distribution, fatigue life, and corrosion resistance; the stress distribution includes minimizing the maximum stress and stress gradient of the structure; the fatigue life includes maximizing the fatigue life; the corrosion resistance includes maximizing the corrosion resistance; The objective function definition includes minimizing stress distribution, maximizing fatigue life, and maximizing corrosion resistance; The constraint conditions include geometric constraints, material strength constraints, and construction process constraints; The optimization variables include geometric parameters, material parameters, and connection parameters; The algorithm selection uses NSGA-II, and NSGA-II includes fast non-dominated sorting, crowding degree calculation, and elitist strategy; For the fast non-dominated sorting, efficiently sort the solutions in the population to find all non-dominated solution sets, that is, the Pareto front solutions; for the crowding degree calculation, ensure the uniform distribution of solutions on the Pareto front by calculating the crowding distance between individuals; for the elitist strategy, retain the excellent solutions of the previous generation to prevent the loss of the optimal solution; According to the constraint conditions and optimization variables, perform non-dominated sorting on the individuals in the population, and generate the next generation of population through selection, crossover, and mutation; For the selection, use the tournament selection method to select high-quality individuals from the current population; For the crossover, perform a crossover operation on the selected individuals to generate a new design plan; For the mutation, mutate some variables of the individuals to increase the population diversity; the size of the next generation of population is the same as that of the initial population. Iteratively optimize and repeat the following steps until the preset conditions are met, and calculate the objective function values of the new population. The steps are as follows: Perform non-dominated sorting on the population and update the Pareto front solutions, and judge whether the stop condition is met, that is, the maximum number of iterations is reached or the objective function converges, and output the results. After the optimization is completed, output the set of Pareto front solutions.

4. According to the steel structure system based on intelligent optimization and real-time monitoring described in claim 3, characterized in that The calculation formula for minimizing the stress distribution is as follows: f1(x) = max(σ i )(i = 1, 2, 3, ..., n) where σ i is the stress of the i-th node, and x is the design variable; The calculation formula for maximizing the fatigue life is as follows: where Δσ i is the stress amplitude, σ lim is the fatigue limit, and m is the material constant; The calculation formula for maximizing the corrosion resistance is as follows: where C corr (x) is the corrosion rate, and t corr is the effective time of the structural anti-corrosion protection.

5. The steel structure system based on intelligent optimization and real-time monitoring according to claim 3, characterized in that, The geometric constraints include meeting the requirements of structural dimensions, shapes, and spatial arrangements; the material strength constraints include that the stress at each node shall not exceed the yield strength of the material; the construction technology constraints include that the connection and processing technologies of components meet the construction requirements.

6. The steel structure system based on intelligent optimization and real-time monitoring according to claim 3, characterized in that, The geometric parameters include the beam section height, width, and thickness; the material parameters include the steel grade and coating type; the connection parameters include the number of bolts and the arrangement method.

7. A steel structure system based on intelligent optimization and real-time monitoring according to claim 3, characterized in that, The output Pareto front solution set, where each solution includes: geometric parameters and performance indicators; The geometric parameters are the beam section size and material thickness; the performance indicators are that the stress distribution is more uniform, the maximum stress value is reduced, the fatigue life is significantly improved, the corrosion resistance is enhanced, and the maintenance period is extended; Select the optimal solution under different weight combinations according to actual requirements.

8. A steel structure system based on intelligent optimization and real-time monitoring according to claim 1, characterized in that The rapid assembly scheme in the construction stage includes: Guiding the manufacturing process of modular components according to the BIM model to improve the accuracy and efficiency in the construction stage; During the construction process, arranging various types of sensors according to the importance of construction nodes to monitor the mechanical properties of key nodes in real time; Outputting the sensor arrangement and modular construction data in the construction stage.

9. The steel structure system based on intelligent optimization and real-time monitoring according to claim 1, characterized in that, The real-time monitoring system includes: Arranging MEMS pressure sensors, temperature sensors, and humidity sensors at key structural parts to collect multi-dimensional performance data of the structure operation; Integrating the monitoring data using the BIM model, comparing it with the performance model in the design stage, and outputting the alarm information of the abnormal state of the structure; Providing performance optimization suggestions for the operation and maintenance stage through the analysis and feedback of the monitoring data.

10. A steel structure system based on intelligent optimization and real-time monitoring according to claim 9, characterized in that, The dynamic maintenance scheme in the operation and maintenance stage includes: Analyzing the operation state of the structure according to the stress, temperature, and humidity data monitored in real time; Generating a dynamic maintenance plan according to the long-term operation performance requirements of the structure, and adjusting the maintenance priorities of potential risk nodes; Outputting the real-time monitoring data and dynamic maintenance suggestions in the operation and maintenance stage.

Images