A Machine Learning-Based Intelligent Analysis Method for Steel Structure Construction Safety

Abstract

This invention discloses an intelligent steel structure safety construction analysis method based on machine learning. By introducing machine learning methods and combining them with digital twin technology, this invention achieves real-time simulation and monitoring of the steel structure construction process, thereby enabling accurate analysis and scientific prediction of structural safety performance and significantly improving the safety and stability of steel structure construction. Real-time simulation allows for the timely detection and resolution of problems during construction, preventing safety accidents. Simultaneously, predictions and optimization suggestions based on the machine learning model guide construction personnel to conduct scientific construction, improving construction efficiency and quality. Furthermore, the implementation of this invention can reduce construction costs and improve the economic benefits for construction companies.

Description

Technical Field

[0001] This invention relates to the field of building construction technology, and specifically to an intelligent steel structure safety construction analysis method based on machine learning. Background Technology

[0002] In modern construction engineering, steel structures are widely used due to their advantages of being lightweight, high-strength, and fast to construct. However, steel structures face numerous challenges during construction, such as time-varying mechanical parameters, structural stability issues, and construction quality control. Many factors influence the safe construction of steel structures, and these factors exhibit complex nonlinear relationships. Furthermore, on-site monitoring of the stress on critical nodes presents significant difficulties. In engineering design, a conservative approach is sometimes adopted to ensure steel structure safety, leading to higher construction costs. Moreover, structural verification requires extensive manual modeling and calculations, making effective parameter optimization difficult. While structural stress analysis often relies on specific software, for complex steel structures such as high-rise, large-scale, special, and specialized structures, relying solely on design drawings for manual modeling is labor-intensive and prone to errors.

[0003] To ensure that steel structure design can simultaneously consider both safety and economy, establishing an efficient and accurate intelligent steel structure safety construction analysis method based on machine learning that takes into account multiple influencing factors has become a worthy research topic. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent analysis method for steel structure construction safety based on machine learning. By introducing machine learning technology and combining it with digital twin technology, real-time simulation and monitoring of the steel structure construction process can be achieved, thereby enabling accurate analysis and scientific prediction of structural safety performance.

[0005] The objective of this invention is achieved as follows:

[0006] A machine learning-based intelligent method for analyzing the safety of steel structure construction includes the following steps:

[0007] Step 1: Use Python software to identify the original structural design drawings and layout drawings, obtain data for each floor, and establish a model database;

[0008] Step 2: Clean, integrate, and standardize the data from Step 1 to obtain a digital twin model, providing high-quality data support for subsequent analysis and completing the construction of intelligent analysis algorithms;

[0009] Step 3: The digital twin model is trained using machine learning methods. Through historical and simulated data, a machine learning model is trained to predict the safety performance of steel structures. The machine learning model analyzes various data during the construction process in real time and predicts the mechanical response and deformation of the structure, thereby achieving accurate analysis of the structural safety performance.

[0010] Step 4: Establish a conversion interface file for finite element calculation to convert the machine learning model into a finite element analysis model for safe construction stability analysis, so as to reflect the various states of the steel structure in real time during the construction process;

[0011] Step 5: Combine the worker's construction procedures, the performance of on-site construction equipment, the types of materials, the construction methods, and environmental factors to conduct data analysis and processing, identify the key factors affecting stability, and establish an optimization objective function to optimize the parameters;

[0012] Step 6: After finding the optimal parameters, use Python to perform optimization analysis, form a post-processing database, obtain the optimized component dimensions, and re-import the optimized component dimensions into the model to perform the second step of stability calculation, analyze whether it meets the specification requirements, and export the calculation report when the results meet the design requirements.

[0013] In step 1, the data includes parts, components, and bolts.

[0014] The specific operations of step 2 are as follows: Step 2.1 Import the data and verify its integrity; Step 2.2 If the data is complete, normalize it using a normalization formula; if the data is incomplete, handle missing values; Step 2.3 After normalizing the data in step 2.2, divide the dataset.

[0015] The formula for the normalization process is:

[0016] .

[0017] In step 4, the various states during the construction process include mechanical response and deformation. Structural calculations and structural stability verifications are performed under different construction conditions according to different requirements.

[0018] In step 4, the finite element analysis model includes a preprocessing module, a calculation module, and a postprocessing module.

[0019] The beneficial effects of this invention are: it significantly improves the safety and stability of steel structure construction. Through real-time simulation, problems during construction can be identified and resolved promptly, preventing safety accidents. Simultaneously, predictions and optimization suggestions based on machine learning models can guide construction personnel to conduct scientific construction, improving efficiency and quality. Furthermore, the implementation of this invention can reduce construction costs and improve the economic benefits for construction companies. Attached Figure Description

[0020] Figure 1 This is a flowchart of the present invention.

[0021] Figure 2 This is a flowchart for data processing. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] like Figure 1 As shown, an intelligent steel structure safety construction analysis method based on machine learning includes the following steps:

[0024] Step 1: Use Python software to identify the original structural design drawings and layout drawings, obtain data for each floor, and establish a model database; the data includes parts, components, and bolts.

[0025] Step 2: Clean, integrate, and standardize the data from Step 1 to obtain a digital twin model, providing high-quality data support for subsequent analysis and completing the construction of the intelligent analysis algorithm. The specific operations of Step 2 are as follows: Figure 2 As shown, step 2.1 involves importing data and verifying its completeness; step 2.2 involves normalizing the data using a normalization formula if the data is complete, and handling missing values ​​if the data is incomplete; step 2.3 involves partitioning the dataset after normalization in step 2.2. Data normalization normalizes the input variables and output values ​​in the dataset to [0, 1] before subsequent predictions are made.

[0026] The formula for the normalization process is:

[0027] .

[0028] Missing value handling methods: Generally, the data completion method is used; 1) Manual filling: Based on the characteristics of other data values ​​in the data sample, the missing data values ​​are manually filled in. This method has the best data completion effect, but it is not suitable when the number of missing values ​​is large.

[0029] 2) Mean imputation: The missing value is imputed by the average of all other values ​​in the feature corresponding to the missing value. Essentially, it uses the existing data to infer the missing data.

[0030] 3) Nearest imputation: Find the set of numbers most similar to the missing values ​​in the complete data sample, and use the set of data to imput the missing values. The difficulty of this method is that it is difficult to define the similarity standard, and the judgment standard is too subjective.

[0031] Step 3: The digital twin model is trained using machine learning methods. Through historical and simulated data, a machine learning model is trained to predict the safety performance of steel structures. The machine learning model analyzes various data in real time during the construction process and predicts the mechanical response and deformation of the structure, thereby achieving accurate analysis of the structural safety performance.

[0032] Step 4: Establish a conversion interface file for finite element calculation to convert the machine learning model into a finite element analysis model for safe construction stability analysis, so as to reflect the various states of the steel structure in real time during the construction process; Step 5: Combine worker construction procedures, on-site construction equipment performance, material types, construction methods, and environmental factors to perform data analysis and processing, find the key factors affecting stability, and establish an optimization objective function to optimize parameters; The various states in the construction process include mechanical response and deformation. According to different needs, perform structural calculations and structural stability verification under construction conditions.

[0033] The finite element analysis model includes a preprocessing module, a calculation module, and a postprocessing module.

[0034] Preprocessing module

[0035] The preprocessing module is the starting point of the finite element analysis process. Its task is to establish the finite element model and provide all the necessary raw data for subsequent finite element calculations. Specific functions include:

[0036] Geometric modeling: The ability to create, edit, modify, and validate geometries to accurately simulate actual physical structures or systems.

[0037] Material property definition: Define the material properties of different parts or regions in the model, such as elastic modulus, Poisson's ratio, density, etc. These properties will directly affect the analysis results.

[0038] Meshing involves dividing the geometric model into many small, interconnected elements (such as triangles, quadrilaterals, tetrahedrons, etc.) and defining nodes within each element to facilitate numerical computation. The quality of the mesh generation has a significant impact on the accuracy of the analysis results and computational efficiency.

[0039] Boundary conditions and load application: Set the boundary conditions (such as fixed constraints, sliding constraints, etc.) and external loads (such as force, pressure, temperature, etc.) of the model to simulate the physical field under actual working conditions.

[0040] The calculation module is the core of finite element analysis. Its main function is to receive the finite element model information provided by the preprocessing module, solve the finite element equations, and calculate the model's response under specific working conditions. Specific functions include:

[0041] Algorithm selection: Select an appropriate solution algorithm based on the type and complexity of the problem being analyzed, such as the direct method or the iterative method.

[0042] Solution process: Solve the finite element equations to calculate the physical quantities such as displacement, stress, and strain of each node in the model.

[0043] Result saving: Save the solution results to a database or file for subsequent analysis and processing.

[0044] The main task of the post-processing module is to read, process, and display the results from the calculation module, providing analysts with intuitive and easy-to-understand evaluation data. Specific functions include:

[0045] Results visualization: Using graphics and image technology, the calculation results are displayed in the form of contour maps, cloud maps, vector maps, animations, etc., to help analysts intuitively understand the stress distribution, deformation, etc. of the model.

[0046] Data extraction and analysis: Allows users to extract physical quantity values ​​of specific nodes or regions from the results data for further data analysis, such as comparing the differences in results under different working conditions and evaluating the reliability of the model.

[0047] Report generation: Automatically generate reports based on analysis results, including model descriptions, analysis processes, and results presentation, making it easy to share with team members or clients.

[0048] Step 5: Combine the worker's construction procedures, the performance of on-site construction equipment, the types of materials, the construction methods, and environmental factors to conduct data analysis and processing, identify the key factors affecting stability, and establish an optimization objective function to optimize the parameters.

[0049] Step 6: After finding the optimal parameters, use Python to perform optimization analysis, form a post-processing database, obtain the optimized component dimensions, and re-import the optimized component dimensions into the model to perform the second step of stability calculation, analyze whether it meets the specification requirements, and export the calculation report when the results meet the design requirements.

Claims

1. A machine learning-based intelligent steel structure safety construction analysis method, characterized in that: Includes the following steps: Step 1: Use Python software to identify the original structural design drawings and layout drawings, obtain data for each floor, and establish a model database; Step 2: Clean, integrate, and standardize the data from Step 1 to obtain a digital twin model, providing high-quality data support for subsequent analysis and completing the construction of intelligent analysis algorithms; Step 3: Train the machine learning method using a digital twin model. Through historical data and simulated data, train a machine learning model to predict the safety performance of steel structures. Machine learning models analyze various data during the construction process in real time and predict the mechanical response and deformation of the structure, thereby achieving accurate analysis of the structural safety performance. The machine learning method includes six steps: data preparation, feature engineering, model selection, model training, model evaluation and optimization, and model deployment and application. Each step has its specific content and purpose, which together constitute the complete process of machine learning. In practical applications, it is necessary to select appropriate machine learning methods and steps according to the characteristics and needs of the specific problem. Step 4: Establish a conversion interface file for finite element calculation to convert the machine learning model into a finite element analysis model for safe construction stability analysis, so as to reflect the various states of the steel structure in real time during the construction process; Step 5: Combine the worker's construction procedures, the performance of on-site construction equipment, the types of materials, the construction methods, and environmental factors to conduct data analysis and processing, identify the key factors affecting stability, and establish an optimization objective function to optimize the parameters; Step 6: After finding the optimal parameters, use Python to perform optimization analysis, form a post-processing database, obtain the optimized component dimensions, and re-import the optimized component dimensions into the finite element analysis model to perform the second step of stability calculation, analyze whether it meets the specification requirements, and export the calculation report when the results meet the design requirements. In step 1, the data includes parts, components, and bolts; The specific operations of step 2 are as follows: Step 2.1 Import the data and verify its integrity; Step 2.

2. When the data is complete, normalize it using a normalization formula; when the data is incomplete, handle missing values. Step 2.

3. After normalizing the data in step 2.2, the dataset is divided; The formula of the normalization processing is: , wherein: is the maximum value, is the normalized value; In step 4, the various states during the construction process include mechanical response and deformation. Structural calculations and structural stability verifications are performed under different construction conditions according to different requirements. In step 4, the finite element analysis model includes a preprocessing module, a calculation module, and a postprocessing module.

Images