A welding deformation simulation system and method for steel structure construction process

Abstract

The present application relates to a kind of steel structure construction process welding deformation simulation system and method thereof, the system includes data preprocessing system, feature analysis system and deformation process simulation system.Wherein, data preprocessing system includes data acquisition module and data cleaning module two modules;Feature analysis system includes geometric feature identification module and material and mechanical characteristic extraction module two modules;Deformation process simulation system includes parameter fine-tuning module, multi-source influence analysis module and process deformation analysis module three modules.The system, based on the welding deformation of typical section steel structure component to the basic model pre-training, and adjusts key parameters, to ensure that model can accurately simulate the deformation under a variety of load combinations, and the geometric, material and mechanical characteristics of non-typical section steel structure are converted into equivalent parameters that pre-training model can understand, to improve the prediction ability of model to non-typical section.

Description

Technical Field

[0001] This invention belongs to the field of building construction technology, and specifically relates to a welding deformation simulation system and method for steel structure construction process. Background Technology

[0002] Welding deformation is a complex issue during steel structure construction, influenced by various factors such as welding process parameters, material properties, environmental conditions, and welding sequence. This makes the deformation behavior during welding difficult to predict and control. Currently, simulations of welding deformation in typical steel structures mainly employ traditional finite element analysis methods such as the thermo-elastic-plastic method and the inherent strain method, or neural network models to predict welding deformation. However, traditional finite element analysis methods are computationally expensive, require continuous improvement of the strain database, and do not consider the varying degrees of deformation that occur during steel structure fabrication, transportation, and on-site installation, thus failing to guarantee the accuracy and reliability of finite element analysis.

[0003] Therefore, how to provide a welding deformation simulation system and method for steel structure construction is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] To address the issues of low accuracy and reliability in traditional welding deformation prediction methods, this invention proposes a welding deformation simulation system and method for steel structure construction. Welding deformation is a complex issue during steel structure construction, influenced by various factors such as welding process parameters, material properties, environmental conditions, and welding sequence, making deformation behavior during welding difficult to predict and control. Currently, welding deformation simulation for typical steel structures mainly employs traditional finite element analysis methods such as the thermo-elastic-plastic method and the inherent strain method, or neural network models to predict welding deformation. However, traditional finite element analysis methods are computationally expensive, require continuous improvement of the strain database, and do not consider the varying degrees of deformation that occur to components during steel structure fabrication, transportation, and on-site installation, thus failing to guarantee the accuracy and reliability of finite element analysis.

[0005] To solve the above technical problems, the present invention includes the following technical solutions:

[0006] A welding deformation simulation system for steel structure construction process, comprising:

[0007] A data preprocessing system that collects welding deformation data of typical cross-section steel structure components at different construction stages;

[0008] A feature analysis system analyzes the characteristics of atypical cross-section steel structures and extracts their geometric, material, and mechanical features.

[0009] The deformation process simulation system integrates the model's prediction results into various construction management processes, simulating different degrees of deformation that occur during the fabrication, transportation, and on-site installation of steel structure components.

[0010] Furthermore, the data preprocessing system includes two modules: a data acquisition module and a data cleaning module. The data acquired by the data acquisition module includes welding process parameters, material properties, environmental conditions, welding sequence, and welding deformation results. The data cleaning module preprocesses the data, including normalization to eliminate the influence of dimensions, and data cleaning to remove outliers and noise.

[0011] Furthermore, the feature analysis system includes two modules: a geometric feature recognition module and a material and mechanical feature extraction module. The geometric feature recognition module maps the features of atypical cross-sections to a feature space that the pre-trained model can understand, decomposes it into a combination of several simple geometric shapes, calculates equivalent geometric parameters, and uses these equivalent parameters as input features of the pre-trained model. The material and mechanical feature extraction module is used to integrate the extracted material properties and mechanical features into a set of feature vectors, which will be used in the training and prediction process of the model.

[0012] Furthermore, the deformation process simulation system includes three modules: a parameter fine-tuning module, a multi-source influence analysis module, and a process deformation analysis module. The parameter fine-tuning module selects a machine learning model to pre-train the collected data. The multi-source influence analysis module considers various influencing factors in the welding process to process multi-source data and improve prediction accuracy. The process deformation analysis module applies the model's prediction results to the actual construction process and simulates the welding deformation that may occur in steel structure components during processing, transportation, and on-site installation.

[0013] Furthermore, the parameter fine-tuning module pre-trains the collected data by adjusting the model parameters during the pre-training process so that the model can accurately simulate the deformation of the component under various load combinations. The parameters include material constitutive relation parameters, element type selection, and mesh generation parameters in the finite element model.

[0014] Furthermore, the multi-source influence analysis module considers various influencing factors in the welding process, including material anisotropy, welding sequence, and environmental conditions.

[0015] This invention also provides a method for simulating welding deformation during steel structure construction, the method comprising:

[0016] Step S1: Use the welding deformation simulation system for the steel structure construction process;

[0017] Step S2: The data acquisition module of the data preprocessing system completes the welding deformation data of typical cross-section steel structure components at different construction stages, and the data is preprocessed by the data cleaning module.

[0018] Step S3: The geometric feature recognition module of the feature analysis system decomposes the features of the atypical cross section into a combination of geometric shapes, calculates the equivalent moment of inertia or equivalent area, and uses it as the input feature of the pre-trained model; the material and mechanics feature extraction module integrates the yield strength, elastic modulus, coefficient of thermal expansion, elasticity, plasticity and fracture characteristics into a set of feature vectors.

[0019] Step S4: Select a machine learning model through the deformation process simulation system to pre-train the collected data, adjust the model parameters so that the model can accurately simulate the deformation of the component under various load combinations, and use random forest or gradient booster to process multi-source data and improve prediction accuracy. Apply the prediction results of the model to the actual construction process to simulate the welding deformation that may occur in the steel structure component during processing, transportation and on-site installation.

[0020] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0021] This invention provides a welding deformation simulation system and method for steel structure construction. The system includes a data preprocessing system, a feature analysis system, and a deformation process simulation system. The data preprocessing system comprises a data acquisition module and a data cleaning module; the feature analysis system comprises a geometric feature recognition module and a material and mechanical feature extraction module; and the deformation process simulation system comprises a parameter fine-tuning module, a multi-source influence analysis module, and a process deformation analysis module. This welding deformation simulation system for steel structure components considering multi-source influences pre-trains a basic model based on the welding deformation of typical cross-section steel structure components, adjusting key parameters such as material constitutive relations, element types, and mesh generation to ensure the model can accurately simulate deformation under various load combinations. Furthermore, it transforms the geometric, material, and mechanical characteristics of atypical cross-section steel structures into equivalent parameters that the pre-trained model can understand, such as equivalent moments of inertia and areas, thereby improving the model's predictive ability for atypical cross-sections.

[0022] Compared with traditional methods, the main advantages of this invention are as follows:

[0023] (1) Generalization ability: By mapping features such as atypical cross sections and materials to the feature space that the pre-trained model can understand, the model’s generalization ability for different types of steel structures is enhanced.

[0024] (2) Comprehensive consideration of multiple influencing factors: Comprehensive consideration of multiple influencing factors in the welding process, which is often difficult to achieve in traditional simulation methods, thereby improving the reliability of simulation results.

[0025] (3) Integration of construction process: The prediction results of the model are integrated into the specific construction process, so that the simulation results can be directly applied to each actual construction process, thereby improving construction efficiency and quality. Attached Figure Description

[0026] Figure 1 This is a system architecture diagram of a welding deformation simulation system for steel structure construction process in one embodiment of the present invention. Detailed Implementation

[0027] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, provides a welding deformation simulation system and method for steel structure construction provided by the present invention. The advantages and features of the present invention will become clearer from the following description.

[0028] Example 1

[0029] The following is combined Figure 1 This invention provides a detailed description of the welding deformation simulation system for the steel structure construction process.

[0030] Please refer to Figure 1 A welding deformation simulation system for steel structure construction includes a data preprocessing system, a feature analysis system, and a deformation process simulation system. The data preprocessing system comprises two modules: a data acquisition module and a data cleaning module. The feature analysis system includes two modules: a geometric feature recognition module and a material and mechanical feature extraction module. The deformation process simulation system includes three modules: a parameter fine-tuning module, a multi-source influence analysis module, and a process deformation analysis module. This welding deformation simulation system for steel structure components considering multi-source influence pre-trains a basic model based on the welding deformation of steel structure components with typical cross-sections, and adjusts key parameters such as material constitutive relations, element types, and mesh generation to ensure the model can accurately simulate deformation under various load combinations. Furthermore, it transforms the geometric, material, and mechanical characteristics of atypical cross-section steel structures into equivalent parameters that the pre-trained model can understand, such as equivalent moments of inertia and areas, thereby improving the model's predictive ability for atypical cross-sections.

[0031] In this embodiment, more preferably, the data preprocessing system is mainly responsible for collecting welding deformation data of typical cross-section steel structure components at different construction stages; the feature analysis system is mainly responsible for analyzing the characteristics of atypical cross-section steel structures and extracting their geometric, material, and mechanical characteristics; the deformation process simulation system is mainly responsible for considering multiple influencing factors, integrating the model's prediction results into various construction management processes, and simulating the different degrees of deformation generated during the fabrication, transportation, and on-site installation of steel structure components.

[0032] In this embodiment, more preferably, the data preprocessing system consists of two modules: a data acquisition module and a data cleaning module. The data acquisition module collects welding deformation data of typical cross-section steel structural members at different construction stages. This data should include welding process parameters, material properties, environmental conditions, welding sequence, and the results of welding deformation. The data cleaning module preprocesses the data, including normalization to eliminate the influence of dimensions, and data cleaning to remove outliers and noise.

[0033] In this embodiment, more preferably, the feature analysis system consists of two modules: a geometric feature recognition module and a material and mechanical feature extraction module. The geometric feature recognition module maps the features of atypical cross-sections to a feature space understandable by the pre-trained model, decomposes it into a combination of several simple geometric shapes, calculates equivalent geometric parameters (such as equivalent moment of inertia, equivalent area, etc.), and uses these equivalent parameters as input features for the pre-trained model. The material and mechanical feature extraction module integrates the extracted material properties (such as yield strength, elastic modulus, coefficient of thermal expansion, etc.) and mechanical features (including elasticity, plasticity, fracture characteristics, etc.) into a set of feature vectors. These feature vectors are used in the model training and prediction process.

[0034] In this embodiment, more preferably, the deformation process simulation system consists of three modules: a parameter fine-tuning module, a multi-source influence analysis module, and a process deformation analysis module. The parameter fine-tuning module selects a suitable machine learning model to pre-train the collected data. During pre-training, the model's parameters are adjusted, such as material constitutive relation parameters, element type selection, and mesh generation parameters in the finite element model, enabling the model to accurately simulate the deformation of components under various load combinations. The multi-source influence analysis module considers various influencing factors in the welding process, such as material anisotropy, welding sequence, and environmental conditions, and uses machine learning algorithms, such as random forests or gradient boosting machines (GBM), to process multi-source data and improve prediction accuracy. The process deformation analysis module applies the model's prediction results to the actual construction process and simulates the welding deformation that may occur in steel structure components during processing, transportation, and on-site installation.

[0035] Please continue to refer to this. Figure 1The present invention also provides a method for simulating welding deformation during steel structure construction, the method comprising:

[0036] Step S1: Use the welding deformation simulation system for the steel structure construction process;

[0037] Step S2: The data acquisition module of the data preprocessing system completes the welding deformation data of typical cross-section steel structure components at different construction stages, and the data is preprocessed by the data cleaning module.

[0038] Step S3: The geometric feature recognition module of the feature analysis system decomposes the features of the atypical cross section into a combination of geometric shapes, calculates the equivalent moment of inertia or equivalent area, and uses it as the input feature of the pre-trained model; the material and mechanics feature extraction module integrates the yield strength, elastic modulus, coefficient of thermal expansion, elasticity, plasticity and fracture characteristics into a set of feature vectors.

[0039] Step S4: Select a machine learning model through the deformation process simulation system to pre-train the collected data, adjust the model parameters so that the model can accurately simulate the deformation of the component under various load combinations, and use random forest or gradient booster to process multi-source data and improve prediction accuracy. Apply the prediction results of the model to the actual construction process to simulate the welding deformation that may occur in the steel structure component during processing, transportation and on-site installation.

[0040] The above examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. The above embodiments only illustrate several implementations of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A welding distortion simulation system for a steel structure construction process, characterized by, Comprising: a data preprocessing system that collects welding deformation data of typical cross-section steel structural members at different construction stages; the data preprocessing system includes a data acquisition module and a data cleaning module, the data acquisition module collects data including welding process parameters, material properties, environmental conditions, welding sequence, and the results of welding deformation; the data cleaning module preprocesses the data, including normalization to eliminate the influence of dimensions, and cleaning the data to remove outliers and noise; a feature analysis system that analyzes the features of atypical cross-section steel structures and extracts geometric, material, and mechanical features of atypical cross-section steel structures; the feature analysis system includes a geometric feature recognition module and a material and mechanical feature extraction module, the geometric feature recognition module maps the features of the atypical cross-section to a feature space that the pre-trained model can understand, and decomposes it into a combination of several simple geometric shapes, calculates the equivalent geometric parameters, and uses these equivalent parameters as input features of the pre-trained model; the material and mechanical feature extraction module is used to integrate the extracted material properties and mechanical features into a set of feature vectors, which will be used in the training and prediction process of the model; a deformation process simulation system that integrates the prediction results of the model into various construction management processes to simulate different degrees of deformation of steel structural members during production, transportation, and on-site installation; the deformation process simulation system includes a parameter fine-tuning module, a multi-source influence analysis module, and a process deformation analysis module, the parameter fine-tuning module selects a machine learning model to pre-train the collected data; the multi-source influence analysis module considers various influencing factors in the welding process to process multi-source data and improve prediction accuracy; the process deformation analysis module applies the prediction results of the model to the actual construction process and simulates the welding deformation that may occur during the processing, transportation, and on-site installation of steel structural members.

2. The welding distortion simulation system for a steel construction process according to claim 1, characterized by, The parameter fine-tuning module pre-trains the collected data, including adjusting the parameters of the model during pre-training to enable the model to accurately simulate the deformation of the member under various load combinations, the parameters include material constitutive relationship parameters in the finite element model, element type selection, and meshing parameters.

3. The welding distortion simulation system for a steel construction process according to claim 2, characterized by, The multi-source influence analysis module considers various influencing factors in the welding process, including material anisotropy, welding sequence, and environmental conditions.

4. A method of simulating welding distortion in a steel construction process, characterized by, Comprising: Step S1, using the welding deformation simulation system of the steel structure construction process according to any one of claims 1 to 3; Step S2, collecting welding deformation data of typical cross-section steel structural members at different construction stages through the data acquisition module of the data preprocessing system, and preprocessing the data through the data cleaning module; Step S3, decomposing the features of the atypical cross-section into a combination of geometric shapes through the geometric feature recognition module of the feature analysis system, calculating the equivalent moment of inertia or equivalent area, and using them as input features of the pre-trained model; The yield strength, the elastic modulus, the thermal expansion coefficient, the elasticity, the plasticity and the fracture characteristics are integrated into a group of characteristic vectors by the material and mechanics characteristic extraction module; In step S4, the collected data is pre-trained by selecting a machine learning model through the deformation process simulation system, the model parameters are adjusted, the model can accurately simulate the deformation of the component under various load combinations, random forest or gradient boosting machine is used to process multi-source data and improve the prediction accuracy, and the prediction result of the model is applied to the actual construction process, so as to simulate the welding deformation of the steel structure component that may be generated in the processing, transportation and on-site installation process.

Images