CN-121997410-A - Green low-carbon intelligent assessment method for welding influence of steel structure

CN121997410ACN 121997410 ACN121997410 ACN 121997410ACN-121997410-A

Abstract

The invention discloses a green low-carbon intelligent assessment method for welding influence of a steel structure, which relates to the technical field of green construction and construction, and comprises the steps of collecting multi-source heterogeneous data of a steel structure welding process in real time, and calculating and visualizing a carbon emission dynamic value in the welding process; and carrying out iterative simulation in the twin welding model based on the carbon emission dynamic value and the weld defect recognition result and aiming at minimizing carbon emission and residual stress, and optimizing to obtain a low-carbon-low-stress process parameter window. The invention solves the technical problems that the traditional steel structure welding related evaluation mode cannot give consideration to low-carbon requirements and mechanical property guarantees, the evaluation result is one-sided and the parameter suitability is insufficient, and achieves the technical effects of realizing the cooperative guarantee of welding low carbon and low stress, and enabling the green low-carbon evaluation and process optimization of the steel structure welding to be more accurate and efficient.

Inventors

ZHANG LIGONG
ZHANG YONGAN
LIU ZHENGHUI
GUO LIMING
ZHANG PENGBO
FAN ZEKAI
WANG CHENG
PAN XINAN
TAN CHAO
YAN WENZHI
SUN ZHIGUO

Assignees

中交建筑集团有限公司

Dates

Publication Date: 20260508
Application Date: 20251223

Claims (8)

1. A green low-carbon intelligent evaluation method for welding influence of a steel structure is characterized by comprising the following steps: the method comprises the steps of collecting multisource heterogeneous data of a steel structure welding process in real time, driving a twin welding model to operate, and calculating and visualizing a carbon emission dynamic value in the welding process in real time; Extracting parameters of the multi-source heterogeneous data, inputting the parameters into a pre-trained defect identification model, identifying and classifying weld defects in real time, and correlating causal relations between defects and technological parameters to obtain weld defect identification results; And based on the carbon emission dynamic value and the weld defect identification result, carrying out iterative simulation in the twin welding model with the aim of minimizing carbon emission and residual stress, and optimizing to obtain a low-carbon low-stress process parameter window.
2. The method for intelligently evaluating the welding influence of a steel structure according to claim 1, wherein the multi-source heterogeneous data comprises welding process parameters, environment parameters, weld morphology point cloud data, welding temperature field space-time distribution data and welding stress evolution data.
3. The method for intelligently evaluating the welding influence of a steel structure in green and low-carbon manner according to claim 1, wherein the method for intelligently evaluating the welding influence of the steel structure in green and low-carbon manner is characterized by collecting multisource heterogeneous data of the welding process of the steel structure in real time, driving a twin welding model to operate, and calculating and visualizing a carbon emission dynamic value in the welding process in real time, and comprises the following steps: Establishing a dynamic calculation model containing direct carbon emission and indirect carbon emission; Driving the twin welding model to operate by the multi-source heterogeneous data, and calling the dynamic calculation model to calculate direct carbon emission and indirect carbon emission to form a green factor matrix; And carrying out weighted quantitative evaluation based on the green factor matrix to generate the carbon emission dynamic value.
4. The method for intelligently evaluating the welding influence of the steel structure according to claim 3, wherein the direct carbon emission is dynamically calculated based on real-time electric energy consumption data and regional power grid carbon emission factors, and the indirect carbon emission is converted based on welding material consumption rate, shielding gas flow and post-welding treatment material consumption.
5. The method for intelligently evaluating the welding influence of the steel structure in green and low carbon according to claim 1, wherein the method for intelligently evaluating the welding influence of the steel structure is characterized in that the multi-source heterogeneous data is input into a pre-trained defect recognition model after parameter extraction, welding defects are recognized and classified in real time, and causal relations between the defects and technological parameters are associated to obtain a welding defect recognition result, and the method comprises the following steps: Extracting characteristic parameters related to the spatial position and the time sequence from the multi-source heterogeneous data to form a characteristic space-time matrix of the welding process; Inputting submatrices related to weld morphology and thermal processes in the characteristic space-time matrix into a pre-trained defect recognition model, wherein the defect recognition model is a mixed framework of a convolutional neural network and an attention mechanism and is used for synchronously processing imaged temperature field distribution data and point cloud weld surface data; outputting the defect type and the three-dimensional space coordinate of the welding line area through the defect identification model; And performing time sequence association matching on the defect type and the three-dimensional space coordinate and welding process parameters at corresponding moments, determining a key parameter deviation event causing defects through causal inference analysis, and obtaining the weld defect identification result.
6. The method for intelligently evaluating the welding influence of a steel structure according to claim 1, wherein the iterative simulation is performed in the twin welding model with the aim of minimizing carbon emissions and residual stresses based on the carbon emission dynamic value and the weld defect recognition result, and optimizing to obtain a low-carbon low-stress process parameter window comprises: Setting welding current, voltage, speed, interlayer temperature and welding sequence as optimization variables in the twin welding model, and setting a process allowable range as a search space; generating a plurality of groups of candidate process parameter combinations in the search space based on the weld defect recognition result by adopting a multi-objective optimization algorithm; And aiming at each group of candidate process parameter combinations, driving the twin welding model to perform quick simulation, performing thermal-mechanical coupling calculation residual stress distribution, synchronously calling a dynamic calculation model to predict carbon emission values, and screening out a process parameter set meeting the dual constraint of green low carbon and mechanical properties as the low carbon-low stress process parameter window.
7. The green low-carbon intelligent assessment method for welding influence of a steel structure according to claim 6, wherein when the twin welding model is driven to perform rapid simulation, a proxy model is introduced, a kriging proxy model is trained in advance through a high-fidelity simulation sample aiming at repeated heat source loading and heat transfer calculation, and the twin welding model is driven after a repeated physical simulation process is performed.
8. The method for intelligently evaluating the welding influence of a steel structure according to claim 1, wherein after optimizing the low-carbon and low-stress process parameter window, the method further comprises: Pushing the low-carbon low-stress process parameter window and the corresponding predicted performance index to a welding control terminal; Establishing a real-time monitoring closed loop at a welding control terminal, continuously collecting actual welding data, calculating actual carbon emission intensity and stress signals monitored through acoustic emission, and comparing the actual carbon emission intensity with the predicted performance index in real time; When the deviation exceeds a preset tolerance, restarting local iterative optimization according to the direction and the size of the deviation.

Description

Green low-carbon intelligent assessment method for welding influence of steel structure Technical Field The invention relates to the technical field of green construction, in particular to a green low-carbon intelligent evaluation method for welding influence of a steel structure. Background The green low carbon is an important development trend in the steel structure manufacturing industry, the welding is used as a core process, the carbon emission, the weld defects and the residual stress of the welding directly affect the structural safety and the low carbon target to achieve, and the accurate assessment and the process optimization are very important. In the prior art, the welding evaluation of the steel structure usually considers the low-carbon requirement and the mechanical property separately, relies on experience judgment or single data detection, and lacks an integrated intelligent evaluation means. The method has obvious limitations in complex welding scenes that the whole-flow carbon emission cannot be quantified in real time, the defect identification and the technological parameter association are inaccurate, and the technological parameters are mostly statically set and are difficult to adapt to the dynamic welding process. The evaluation result is one-sided, and the accurate control requirement of the dual guarantee of the green low carbon and the mechanical property of the steel structure welding cannot be met. Disclosure of Invention The application solves the technical problems that the traditional steel structure welding related evaluation mode cannot meet the low-carbon requirement and the mechanical property guarantee, the evaluation result is one-sided and the parameter suitability is insufficient. Aiming at the technical problems, the application provides a green low-carbon intelligent assessment method for welding influence of a steel structure, which comprises the steps of collecting multi-source heterogeneous data of a welding process of the steel structure in real time, driving a twin welding model to operate, calculating and visualizing a carbon emission dynamic value in the welding process in real time, extracting parameters of the multi-source heterogeneous data, inputting the parameters into a pre-trained defect identification model, identifying and classifying weld defects in real time, correlating causal relation between the defects and technological parameters to obtain a weld defect identification result, and carrying out iterative simulation in the twin welding model based on the carbon emission dynamic value and the weld defect identification result with the aim of minimizing carbon emission and residual stress to obtain a low-carbon low-stress technological parameter window by optimizing. The application provides one or more technical schemes, which at least have the following technical effects: According to the application, the multisource data of the welding process of the steel structure is collected in real time, the twin model is driven to calculate the carbon emission dynamic value, the related result is obtained through the causal relation processing of the defect identification and the technological parameter, the iterative simulation optimizing parameter of the twin model is combined with the twin object, and the cooperative guarantee of low carbon and low stress of the welding is achieved through the real-time monitoring and the closed-loop continuous comparison adjustment, so that the technical effects of more accurate and efficient green low carbon assessment and technological optimization of the welding of the steel structure are achieved. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 is a schematic flow chart of a green low-carbon intelligent evaluation method for welding influence of a steel structure. Fig. 2 is a schematic flow chart of calculating a carbon emission dynamic value in a green low-carbon intelligent assessment method for welding influence of a steel structure according to an embodiment of the present application. Detailed Description The application provides a green low-carbon intelligent assessment method for the welding influence of a steel structure, which solves the technical problems that the traditional steel structure welding related assessment mode cannot give consideration to low-carbon requirements and mechanical property guarantee, and the assessment result is one-sided and the parameter suitability is insufficient. The technical solutions in the embodiments of the present application will be clearly and completely described bel