电焊机2025，Vol.55Issue(12)：1-8,8.DOI:10.7512/j.issn.1001-2303.2025.12.01
错边-间隙模式下熔化极气体保护焊熔透预测与特征分析
Gas Shielded Metal Arc Welding with Misalignment-Gap Mode of Penetration Prediction and Feature Analysis
摘要
Abstract
Gas Metal Arc Welding(GMAW)has found extensive application in engineering fields due to its advantages of low cost,high efficiency,and ease of automation.However,variations in fit-up factors such as mismatch and gap during ac-tual welding processes readily cause instability in the weld poo,rendering real-time monitoring and control of the penetra-tion state in GMAW backing welding challenging.To address this,a dynamic sensing system for groove and weld pool,based on a structured light laser and a High Dynamic Range(HDR)camera,is proposed.This system is used for pre-welding scanning to acquire mismatch and gap groove information,as well as for dynamic measurement of the front dimen-sions of the GMAW weld pool during real-time welding.A dataset of front weld poo images and geometric characteristics of the back bead width under different welding process parameters and fit-up parameters(mismatch and gap)is collected through orthogonal experiments.Furthermore,a Deep Neural Network(DNN)model based on process factors,weld poo im-ages,and fit-up factors is constructed to predict back-side penetration.The SHapley Additive exPlanations(SHAP)interpre-table algorithm is employed to analyze the key factors influencing the penetration state and optimize the DNN model.The re-sults indicate that the performance of the neural network model considering fit-up factors is significantly superior to that of a model solely considering weld poo geometric characteristics.Gap is identified as a crucial factor influencing the size and sta-bility of back-side penetration,as variations in gap can alter the force distribution at the bottom of the weld poo and the inter-nal metal flow pattern.Larger gaps lead to increased liquid metal flowing to the bottom,reducing the stability of back-side penetration.The optimized DNN model meets the requirements of practical welding in terms of prediction accuracy and real-time performance.关键词
人工神经网络/GMAW/深度学习/间隙Key words
artificial neural network/GMAW/deep learning/gap分类
矿业与冶金引用本文复制引用
LI Chunkai,XIE Ruoyu,SHI Yu,WANG Wenkai,WANG Cheng..错边-间隙模式下熔化极气体保护焊熔透预测与特征分析[J].电焊机,2025,55(12):1-8,8.基金项目
兰州市青年科技人才创新项目(2024-QN-121) （2024-QN-121）
国家自然科学基金(52365048) （52365048）
甘肃省科技重大专项(24ZD13GA018) （24ZD13GA018）
宁夏自然科学基金(2023AAC03122) （2023AAC03122）
