Mapping relationship analysis of welding assembly properties for thin-walled parts with finite element and machine learning algorithm

作     者：Pan Minghui Liao Wenhe Xing Yan Tang Wencheng 潘明辉;廖文和;幸研;汤文成

作者机构：School of Mechanical Engineering Nanjing University of Science and Technology Nanjing 210094 China Digital Forming Technology and Equipment National-Local United Engineering Laboratory Nanjing University of Science and Technology Nanjing 210094 China School of Mechanical Engineering Southeast University Nanjing 211189 China 

出 版 物：《Journal of Southeast University(English Edition)》 (东南大学学报（英文版）)

年 卷 期：2022年第38卷第2期

页      面：126-136页

核心收录：

学科分类：080503[工学-材料加工工程] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：The Natural Science Foundation of Jiangsu Province,China(No.BK20200470) China Postdoctoral Science Foundation(No.2021M691595) Innovation and Entrepreneurship Plan Talent Program of Jiangsu Province(No.AD99002) 

主　　题：parallel T-shaped thin-walled parts welding assembly property finite element analysis mapping relationship machine learning algorithm 

摘      要：The finite element(FE)-based simulation of welding characteristics was carried out to explore the relationship among welding assembly properties for the parallel T-shaped thin-walled parts of an antenna *** effects of welding direction,clamping,fixture release time,fixed constraints,and welding sequences on these properties were analyzed,and the mapping relationship among welding characteristics was thoroughly *** machine learning algorithms,including the generalized regression neural network(GRNN),wavelet neural network(WNN),and fuzzy neural network(FNN),are used to predict the multiple welding properties of thin-walled parts to mirror their variation trend and verify the correctness of the mapping *** with those from GRNN and WNN,the maximum mean relative errors for the predicted values of deformation,temperature,and residual stress with FNN were less than 4.8%,1.4%,and 4.4%,*** results indicate that FNN generated the best predicted welding *** under various welding conditions also shows a mapping relationship among welding deformation,temperature,and residual stress over a period of *** finding further provides a paramount basis for the control of welding assembly errors of an antenna structure in the future.