宇航材料工艺2018，Vol.48Issue(3)：33-37,5.DOI:10.12044/j.issn.1007-2330.2018.03.007
基于遗传算法与神经网络微电阻点焊工艺参数优化
Optimization of Micro Resistance Spot Welding Process Parameters Based on Genetic Algorithm and Neural Network
摘要
Abstract
The setting of micro resistance spot welding parameters plays an important role in the shear force and peel force,through the range analysis of orthogonal test and the influence of process parameters on the shear force and peel force of thickness of 0.05 mm foil TC1 resistance spot welding was investigetal.By giving the corresponding values of shear force and peeling force,the bi-objective optimization is transformed into a single hybrid objective optimization,BP neural network and genetic algorithm are combined to optimize the process parameters.A prediction model of the mechanical properties of solder joints based on BP neural network is established.The prediction results show that the error is less than 4％,indicating that the network model has higher prediction accuracy and ability.It can predict the mechanical properties of solder joints accurately.At the same time,with the global optimization ability of genetic algorithm,the parameters of spot welding are optimized,and the optimum combination of welding parameters is obtained:welding current 800 A,electrode pressure 8.89 N,ramping time 1.608 ms,welding time 8 ms,hybrid target force value 55.73 N.By comparing the results of orthogonal test,genetic algorithm optimization can get better comprehensive mechanical performance.关键词
微电阻点焊/TC1箔材/正交试验/BP神经网络/遗传算法/参数优化Key words
Micro resistance spot welding/TC1/Orthogonal test/BP neural network/Genetic algorithm/Parameter optimization分类
矿业与冶金引用本文复制引用
高星鹏,陈峰,王宇盛,黄翔,童国权..基于遗传算法与神经网络微电阻点焊工艺参数优化[J].宇航材料工艺,2018,48(3):33-37,5.基金项目
南京航空航天大学研究生创新基地(实验室)开放基金(kfjj20160501) （实验室）
