基于BP神经网络遗传算法的薄板CMT点焊变形
|
摘要
焊接是汽车车身制造的一个关键环节,焊接质量的好坏严重影响汽车车身质量,所以焊接参数的选择至关重要.针对薄板焊接质量控制问题,论文利用BP神经网络解决非线性问题的优势,建立焊接变形量与工艺参数之间映射关系模型;结合遗传算法构建基于遗传神经网络焊接的工艺参数优化系统;同时设计正交试验,将该方法与正交试验法相对比.结果表明,该方法可以有效地实现CMT(cold metal transfer)点焊焊接变形预测与工艺参数优化.通过预测模型给出合理参数,指导钢薄板和铝合金薄板的CMT点焊变形试验,提高焊接的效率.
Welding was a key link in automobile bodymanufacturing. The quality of welding seriously affected the quality of automobile body, so the selection of welding parameters was very important. Aiming at the quality control of thin plate welding, the advantage of BP neural network was used to solve the non-linear problem, and established the mapping model between welding deformation and process parameters. Combining with genetic algorithm, the optimization system of welding process parameters was constructed based on genetic neural network. Then the orthogonal test was designed and compared with the proposed model. The results showed that the method could effectively achieve welding deformation prediction and optimization of process parameter on CMT(cold metal transfer) spot. The reasonable parameters were given by the prediction model to guide the CMT spot welding deformation test of steel sheet and aluminium alloy sheet, and to improve the welding efficiency.
Welding was a key link in automobile bodymanufacturing. The quality of welding seriously affected the quality of automobile body, so the selection of welding parameters was very important. Aiming at the quality control of thin plate welding, the advantage of BP neural network was used to solve the non-linear problem, and established the mapping model between welding deformation and process parameters. Combining with genetic algorithm, the optimization system of welding process parameters was constructed based on genetic neural network. Then the orthogonal test was designed and compared with the proposed model. The results showed that the method could effectively achieve welding deformation prediction and optimization of process parameter on CMT(cold metal transfer) spot. The reasonable parameters were given by the prediction model to guide the CMT spot welding deformation test of steel sheet and aluminium alloy sheet, and to improve the welding efficiency.
引文
[1]Rodriguez N,Vazquez L,Huarte L,et al.Wire and arc additive manufacturing:a comparison between CMT and top TIG processes applied to stainless steel[J].Welding in the World,2018,62(5):1083-1096.
[2]崔晴晴.铝合金和镀锌钢的CMT焊接技术研究[D].江苏:江苏科技大学,2012.
[3]程方杰,李慧娟,廉金瑞,等.焊接参数变化对点焊质量的影响[J].汽车技术,2005(4):35-37.Cheng Fangjie,Li Huijuan,Lian Jinrui,et al.Influence of variation of welding parameters on spot welding quality[J].Automobile Technology,2005(4):35-37.
[4]彭金宁,陈炳森,朱平.焊接工艺参数的神经网络智能设计[J].焊接学报,1998,19(1):19-23.Peng Jinning,Chen Bingsen,Zhu Ping.Intelligent design of welding procedure parameters based on neural networks[J].Transactions of the China Welding Institution,1998,19(1):19-23.
[5]张鹏贤,李浩,张杰.一种冷丝填充速度的GABP优化算法[J].焊接学报,2012,33(12):77-80.Zhang Pengxian,Li Hao,Zhang Jie.A GABP optimized algorithm for filler rate of non-heated wire[J].Transactions of the China Welding Institution,2012,33(12):77-80.
[6]张玉宝,苟建军,张恩慧,等.基于改进遗传神经网络的SMAW焊接变形预测[J].热加工工艺,2015,44(1):208-210.Zhang Yubao,Gou Jianjun,Zhang Enhui,et al.Welding deformation prediction of SMAW based on improved genetic neural network[J].Hot Working Technology,2015,44(1):208-210.
[7]Nie Y P,Zhang P L,Wu X,et al.Rapid prototyping of 4043 Alalloy parts by cold metal transfer[J].Science and Technology Welding and Joining,2018,23(6):527-535.
[8]陈达亮,李洪亮,顾灿松,等.副车架系统边界约束对计算模态分析精度的影响研究[J].汽车技术,2016(4):27-30.Chen Daliang,Li Hongliang,Gu Cansong,et al.The effect of subframe system boundary constraints on accuracy of computational modal analysis[J].Automobile Technology,2016(4):27-30.
[9]林惠乐.基于遗传神经网络的CO2弧焊机器人工艺参数优化研究[D].广西:广西大学,2015.
[10]Lin W Y,Ren X Y,Zhou T T,et al.A novel robust algorithm for position and orientation detection based on cascaded deep neural network[J].Neurocomputing,2018,308:138-146.
[2]崔晴晴.铝合金和镀锌钢的CMT焊接技术研究[D].江苏:江苏科技大学,2012.
[3]程方杰,李慧娟,廉金瑞,等.焊接参数变化对点焊质量的影响[J].汽车技术,2005(4):35-37.Cheng Fangjie,Li Huijuan,Lian Jinrui,et al.Influence of variation of welding parameters on spot welding quality[J].Automobile Technology,2005(4):35-37.
[4]彭金宁,陈炳森,朱平.焊接工艺参数的神经网络智能设计[J].焊接学报,1998,19(1):19-23.Peng Jinning,Chen Bingsen,Zhu Ping.Intelligent design of welding procedure parameters based on neural networks[J].Transactions of the China Welding Institution,1998,19(1):19-23.
[5]张鹏贤,李浩,张杰.一种冷丝填充速度的GABP优化算法[J].焊接学报,2012,33(12):77-80.Zhang Pengxian,Li Hao,Zhang Jie.A GABP optimized algorithm for filler rate of non-heated wire[J].Transactions of the China Welding Institution,2012,33(12):77-80.
[6]张玉宝,苟建军,张恩慧,等.基于改进遗传神经网络的SMAW焊接变形预测[J].热加工工艺,2015,44(1):208-210.Zhang Yubao,Gou Jianjun,Zhang Enhui,et al.Welding deformation prediction of SMAW based on improved genetic neural network[J].Hot Working Technology,2015,44(1):208-210.
[7]Nie Y P,Zhang P L,Wu X,et al.Rapid prototyping of 4043 Alalloy parts by cold metal transfer[J].Science and Technology Welding and Joining,2018,23(6):527-535.
[8]陈达亮,李洪亮,顾灿松,等.副车架系统边界约束对计算模态分析精度的影响研究[J].汽车技术,2016(4):27-30.Chen Daliang,Li Hongliang,Gu Cansong,et al.The effect of subframe system boundary constraints on accuracy of computational modal analysis[J].Automobile Technology,2016(4):27-30.
[9]林惠乐.基于遗传神经网络的CO2弧焊机器人工艺参数优化研究[D].广西:广西大学,2015.
[10]Lin W Y,Ren X Y,Zhou T T,et al.A novel robust algorithm for position and orientation detection based on cascaded deep neural network[J].Neurocomputing,2018,308:138-146.