Optimal Design for Laser Oscillating Welding Process Parameter Based on Artificial Neural Networks and Genetic Algorithm for Aluminum Alloy

Chao LIANG; Xiong ZHANG; Gaoyang MI; Chunming WANG

doi:10.7512/j.issn.1001-2303.2022.08.06

Important Issuse | Views : 0 下载量: 8 CSCD: 0

PDF
Export
Share
Collection
Album

Optimal Design for Laser Oscillating Welding Process Parameter Based on Artificial Neural Networks and Genetic Algorithm for Aluminum Alloy
Vol. 52, Issue 8, Pages: 43-49(2022)
DOI： 10.7512/j.issn.1001-2303.2022.08.06

扫描看全文

梁超，张熊，米高阳，等.基于神经网络与遗传算法的铝合金激光摆动焊工艺参数优化［J］.电焊机，2022，52（8）：43-49.

LIANG Chao, ZHANG Xiong, MI Gaoyang, et al.Optimal Design for Laser Oscillating Welding Process Parameter Based on Artificial Neural Networks and Genetic Algorithm for Aluminum Alloy[J].Electric Welding Machine, 2022, 52(8): 43-49.
梁超，张熊，米高阳，等.基于神经网络与遗传算法的铝合金激光摆动焊工艺参数优化［J］.电焊机，2022，52（8）：43-49. DOI： 10.7512/j.issn.1001-2303.2022.08.06.

LIANG Chao, ZHANG Xiong, MI Gaoyang, et al.Optimal Design for Laser Oscillating Welding Process Parameter Based on Artificial Neural Networks and Genetic Algorithm for Aluminum Alloy[J].Electric Welding Machine, 2022, 52(8): 43-49. DOI： 10.7512/j.issn.1001-2303.2022.08.06.

摘要

铝合金焊接时容易产生气孔，严重影响焊缝的力学性能。激光摆动焊接工艺可以显著降低铝合金焊接过程中的气孔率，提高接头拉伸强度，但其工艺参数繁多且互相影响，很难直接对工艺参数进行优化。因此设计了18组正交试验，通过极差分析研究了不同工艺参数对气孔率的影响程度，并通过正交优化设计对工艺参数进行优化。通过不同的学习算法建立BP神经网络，结果表明使用BR算法的模型均方误差最小，预测性能最好。采用遗传算法结合BP神经网络对焊缝性能和焊接效率进行多目标优化，获得的焊缝拉伸强度相比正交优化所得焊缝提升了3.02%，焊接效率提升了18.3%。BP神经网络-遗传算法组合模型可在保证焊接性能的同时提高焊接效率。

Abstract

Aluminum alloys tend to produce pores during welding, which critically affects the mechanical properties of the weld. The laser oscillating welding can significantly reduce the porosity of aluminum alloy welding. However, it is very difficult to figure out and optimize the welding parameters since they are in a complex relationship. To study and figure out the influence of different parameters on porosity, 18 sets of orthogonal experiments are designed followed by the analysis of variance. In addition, the welding parameters are optimized by the analysis of variance. The multi-objective optimization of weld performance and welding efficiency are carried out by using genetic algorithm combined with BP neural network. The tensile strength of the weld optimized by genetic algorithm is increased by 3.02% and the welding efficiency is increased by 18.3% compared with the orthogonal optimization. Therefore, the combined model of BP neural network and genetic algorithm can improve welding efficiency while ensuring welding performance.

关键词

激光摆动焊正交试验BP神经网络遗传算法参数优化

Keywords

laser oscillating weldingorthogonal testbackward propagation neural networkgenetic algorithmparameter optimization

references

Kabasakaloglu T S， Erdogan M. Characterization of figure-eight shaped oscillation laser welding behavior of 5083 aluminium alloy［J］. Science and Technology of Welding & Joining， 2020， 25（7）： 609-616.

Wang Zhimin， Oliveira J P， Zeng Zhi， et al. Laser beam oscillating welding of 5A06 aluminum alloys： Microstructure， porosity and mechanical properties［J］. Optics & Laser Technology， 2018， 111： 58-65.

Wang Lei， Gao Ming， Zhang Chen. Effect of beam oscillating pattern on weld characterization of laser welding of AA6061-T6 aluminum alloy［J］. Materials & design， 2016， 108： 707-717.

余世文，周昆，张威，等. 6.0 mm厚5183铝合金激光摆动焊接工艺研究［J］. 激光技术， 2018， 42（02）： 254-258.

Yu Shiwen， Zhou Kun， Zhang Wei， et al. Laser -weaving welding of 5183 aluminum alloy plate with 6.0mm thickness［J］. Laser Technology， 2018， 42（02）： 254-258.

Shanavas S， Dhas J. Weld quality prediction of AA 5052-H32 aluminium alloy using neural network approach［J］. Materials today： proceedings， 2018， 5（2）： 8256-8262.

Kannan T， Ramesh T， Sathiya P. Application of Artificial Neural Network Modelling for Optimization of Yb： YAG Laser Welding of Nitinol［J］. Transactions of the Indian Institute of Metals， 2016， 70（7）： 1763-177.

Choudhury B， Chandrasekaran M. Gas Tungsten Arc Welding of Inconel 825 Sheet： Study on Weld Bead Geometry and GA Optimization［C］. Advances in Materials and Manufacturing Engineering， ICAMME 2019.

Chandrasekhar N， Ragavendran M， Ravikumar R， et al. Optimization of hybrid laser-TIG welding of 316LN stainless steel using genetic algorithm［J］. Materials & Manufacturing Processes， 2017， 32（10）： 1094-1100.

陈超，陈芙蓉，张慧婧. 响应面法分析7A52铝合金光纤激光焊气孔敏感性［J］. 焊接， 2016（05）： 17-21，73-74.

Chen Chao， Chen Furong， Zhang Huijing. Porosity sensitivity analysis of 7A52 aluminum alloy during fiber laser welding by response surface method［J］. Welding & Joining. 2016（05）： 17-21，73-74.

Liu Bowen， Jin Wentao， Lu Anjin， et al. Optimal design for dual laser beam butt welding process parameter using artificial neural networks and genetic algorithm for SUS316L austenitic stainless steel［J］. Optics & Laser Technology， 2020， 125.

蔡荣辉，崔雨轩，薛培静. 三层BP神经网络隐层节点数确定方法探究［J］. 电脑与信息技术， 2017， 25（05）： 29-33.

Cai Ronghui， Cui Yuxuan， Xue Peijing. Research on the Methods of Determining the Number of Hidden Nodes in Three-layer BP Neural Network［J］. Computer and Information Technology， 2017， 25（05）： 29-33.

高星鹏，陈峰，王宇盛，等. 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（03）： 33-37.

Gao Xingpeng， Chen Feng， Wang Yusheng， et al. Optimization of Micro Resistance Spot Welding Process Parameters Based on Genetic Algorithm and Neural Network［J］. Aerospace Materials & Technology， 2018，48（03）： 33-37.

Li Shangren， Mi Gaoyang， Wang Chunming. A study on laser beam oscillating welding characteristics for the 5083 aluminum alloy： Morphology，microstructure and mechanical properties［J］. Journal of Manufacturing Pr-ocesses， 2020， 53： 12-20.

Alert me when the article has been cited

提交

Study on Welding Process of Friction Welding of Reinforcement Steel Embedded Parts in Nuclear Power Plant