Quality Prediction of Pulse Laser Welding of Aluminum Alloy Based on Machine Learning

GOU Xinglu; WU DI; DONG Jinfang; YANG Fangyi; ZENG Da; HUANG Hongxing; ZHANG Peilei; YE Xin; SHI Haichuan

doi:10.7512/j.issn.1001-2303.2023.09.11

Human-machine Cooperation & Intelligent Welding | Views : 0 下载量: 22 CSCD: 0

PDF
Export
Share
Collection
Album

Quality Prediction of Pulse Laser Welding of Aluminum Alloy Based on Machine Learning
Vol. 53, Issue 9, Pages: 84-90(2023)
DOI： 10.7512/j.issn.1001-2303.2023.09.11

扫描看全文

苟星禄，吴頔，董金枋，等.基于机器学习的铝合金脉冲激光焊接工艺及质量预测研究［J］.电焊机，2023，53（9）：84-90.

GOU Xinglu, WU DI, DONG Jinfang, et al.Quality Prediction of Pulse Laser Welding of Aluminum Alloy Based on Machine Learning[J].Electric Welding Machine, 2023, 53(9): 84-90.
苟星禄，吴頔，董金枋，等.基于机器学习的铝合金脉冲激光焊接工艺及质量预测研究［J］.电焊机，2023，53（9）：84-90. DOI： 10.7512/j.issn.1001-2303.2023.09.11.

GOU Xinglu, WU DI, DONG Jinfang, et al.Quality Prediction of Pulse Laser Welding of Aluminum Alloy Based on Machine Learning[J].Electric Welding Machine, 2023, 53(9): 84-90. DOI： 10.7512/j.issn.1001-2303.2023.09.11.

摘要

铝合金脉冲激光焊接能够精准调节激光能量输入，广泛应用于动力电池与新能源汽车等精密加工领域。然而，铝合金自身高导热率和高反射率等固有属性，以及与高能量激光剧烈的相互耦合作用，对工艺参数优化和焊接质量控制带来挑战。以2 mm厚1060铝合金作为研究对象，主要分析了不同脉冲激光工艺参数（峰值功率、脉冲频率和焊接速度）对焊缝成形的影响规律；以工艺参数为多维输入变量，进一步构建了基于BP神经网络的熔池尺寸预测模型。结果表明：不同工艺参数均对焊缝熔深和熔宽有直接影响，需要确定一个合适的工艺窗口；同时构建模型的平均预测误差在10%以内，具有较高的预测精度。为铝合金脉冲激光焊接质量预测及工艺优化提供了可靠的实验和指导依据。

Abstract

Pulsed laser welding of aluminum alloy is widely used in precision machining fields such as power batteries and new energy vehicles because it can accurately adjust the laser energy input. However, the inherent properties of aluminum alloy such as high thermal conductivity and high reflectivity, as well as the intense interaction with high energy laser, bring challenges to the optimization of process parameters and welding quality assurance. In this paper, the influences of different pulse laser parameters (peak power, pulse frequency and welding speed) on weld forming were analyzed. Taking the process parameters as multi-dimensional input features, the prediction model of melting width and depth based on BP neural network was further constructed. The results show that different process parameters have direct influences on the weld depth and width, and it is necessary to determine a suitable process window. At the same time, the average prediction error of the constructed model is less than 10%, which has a high prediction accuracy. The research provides a reliable experimental and guiding basis for the quality prediction and process optimization of pulsed laser welding of aluminum alloy.

关键词

脉冲激光焊接1060铝合金焊缝尺寸神经网络质量预测

Keywords

pulsed laser welding1060 aluminum alloyWeld sizeNeural networkQuality prediction

references

王栋梁. 铝合金激光焊接工艺能耗及焊接质量多目标优化研究［D］.湖北：武汉科技大学，2022.

WANG D L. Research on multi-objective optimization of energy consumption and welding quality of aluminum alloy laser welding process ［D］.Hubei： Wuhan University of Science and Technology，2022.

周英才. 6016铝合金激光焊接接头组织性能强化研究［D］.河北：燕山大学，2021.

ZHOU Y C. Research on Strengthening Micorstructure and Properties of Laser Welded Joints of 6016 Aluminum Alloy［D］.Hebei： Yanshan University，2021.

朱桢. 6061/5182异种铝合金激光焊接接头组织与性能研究［D］.江苏：苏州大学，2022.

ZHU Z. Study on microstructure and properties of 6061/5182 dissimilar aluminum alloy laser welded joints［D］.Jiangsu： Soochow University，2022.

张大文，张宏，刘佳，等．铝合金连续-脉冲激光焊接工艺实验研究［J］.激光技术，2012，36（4）：453-458.

ZHANG D W， ZHANG H， LIU J， et al. Experimental study on Continuous pulse laser welding process of Aluminum alloy［J］. Laser Technology，2012（4）：453-458．

胡玉，张健，谭小军，等.Nd：YAG脉冲激光焊接TC4时峰值功率，脉宽对焊缝成形的影响［J］.应用激光，2014，34（5）：427-432.

HU Y， ZHANG J， TAN X J， et al. Effect of Peak power and pulse Width on weld formation during Nd： YAG pulsed Laser welding TC4［J］. Applying a laser， 2014， 34（5）： 427-432.

Akman E， Demir A， Canel T， et al. Laser welding of Ti6Al4V titanium alloys［J］. Journal of materials processing technology， 2009， 209（8）： 3705-3713.

Jia Z， Zhang P， Yu Z， et al. Effect of pulse shaping on solidification process and crack in 5083 aluminum alloy by pulsed laser welding［J］. Optics & Laser Technology， 2021， 134： 106608.

Torkamany M J， Hamedi M J， Malek F， et al. The effect of process parameters on keyhole welding with a 400 W Nd： YAG pulsed laser［J］. Journal of Physics D： Applied Physics， 2006， 39（21）： 4563.

朱玮涛，张海兵，吴苏兴，等.微波组件壳体激光焊接技术的研究［J］. 雷达与对抗， 2014， 34（1）： 53-57.

ZHU W T， ZHANG H B， WU S X， et al.Research on Laser Welding Technology of Microwave Module Shell［J］. Radar and countermeasures， 2014， 34（1）： 53-57.

王金风，张兰.小功率激光器焊接纯铝薄板工艺研究［J］.轻合金加工技术，2017，45（10）：57-60．

WANG J F， ZHANG L. Study on Welding technology of pure aluminum sheet with Low Power laser［J］. Light Alloy plus T Technology， 2017， 45（10）： 57-60.

张帆，泮佳俊，刘腾，等. 基于机器视觉的焊缝识别研究现状与发展趋势［J］. 电焊机， 2022， 52（7）： 24-33.

ZHANG F， PAN J J， LIU T， et al.Research Status and Development Trend of Welding Seam Recognition Based on Machine Vision［J］. Electric Welding Machine， 2022， 52（7）： 24-33.

刘荷花.基于BP神经网络的激光焊接工艺参数优化数据库系统［J］. 激光杂志，2015，36（04）：182-184.

LIU H H. Optimized database system of technologic parameters of laser welding process based on BP neural network［J］. Laser Journal，2015，36（04）：182-184.

任文坚，王永红，李春凯，等.液体火箭发动机推力室熔焊缝数字化胶片图像缺陷识别方法研究［J］. 电焊机，2023，53（1）：9-14.

REN W j， WANG Y H， LI C K， et al.Research on Automatic Detection Method of DR Digital imaging for Brazing Seam Defects of Thrust Chamber Body［J］. Electric Welding Machine， 2023， 53（1）： 9-14.

吴许祥，王成，薛华军，等.基于BP神经网络的激光焊接工艺参数优化及组织性能研究［J］. 锻压装备与制造技术，2021，56（06）：77-82.

WU X X，WANG C，XUE H J，et al. Research on optimization of laser welding process parameters and microstructure performance based on BP neural network［J］. China Metalforming Equipment & Manufacturing Technology，2021，56（06）：77-82.

张爱华，魏浩，马晶，等. 基于时间序列深度学习的超窄间隙焊接质量预测方法［J］. 电焊机， 2020， 50（8）：43-47.

ZHANG A H， WEI H， MA J， et al. A deep learning ultra-narrow gap welding quality prediction method based on time series［J］. Electric Welding Machine，2020， 50（8）：43-47.

赵子竣. 铝合金激光-电弧复合焊接的工艺研究［D］.四川：电子科技大学，2013.

ZHAO Z J. Research on the Process of Laser Arc Composite Welding of Aluminum Alloy［D］. Sichuan： University of Electronic Science and Technology of China，2013.

郭华锋，李菊丽，孙涛.基于BP神经网络的光纤激光切割切口粗糙度预测［J］. 激光技术， 2014， 38（06）：798-803.

GUO H F，LI J L，SUN T. Roughness prediction of kerf cut with fiber laser based on BP artificial neural networks［J］. Laser Technology， 2014，38（06）： 798-803.

郭亮，王少华，张庆茂，等.基于BP神经网络的光纤激光焊接工艺参数优化及性能预测［J］. 应用激光，2010，30（06）：479-482.

GUO L，WANG S H，ZHANG Q M，et al. Optimization of Fiber Laser Welding Process Viarables and Performance Prediction Based on BP Neural Network［J］. Applied Laser，2010，30（06）：479-482.

编辑部网址：http：//www.71dhj.comhttp://www.71dhj.com

Alert me when the article has been cited

提交

暂无数据