Research on Predicting the Depth and Width of Laser Welding of AH36 Steel Based on Plasma Vision and Spectral Features

CHEN Jinyi; TIAN Lei; SHEN Nannan; TAN Caiwang

doi:10.7512/j.issn.1001-2303.2024.05.04

Important Issuse | Views : 0 下载量: 6 CSCD: 0

PDF
Export
Share
Collection
Album

Research on Predicting the Depth and Width of Laser Welding of AH36 Steel Based on Plasma Vision and Spectral Features
Vol. 54, Issue 5, Pages: 31-38(2024)
Published： 25 May 2024 ，
DOI： 10.7512/j.issn.1001-2303.2024.05.04

扫描看全文

程晋宜，田雷，沈楠楠，等.基于等离子体视觉和光谱特征的AH36钢激光焊接熔深熔宽预测研究［J］.电焊机，2024，54（5）：31-38.

CHEN Jinyi, TIAN Lei, SHEN Nannan, et al.Research on Predicting the Depth and Width of Laser Welding of AH36 Steel Based on Plasma Vision and Spectral Features[J].Electric Welding Machine, 2024, 54(5): 31-38.
程晋宜，田雷，沈楠楠，等.基于等离子体视觉和光谱特征的AH36钢激光焊接熔深熔宽预测研究［J］.电焊机，2024，54（5）：31-38. DOI： 10.7512/j.issn.1001-2303.2024.05.04.

CHEN Jinyi, TIAN Lei, SHEN Nannan, et al.Research on Predicting the Depth and Width of Laser Welding of AH36 Steel Based on Plasma Vision and Spectral Features[J].Electric Welding Machine, 2024, 54(5): 31-38. DOI： 10.7512/j.issn.1001-2303.2024.05.04.

摘要

针对AH36船用钢不同激光功率和焊接速度的激光焊接，通过高速摄像提取焊接过程等离子体的图像，同时采集了光谱信息，最终建立GA-BP（Genetic Algorithm-Back propagation）神经网络以预测焊缝的质量即熔深和熔宽，并与常用的回归分析方法和未经优化的BP神经网络预测效果相比较。结果表明，焊缝熔深和熔宽均随激光功率的增大而增大，随焊速提高而降低；等离子体面积、高度、灰度以及电子密度均随激光功率增大呈增大趋势。当采用仅考虑焊接工艺参数的回归模型进行预测时，熔深预测相对误差18.2%，熔宽预测相对误差12.1%。而采用引入焊接过程等离子体特征的BP神经网络，虽然精度提高，但由于随机性存在导致相对误差变化较大，进一步采用GA算法进行全局求解能力优化后，熔深预测相对误差降低至7.23%，熔宽预测相对误差降低至5.79%，模型稳定性也明显改善。综合考虑工艺参数和等离子体特征建立的神经网络模型能够更准确预测AH36钢激光焊接焊缝形貌，为焊接工艺规划和质量预测提供参考。

Abstract

For laser welding of AH36 steel with different laser powers and welding speeds

high-speed cameras were used to extract plasma images during the welding process

meanwhile spectral information was collected. Finally

a GA-BP(Genetic Algorithm-Back propagation) neural network was established to predict the quality of the weld

namely the depth and width of fusion

and the prediction results were compared with commonly used regression analysis methods. The results showed that the depth and width of the weld seam increase with the increase of laser power

and decrease with the increase of welding speed; The plasma area

height

grayscale

and electron density all show an increasing trend with increasing laser power. When using a regression model for prediction

the relative error of melt depth prediction is 18.2%

and the relative error of melt width prediction is 12.1%. The use of an un-optimized BP neural network results in significant changes in relative error due to randomness. After optimizing using the GA algorithm and introducing process parameters as input features

the relative error of melt depth prediction is reduced to 7.23%

and the relative error of melt width prediction is reduced to 5.79%.

关键词

AH36钢激光焊接等离子体回归分析神经网络

Keywords

AH36 steelLaser weldingPlasmaRegression analysisneural network

references

姬宜朋，陈家庆，焦向东，等. 激光-电弧复合热源焊接技术［J］. 焊接技术，2009，38（12）：1-7.

JI P Y，CHEN J Q，JIAO X D，et al. Laser-arc hybrid welding technique［J］. Welding Technology，2009，38（12）：1-7.

赵子强.激光-TIG电弧复合焊接等离子体形态与焊缝特征的研究［D］. 北京：北京工业大学， 2011.

ZHAO Z Q. Study on Plasma Morphology and Weld Characteristics in Laser-TIG Hybrid Welding （Doctoral dissertation）［D］. Beijing： Beijing University of Technology，2011.

Zhang P，Kong L，Liu W，et al. Real-time monitoring of laser welding based on multiple sensors［C］. Control and Decision Conference， 2008：1746-1748.

Sudhagar S，Sakthivel M，Daniel S A. Application of image processing to radiographic image for quantitative assessment of friction stir welding quality of aluminium 2024 alloy［J］. Measurement，2020，152：107294.

李志勇，王威，王旭友，等. 大功率YAG激光-MAG复合热源的光谱诊断与分析［J］. 光谱学与光谱分析，2010（11）：3127-3131.

LI Z Y，WANG W，WANG X Y，et al. Spectral diagnosis and analysis of high-power YAG laser-MAG hybrid heat source［J］. Spectroscopy and Spectral Analysis，2010（11）：3127-3131.

陈实现，刘双宇，张宏，等. 激光-电弧复合焊等离子体特性与焊缝熔深相关性研究［J］. 兵工学报，2017，38（05）：978-985.

CHEN S X，LIU S Y，ZHANG H，et al. Study on the correlation between plasma characteristics and weld penetration in laser-arc hybrid welding［J］. Acta Armamentarii，2017，38（05）：978-985.

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 and performance prediction of fiber laser welding process parameters based on BP neural network［J］. Applied Laser，2010，30（06）：479-482.

应业勇. TC4钛合金激光焊接变形与光致等离子体的行为研究［D］. 湖南：湖南大学， 2016.

YING Y Y. Study on the deformation and photogenic plasma behavior of TC4 titanium alloy laser welding （Doctoral dissertation）［D］. Hunan：Hunan University，2016.

才宇航，高延峰，潘皓，等. TC4钛合金激光扫描焊接金属蒸气形态及其光谱特性研究［J/OL］. 重庆工商大学学报（自然科学版），1-12.［2024-05-13］. http：//kns.cnki.net/kcms/detail/50.1155.n.20230526.1437.002.htmlhttp://kns.cnki.net/kcms/detail/50.1155.n.20230526.1437.002.html

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（09）：84-90.

GOU X L，WU D，DONG J F，et al. Study on the process and quality prediction of aluminum alloy pulse laser welding based on machine learning［J］. Electric Welding Machine，2023，53（09）：84-90.

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 and performance prediction of fiber laser welding process parameters based on BP neural network［J］. Applied Laser，2010，30（06）：479-482.

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（08）：43-49+64.

LIANG C，ZHANG X，MI G Y，et al. Optimization of aluminum alloy laser oscillating welding process parameters based on neural network and genetic algorithm［J］.Electric Welding Machine，2022，52（08）：43-49+64.

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

Alert me when the article has been cited

提交

Research Status of High-Efficiency 10 000-Watt Laser Welding

Optimization of Multi-Wave Annular Laser Sealing Stud Welding Process

Effect of Copper Interlayer on the Quality of Laser Lap Welding of Stainless Steel Aluminum Alloy

Porosity Formation Mechanism Research in Laser Welding of Micro-pump

Development and Process Test of a Local Dry Underwater Laser Welding Device