首页 > 论文 > 中国激光 > 44卷 > 3期(pp:302004--1)

基于主成分分析-支持向量机模型的激光钎焊接头质量诊断

Quality Diagnosis of Joints in Laser Brazing Based on Principal Component Analysis-Support Vector Machine Model

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

基于主成分分析-支持向量机(PCA-SVM)模型,提出一种利用近红外辐射信号预测接头形貌的方法,研究了信号的变化规律与焊缝形貌之间的相关性,实现了工艺参数的优化。提取信号的6种时域特征参数并进行主成分分析,获得了接头形貌综合评定指标。根据信号的输入特征,利用支持向量机进行了分类预测。结果表明,近红外辐射信号能够反映焊接过程中焊缝状态的变化,不同缺陷的特征变化具有较大差异,且存在清晰的识别度。该预测模型能够准确识别焊缝成形形貌,准确率高达96.6%。

Abstract

Based on the principal component analysis-support vector machine (PCA-SVM) model, one method is proposed to predict the joint morphology with the near infrared radiation signal. The correlation between the change laws of signals and the weld formation morphology is investigated and the optimization of process parameters is realized. Six kinds of characteristic parameters of signals in time domain are extracted and the principal component analysis is carried out to obtain the comprehensive evaluation index of joint morphology. Based on the input characteristics of signals, the classification prediction is done by using the support vector machine. The results show that, the near infrared radiation signals can reflect the change of weld state during the welding process, the characteristic changes of different defects have great difference, and the clear recognition exists. The proposed prediction model can accurately identify weld appearance with accuracy up to 96.6%.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TG456.7

DOI:10.3788/cjl201744.0302004

所属栏目:激光制造

基金项目:国家自然科学基金(51375191)

收稿日期:2016-10-08

修改稿日期:2016-11-12

网络出版日期:--

作者单位    点击查看

程力勇:华中科技大学材料科学与工程学院, 湖北 武汉 430074
米高阳:华中科技大学材料科学与工程学院, 湖北 武汉 430074
黎 硕:华中科技大学材料科学与工程学院, 湖北 武汉 430074
胡席远:华中科技大学材料科学与工程学院, 湖北 武汉 430074
王春明:华中科技大学材料科学与工程学院, 湖北 武汉 430074

联系人作者:程力勇(chengliyong@hust.edu.cn)

备注:程力勇(1992—),男,硕士研究生,主要从事激光焊接在线质量监测方面的研究。

【1】Gao X D, You D Y, Katayama S. The high frequency characteristics of laser reflection and visible light during solid state disk laser welding[J]. Laser Physics Letters, 2015, 12(7): 076003.

【2】Zhang Yanxi. Recognition of molten pool morphology in real time and prediction of weld appearance during high-power disk laser welding[D]. Guangzhou: Guangdong University of Technology, 2014.
张艳喜. 大功率盘型激光焊熔池形态在线识别及焊缝成形预测模型[D]. 广州: 广东工业大学, 2014.

【3】Bardin F, Cobo A, Lopez-Higuera J M, et al. Optical techniques for real-time penetration monitoring for laser welding[J]. Applied Optics, 2005,44(19): 3869-3876.

【4】Hand D P, Peters C, Jones J D C. Nd∶YAG laser welding process monitoring by non-intrusive optical detection in the fibre optic delivery system[J]. Measurement Science and Technology, 1995, 6(9): 1389-1394.

【5】Yu Dong, Zhong Minlin, Liu Wenjin, et al. Realtime monitoring research of melt pool images in laser cladding process[J]. Chinese J Lasers, 2007, 34(s1): 86-90.
于 栋, 钟敏霖, 刘文今, 等. 激光熔覆过程中熔池图像的实时检测[J]. 中国激光, 2007, 34(s1): 86-90.

【6】Yu H W, Xu Y L, Lü N, et al. Arc spectral processing technique with its application to wire feed monitoring in Al-Mg alloy pulsed gas tungsten arc welding[J]. Journal of Materials Processing Technology, 2013, 213(5): 707-716.

【7】Cai Huaiyu, Feng Zhaodong, Huang Zhanhua. Centerline extraction of structured light stripe based on principal component analysis[J]. Chinese J Lasers, 2015, 42(3): 0308006.
蔡怀宇, 冯召东, 黄战华. 基于主成分分析的结构光条纹中心提取方法[J]. 中国激光, 2015, 42(3): 0308006.

【8】Fan Jinping, Xu Xiaofei, Zhang Wangping, et al. Multi-wavelength phase-shifting interferometry based on principal component analysis[J]. Chinese J Lasers, 2015, 42(10): 1008004.
范金坪, 徐小飞, 张望平, 等. 一种基于主成分分析的多波长相移干涉测量方法[J]. 中国激光, 2015, 42(10): 1008004.

【9】Zhang Z F, Chen H B, Xu Y L, et al. Multisensor-based real-time quality monitoring by means of feature extraction, selection and modeling for Al alloy in arc welding[J]. Mechanical Systems and Signal Processing, 2015, 60-61: 151-165.

引用该论文

Cheng Liyong,Mi Gaoyang,Li Shuo,Hu Xiyuan,Wang Chunming. Quality Diagnosis of Joints in Laser Brazing Based on Principal Component Analysis-Support Vector Machine Model[J]. Chinese Journal of Lasers, 2017, 44(3): 0302004

程力勇,米高阳,黎 硕,胡席远,王春明. 基于主成分分析-支持向量机模型的激光钎焊接头质量诊断[J]. 中国激光, 2017, 44(3): 0302004

被引情况

【1】廖建尚,王立国,郝思媛. 基于自适应流形滤波的高光谱图像分类方法. 激光与光电子学进展, 2018, 55(4): 41010--1

【2】李素梅. 基于卷积神经网络的立体图像舒适度客观评价. 光学学报, 2018, 38(6): 610003--1

【3】杨恢先,陈永,张翡,周彤彤. 基于改进梯度局部二值模式的人脸识别. 激光与光电子学进展, 2018, 55(6): 61004--1

【4】徐天扬,杨娟,孙晓荣,刘翠玲,李熠,周金慧,陈兰珍. 中红外光谱法结合支持向量机快速鉴别蜂蜜品种. 激光与光电子学进展, 2018, 55(6): 63003--1

【5】赵小虎,尹良飞,朱亚楠,刘鹏,王学奎,沈雪茹. 基于主成分分析网络的改进图像分类算法. 激光与光电子学进展, 2019, 56(2): 21004--1

【6】张洁,赵红东,李宇海,闫苗,赵泽通. 复杂背景下车型识别分类器. 激光与光电子学进展, 2019, 56(4): 41501--1

【7】陈冠楠,周群,韦超,王敏,陈建新. 基于facet模型的三维纤维方向检测方法研究. 激光与光电子学进展, 2019, 56(14): 141004--1

【8】严春满,陈佳辉,马芸婷,郝有菲,张迪. 改进灰狼优化算法及其在QR码识别上的应用. 激光与光电子学进展, 2020, 57(2): 21015--1

【9】胡潇,吴瑞梅,朱晓宇,刘鹏,熊爱华,黄俊仕,杨普香,熊俊飞,艾施荣. 表面增强拉曼光谱结合二维相关谱快速检测茶叶中的毒死蜱残留. 光学学报, 2019, 39(7): 730001--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF