Root hump defect prediction for laser-MIG hybrid welding

LIU Xiuhang; YE Guangwen; HUANG Yuhui; ZHANG Yanxi; FENG Sang; GAO Xiangdong

doi:10.12073/j.hjxb.20211216003

TRANSACTIONS OF THE CHINA WELDING INSTITUTION > 2022 > 43(12): 47-52, 99. > DOI: 10.12073/j.hjxb.20211216003

LIU Xiuhang, YE Guangwen, HUANG Yuhui, ZHANG Yanxi, FENG Sang, GAO Xiangdong. Root hump defect prediction for laser-MIG hybrid welding[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(12): 47-52, 99. DOI: 10.12073/j.hjxb.20211216003

Citation:

PDF (2723 KB)

Root hump defect prediction for laser-MIG hybrid welding

Guangdong Provincial Welding Engineering Technology Research Center, Guangdong University of Technology, Guangzhou, 510006, China

More Information

Received Date: December 15, 2021
Available Online: November 10, 2022

Graphical Abstract

Abstract

Abstract

The root hump defect is easy to appear in the laser-MIG composite welding process. In order to realize the simultaneous prediction of the root hump defect in the welding process, this paper studies the algorithm of root hump defect prediction and analyzes the prediction results of different algorithm. The real-time visual sensing information of composite welding process is carried out by a high-speed camera, the time series characteristic information of the front weld pool and the keyhole in the welding process is extracted, and the characteristics signals are decomposed and reconstructed by wavelet packet decomposition (WPD). Then, the residual height of the back weld is obtained by a laser scanner, which is used as the basis for marking the hump status. Long short-term memory (LSTM) neural network was used to predict the status of root hump in the welding process. Experimental results show that the accuracy of WPD-LSTM algorithm for root hump prediction is 97.85%. Compared with other algorithms, the prediction accuracy of WPD-LSTM algorithm based on the temporal feature information of the front visual sensing in the welding process is higher, and the prediction results have higher continuity, which is conducive to realize the synchronous detection and control of root hump defects in welding process.
- root hump,
- visual inspection,
- long short-term memory neural networks,
- wavelet packet decomposition

FullText(HTML)

References (19)

References

Blecher J J, Palmer T A, Debroy T. Mitigation of root defect in laser and hybrid laser-arc welding[J]. Welding Journal, 2015, 94: 73 − 82.

Jan F. Factors affecting weld root morphology in laser keyhole welding[J]. Optics and Lasers in Engineering, 2018, 101: 89 − 98. doi: 10.1016/j.optlaseng.2017.10.005

高向东, 梁剑斌, 刘桂谦, 等. 大功率光纤激光焊熔透状态模糊聚类识别方法[J]. 焊接学报, 2017, 38(5): 22 − 25. doi: 10.12073/j.hjxb.20170505

Gao Xiangdong, Liang Jianbin, Liu Guiqian, et al. Identification of high-power fiber laser welding penetration based on fuzzy clustering algorithm[J]. Transactions of the China Welding Institution, 2017, 38(5): 22 − 25. doi: 10.12073/j.hjxb.20170505

杨嘉佳, 王克鸿, 吴统立, 等. 基于熔池视觉特征的铝合金双丝焊熔透识别[J]. 焊接学报, 2017, 38(3): 49 − 52.

Yang Jiajia, Wang Kehong, Wu Tongli, et al. Welding penetration recognition in aluminum alloy tandem arc welding based on visual characters of weld pool[J]. Transactions of the China Welding Institution, 2017, 38(3): 49 − 52.

冯宝, 覃科, 蒋志勇. 基于L1/L2极限学习机的熔池熔透状态识别[J]. 焊接学报, 2018, 39(9): 31 − 35.

Feng Bao, Qin Ke, Jiang Zhiyong. ELM with L1/L2 regularization constraints[J]. Transactions of the China Welding Institution, 2018, 39(9): 31 − 35.

刘天元, 鲍劲松, 汪俊亮, 等. 融合时序信息的激光焊接熔透状态识别方法[J]. 中国激光, 2021, 48(6): 228 − 238. doi: 10.3788/CJL202148.0602119

Liu Tianyuan, Bao Jinsong, Wang Junliang, et al. Laser welding penetration state recognition method fused with timing information[J]. Chinese Journal of Lasers, 2021, 48(6): 228 − 238. doi: 10.3788/CJL202148.0602119

陈子琴, 高向东, 王琳. 大功率盘形激光焊焊缝背面宽度预测[J]. 光学精密工程, 2017, 25(9): 2524 − 2531. doi: 10.3788/OPE.20172509.2524

Chen Ziqin, Gao Xiangdong, Wang Lin. Weld width prediction of weldment bottom surface in high-power disk laser welding[J]. Optics and Precision Engineering, 2017, 25(9): 2524 − 2531. doi: 10.3788/OPE.20172509.2524

Chang Y F, Lei Z, Wang X Y, et al. Characteristic of laser-MIG hybrid welding with filling additional cold wire for aluminum alloy[J]. China Welding, 2018, 27(3): 35 − 41.

Gao X D, Zhang Y X. Monitoring of welding status by molten pool morphology during high-power disk laser welding[J]. Optik-International Journal for Light and Electron Optics, 2015, 126(19): 1797 − 1802. doi: 10.1016/j.ijleo.2015.04.060

Zhang Y X, Han S W, Cheon J, et al. Effect of joint gap on bead formation in laser butt welding of stainless steel[J]. Journal of Materials Processing Technology, 2017, 249: 274 − 284.

Wang T, Gao X D, Katayama S, et al. Study of dynamic features of surface plasma in high-power disk laser welding[J]. Plasma Science and Technology, 2012, 14(3): 245 − 251.

Fan X A, Gao X D, Zhang Y X, et al. Monitoring of 304 austenitic stainless-steel laser-MIG hybrid welding process based on EMD-SVM[J]. Journal of Manufacturing Processes, 2022, 73: 736 − 741. doi: 10.1016/j.jmapro.2021.11.031

王艺蒙, 李蔚, 韩纪龙, 等. 基于小波包变换码的新型无源光网络上行信号复用和传输方法[J]. 中国激光, 2014, 41(6): 0605001. doi: 10.3788/CJL201441.0605001

Wang Yimeng, Li Wei, Han Jilong, et al. Upstream date transmission based on wavelet packet transform coding in passive optical network[J]. Chinese Journal of Lasers, 2014, 41(6): 0605001. doi: 10.3788/CJL201441.0605001

周旭峰, 王醒策, 武仲科, 等. 基于组合RNN网络的EMG信号手势识别[J]. 光学精密工程, 2020, 28(2): 424 − 442.

Zhou Xufeng, Wang Xingce, Wu Zhongke, et al. Gesture recognition with EMG signals based on ensemble RNN[J]. Optics and Precision Engineering, 2020, 28(2): 424 − 442.

李清亮, 蔡凯旋, 耿庆田, 等. 极限梯度提升和长短期记忆网络相融合的土壤温度预测[J]. 光学精密工程, 2020, 28(10): 2337 − 2348. doi: 10.37188/OPE.20202810.2337

Li Qingliang, Cai Kaixuan, Geng Qingtian, et al. Estimation of soil temperature based on XGBoost and LSTM methods[J]. Optics and Precision Engineering, 2020, 28(10): 2337 − 2348. doi: 10.37188/OPE.20202810.2337

冯泽斌, 周翊, 江锐, 等. 门控循环网络辨识准分子激光器能量模型[J]. 中国激光, 2021, 48(9): 34 − 43. doi: 10.3788/CJL202148.0901004

Feng Zebin, Zhou Yi, Jiang Rui, et al. Recognition of energy model of excimer laser by gate recurrent unit[J]. Chinese Journal of Lasers, 2021, 48(9): 34 − 43. doi: 10.3788/CJL202148.0901004

Liu T Y, Bao J S, Wang J L, et al. A hybrid CNN–LSTM algorithm for online defect recognition of CO₂ welding[J]. Sensors, 2018, 18(12): 4369. doi: 10.3390/s18124369

You D Y, Gao X D, Katayama, S. Multisensor fusion system for monitoring high-power disk laser welding using support vector machine[J]. IEEE Transactions on Industrial Informatics, 2014, 10(2): 1285 − 1295. doi: 10.1109/TII.2014.2309482

Zhang Y X, Gao X D, Katayama, S. Weld appearance prediction with BP neural network improved by genetic algorithm during disk laser welding[J]. Journal of Manufacturing Systems, 2015, 34: 53 − 59. doi: 10.1016/j.jmsy.2014.10.005

[1]	CHEN Haiyong, DU Xiaolin, DONG Yan. Tiny visual feature extraction of random changing weld[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2016, 37(5): 97-101.
[2]	CHI Dazhao, MAI Chengle, SUN Changli, GANG Tie. Wavelet package based ultrasonic defect detection method for testing austenitic stainless steel weldment[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2015, 36(12): 43-46.
[3]	ZHAO Huihuang, ZHOU Dejian, WU Zhaohua, LI Chunquan, LI Kangman. SMT soldering image denoising based on wavelet packet transform and adaptive threshold[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2011, (11): 73-76.
[4]	LIU Lijun, LAN Hu, WEN Jianli, YU Zhongwei. Feature extraction of penetration arc sound in MIG welding via wavelet packet frequency-band energy[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2010, (1): 45-49.
[5]	WEN Jianli, LIU Lijun, LAN Hu. Penetration state recognition of MIG welding based on genetic wavelet neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2009, (8): 41-44.
[6]	DI Xinjie, LI Wushen, BAI Shiwu, LIU Fangming. Metal magnetic memory signal recognition by neural network for welding crack[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2008, (3): 13-16.
[7]	LI Hexi, WANG Guorong, SHI Yonghua, ZHANG Weimin. Automatic recognition of welding targets based on normalized singular value decomposition of image matrix[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2008, (2): 35-39.
[8]	TIAN Songya, WU Dongchun, SUN Ye, FU Weiliang. Wavelet detection of short circuit signal in CO₂ arc welding based on DSP[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2007, (7): 65-68.
[9]	YANG Lijun, XU Licheng, ZHANG Xiaonan, LI Junyue. Wavelet filtering of electric signals in short circuit CO₂ welding[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2006, (8): 31-34,38.
[10]	QU Wen-tai, ZHU jing. Research on Technology of Detecting Welding Seam Based on Gauss Wavelet[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2002, (4): 64-68.

Cited By

Cited by

Periodical cited type(1)

陈晓明，王丽，马良，周峰，袁山山. 钢筋工程焊缝质量检测技术研究进展. 北京理工大学学报. 2024(12): 1215-1224 .

Other cited types(1)

Get Citation

PDF

XML

Article views (380) PDF downloads (111) Cited by(2)

Turn off MathJax

Article Contents

Abstract

References

Root hump defect prediction for laser-MIG hybrid welding