Laser welding steady status recognition method based on correlation analysis and neural network

HUANG Weiwei; YOU Deyong; GAO Xiangdong; ZHANG Yanxi; HUANG Yuhui

doi:10.7510/jgjs.issn.1001-3806.2022.03.004

LASER TECHNOLOGY > 2022 > 46(3): 312-319. > DOI: 10.7510/jgjs.issn.1001-3806.2022.03.004

HUANG Weiwei, YOU Deyong, GAO Xiangdong, ZHANG Yanxi, HUANG Yuhui. Laser welding steady status recognition method based on correlation analysis and neural network[J]. LASER TECHNOLOGY, 2022, 46(3): 312-319. DOI: 10.7510/jgjs.issn.1001-3806.2022.03.004

Citation:

PDF (15207 KB)

Laser welding steady status recognition method based on correlation analysis and neural network

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

More Information

Received Date: March 30, 2021
Revised Date: April 14, 2021
Published Date: May 24, 2022

Graphical Abstract

Abstract

Abstract

In order to accurately identify the type of weld seam status in laser welding, image processing, correlation analysis, and neural network methods were used. The study of quasi-steady status was added, and the correlation coefficients of the signal features were used as the input of the neural network model. Theoretical analysis and experimental verification were carried out, and the effects of the correlation of optical and visual signals on the steady-status types of laser welding were obtained. The results show that the correlation between keyhole area and plume area is the best way to distinguish the steady-status types. When its correlation coefficient is 0.2~0.3, it is in steady status, 0.4~0.5 corresponds to the quasi-steady status, and 0.6~0.7 corresponds to the unsteady status. The trained neural network model achieves 98.76% prediction accuracy on the test set, which can meet the needs of accurately identifying types of weld seam status. This research provides a reference for preventing laser welding defects in automated production.
- laser technique,
- steady statuses recognition,
- correlation analysis,
- neural network,
- image processing

FullText(HTML)

References (20)

References

[1]	WANG C Y, GAO X D, MA N J, et al. Magneto-optical imaging detection of laser welding defects under multi-directional magnetic field excitation[J]. Laser Technology, 2020, 44(5): 592-599(in Chinese).
[2]	SU Sh X, YU Y L, FEI W, et al. Research of characteristics of weld formation of aluminum alloy by high power fiber laser welding[J]. Laser Technology, 2017, 41(3): 322-327(in Chinese).
[3]	LIU T Y, BAO J S, WANG J L, et al. Laser welding penetration state recognition method fused with timing information[J]. Chinese Journal of Lasers, 2021, 48(6): 0602119(in Chinese). DOI: 10.3788/CJL202148.0602119
[4]	CHEN Z Q, GAO X D, WANG Y, et al. Weldment back of weld width prediction based on neural network during high-power laser welding[J]. Transactions of The China Welding Institution, 2018, 39(11): 48-52(in Chinese).
[5]	HUANG Y, SHEN C, JI X R, et al. Correlation between gas-dyna-mic behaviour of a vapour plume and oscillation of keyhole size during laser welding of 5083 Al-alloy[J]. Journal of Materials Processing Technology, 2020, 283: 116721. DOI: 10.1016/j.jmatprotec.2020.116721
[6]	SUDER W, GANGULY S, WILLIAMS S, et al. Penetration and mixing of filler wire in hybrid laser welding[J]. Journal of Materials Processing Technology, 2021, 291: 117040. DOI: 10.1016/j.jmatprotec.2020.117040
[7]	FANG J F. Study on the mechanism of penetration mode for thin steel laser deep penetration welding[D]. Harbin: Harbin Institute of Technology, 2007: 41-42(in Chinese).
[8]	WANG J, WANG C M, MENG X X, et al. Study on the periodic oscillation of plasma/vapour induced during high power fibre laser penetration welding[J]. Optics and Laser Technology, 2011, 44(1): 67-70.
[9]	PANG S Y, CHEN X, SHAO X Y, et al. Dynamics of vapor plume in transient keyhole during laser welding of stainless steel: Local evaporation, plume swing and gas entrapment into porosity[J]. Optics and Lasers in Engineering, 2016, 82: 28-40. DOI: 10.1016/j.optlaseng.2016.01.019
[10]	VOLPP J. Impact of fume particles in the keyhole vapour[J]. Applied Physics, 2019, A125(1): 70-77.
[11]	LIU X F, JIA C B, WU C S, et al. Measurement of the keyhole entrance and topside weld pool geometries in keyhole plasma arc welding with dual CCD cameras[J]. Journal of Materials Processing Technology, 2017, 248: 39-48. DOI: 10.1016/j.jmatprotec.2017.05.012
[12]	ROOZBAHANI H, MARTTINEN P, SALMINEN A. Real-time monitoring of laser scribing process of CIGS solar panels utilizing high speed camera[J]. IEEE Photonics Technology Letters, 2018, 30(20): 1741-1744. DOI: 10.1109/LPT.2018.2867274
[13]	CAI W, WANG J Z, JIANG P, et al. Application of sensing techniques and artificial intelligence-based methods to laser welding real-time monitoring: Acritical review of recent literature[J]. Journal of Manufacturing Systems, 2020, 57: 1-18. DOI: 10.1016/j.jmsy.2020.07.021
[14]	WANG B C, HU S J, SUN L, et al. Intelligent welding system technologies: State-of-the-artreview and perspectives[J]. Journal of Manufacturing Systems, 2020, 56: 373-391. DOI: 10.1016/j.jmsy.2020.06.020
[15]	GAO X D, LI Z M, WANG L, et al. Detection of weld imperfection in high-power disk laser welding based on association analysis of multi-sensing features[J]. Optics and Laser Technology, 2019, 115: 306-315. DOI: 10.1016/j.optlastec.2019.01.053
[16]	MA G H, YU L S, YUAN H T, et al. A vision-based method for lap weld defects monitoring of galvanized steel sheets using convolutional neural network[J]. Journal of Manufacturing Processes, 2021, 64: 130-139. DOI: 10.1016/j.jmapro.2020.12.067
[17]	HUANG J F, XUE L, HUANG J Q, et al. GMAW penetration state prediction based on visual sensing[J]. Journal of Mechanical Engineering, 2019, 55(17): 41-47(in Chinese). DOI: 10.3901/JME.2019.17.041
[18]	ZHANG Y X, YOU D Y, GAO X D, et al. Online monitoring of welding status based on a DBN model during laser welding[J]. Engineering, 2019, 5(4): 169-185.
[19]	MA X, DU Zh H, CAI Y, et al. Research on improved median filtering algorithm fused with gradient information[J]. Transducer and Microsystem Technologies, 2021, 40(3): 48-51(in Chinese).
[20]	PRAKASH A, STORER J, FLORENCIO D, et al. RePr: Improved Training of convolutional filters[C]// IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2019: 10658-10667.

Cited By

Cited by

Periodical cited type(4)

1.	黄贻蔚，高向东，李来明，马波，张艳喜. 激光焊OCT熔深测量去噪及数据拟合方法研究. 激光技术. 2024(04): 590-596 . 本站查看
2.	葛芸萍，王玉梅. 基于改进灰色模型的激光切割粗糙度预测. 激光与红外. 2023(04): 522-527 .
3.	鞠亚军. 计算机多媒体技术在机械制造业中的应用. 造纸装备及材料. 2023(06): 122-124 .
4.	田猛，高向东，谢岳轩，张艳喜. 焊接缺陷磁光成像噪声特征分析及处理算法. 激光技术. 2023(05): 646-652 . 本站查看

Other cited types(1)

Get Citation

PDF

XML

Article views (8) PDF downloads (7) Cited by(5)

Turn off MathJax

Article Contents

Abstract

References

Laser welding steady status recognition method based on correlation analysis and neural network

Abstract

References

Cited by

Periodical cited type(4)

Other cited types(1)

Catalog

Links：

Laser welding steady status recognition method based on correlation analysis and neural network

Abstract

References

Cited by

Periodical cited type(4)

Other cited types(1)

Catalog

Links：

Export File

Citation

Format

Content