Defect generation of small sample laser welding based on generative adversarial network

XIAO Sizhe; LIU Zhenguo; YAN Zhihong; LI Min; HUANG Jiyuan

doi:10.12073/j.hjxb.20220429003

TRANSACTIONS OF THE CHINA WELDING INSTITUTION > 2022 > 43(10): 43-48. > DOI: 10.12073/j.hjxb.20220429003

XIAO Sizhe, LIU Zhenguo, YAN Zhihong, LI Min, HUANG Jiyuan. Defect generation of small sample laser welding based on generative adversarial network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(10): 43-48. DOI: 10.12073/j.hjxb.20220429003

Citation:

PDF (1436 KB)

Defect generation of small sample laser welding based on generative adversarial network

1.
Beijing Research Institute of Automation for Machinery Industry, Beijing, 100120, China
2.
Faculty of Materials and Manufacturing, Beijing University of Technology, Beijing, 100124, China

More Information

Received Date: April 28, 2022
Available Online: July 22, 2022

Graphical Abstract

Abstract

Abstract

To improve the performance of deep learning models on an unbalanced dataset of small samples of laser welded surface defects, an adversarial generative network (GAN) model using small datasets as input is optimized. By comparing the difference in feature complexity between laser welding defects and other public datasets used to test adversarial generative networks, a new OCM (one class mixup) module is designed and introduced into the stylegan2-ada for a limited number of samples to improve the performance of the adversarial generative network and accelerate its convergence. The results show that the dataset generated by OCM-stylegan2-ada improves the performance of the classification model by 40% over the original dataset and by 20% over the dataset enhanced with mixup and stylegan2-ada. Also the quality of the visually generated images of weld defects is greatly improved.
- welding defects,
- generative adversarial network,
- small sample,
- unbalanced dataset

FullText(HTML)

References (14)

References

Mery D, Riffo V, Zscherpel U, et al. GDXray: The database of X-ray images for nondestructive testing[J]. Journal of Nondestructive Evaluation, 2015, 34(4): 1 − 12.

Zhang Hongyi, Moustapha Cisse, Yann N. , et al. Mixup: beyond empirical risk minimization[C].//International Conference on Learning Representations. 2018.

Creswell A, White T, Dumoulin V, et al. Generative adversarial networks: An overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53 − 65. doi: 10.1109/MSP.2017.2765202

黄旭丰. 基于深度迁移学习的焊接质量在线监测方法研究[D]. 南宁: 广西大学, 2019.

Huang Xufeng. Deep transfer learning for online welding quality monitoring[D]. Nanning: Guangxi University, 2019.

Gurumurthy S, Kiran Sarvadevabhatla R, Venkatesh Babu R. Deligan: Generative adversarial networks for diverse and limited data[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 166 − 174.

谷静, 张可帅, 朱漪曼. 基于卷积神经网络的焊缝缺陷图像分类研究[J]. 应用光学, 2020, 41(3): 531 − 537.

GU Jing, ZHANG Keshuai, ZHU Yima. Research on weld defect image classification based on convolutional neural network[J]. Journal of Applied Optics, 2020, 41(3): 531 − 537.

Radford A , Metz L , Chintala S . Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[C]//International Conference on Computer Vision. 2016.

Karras T, Aittala M, Hellsten J, et al. Training generative adversarial networks with limited data[J]. Advances in Neural Information Processing Systems, 2020, 33: 12104 − 12114.

Karras T, Laine S, Aila T. A style-based generator a-rchitecture for generative adversarial networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 4401 − 4410.

Karras T, Laine S, Aittala M, et al. Analyzing and improving the image quality of stylegan[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 8110 − 8119.

Heusel M, Ramsauer H, Unterthiner T, et al. GANS trained by a two time-scale update rule converge to a local nash equilibrium[J]. Advances in Neural Information Processing Systems, 2017, 30: 1 − 38.

Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF Interna-tional Conference on Computer Vision. 2019: 1314 − 1324.

Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 432 − 445.

Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 4510 − 4520.

[1]	AO Bo, WANG Naibo, HE Shenyuan, DENG Cuizhen. Three dimensional imaging of internal defects in small diameter pipe welding seam by X-ray microtomography[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2016, 37(5): 11-14.
[2]	XIE Huangsheng, FU Zhihe, WANG Yuexin, XU Min, XUE Jiaxiang. Pulsed MIG welding stability evaluation based on current sample entropy[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2015, 36(10): 95-99.
[3]	LE Jian, ZHANG Hua, YE Yanhui, WANG Shuai. Tracking of fillet weld with small bending angle and detecting of weld seam endpoint[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2015, 36(9): 21-25.
[4]	YANG Xinhua, SUN Yibo, ZOU Li. Data distribution in welding fatigue analysis based on mesh-insensitive structural stress[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2015, 36(2): 11-14.
[5]	DU Bing, SUN Fenglian, LI Xiaoyu, SUN Jingtao, LÜ Xiaochun. Effect of sample size on fracture toughness of SA508-3 steel welded joint[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2014, 35(6): 1-4.
[6]	SONG Zhihua, WU Aiping, ZOU Guisheng, WANG Guoqing, REN Jialie. Metallographic sample preparation of Ti₃Al alloy laser welded joints for EBSD[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2011, (5): 93-96.
[7]	Lü Jian-min, CHEN Huai-ning, LIN Quan-hong.. Numerical analysis of a method for relieving welding stresses of girth-weld pipes with small diameters[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2003, (4): 83-86.
[8]	Li Heqi, Kenji Oshima. STUDY OF SAMPLING AND CONTROLLING MAG WELDING ARC LENGTH BY TV CAMERA[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 1989, (4): 258-264.
[9]	Zhou Dazhong, Yin Dianxiang, Chi Yuankui, Qu Jinku. NEW INTERNAL BORE PLASMA ARC WELDING PROCESS FOR SMALL DIAMETER STEEL TUBING[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 1982, (2): 81-87.
[10]	THE STUDY OF ALL POSITION PROGRAMMED PULSED TIG-WELDING OF SMALL THICK-WALLED TUBES——ITS TECHNOLOGY AND EQUIPMENT[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 1980, (1): 43-52.

Cited By

Cited by

Periodical cited type(1)

晏嘉陵，齐彦昌，刘明星，常子金，吴赵波，崔冰. 焊缝填充量对15Cr2Mo1耐热钢焊接修复性能的影响. 焊接. 2024(09): 56-61 .

Other cited types(1)

Get Citation

PDF

XML

Article views (503) PDF downloads (97) Cited by(2)

Turn off MathJax

Article Contents

Abstract

References

Defect generation of small sample laser welding based on generative adversarial network