Welding forming quality monitoring based on CNN-LSTM hybrid drive

WANG Jie; ZHANG Zhifen; BAI Zijian; ZHANG Shuai; QIN Rui; WEN Guangrui; CHEN Xuefeng

doi:10.12073/j.hjxb.20240707002

TRANSACTIONS OF THE CHINA WELDING INSTITUTION > 2024 > 45(11): 121-127. > DOI: 10.12073/j.hjxb.20240707002

WANG Jie, ZHANG Zhifen, BAI Zijian, ZHANG Shuai, QIN Rui, WEN Guangrui, CHEN Xuefeng. Welding forming quality monitoring based on CNN-LSTM hybrid drive[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(11): 121-127. DOI: 10.12073/j.hjxb.20240707002

Citation:

PDF (16712 KB)

Welding forming quality monitoring based on CNN-LSTM hybrid drive

WANG Jie^{1, 2,},
ZHANG Zhifen^{1, 2, ,},
BAI Zijian^{1, 2},
ZHANG Shuai^{1, 2},
QIN Rui^{1, 2},
WEN Guangrui^{1, 2},
CHEN Xuefeng^{1, 2}

1.
National Key Laboratory of Aeronautical Power Systems and Plasma Technology, Xi'an Jiaotong University, Xi'an, 710049, China
2.
School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an, 710049, China

More Information

Received Date: July 06, 2024
Available Online: October 18, 2024

Graphical Abstract

Abstract

Abstract

Welding forming quality monitoring is crucial for modern manufacturing industry, but most of the existing quality identification methods are based on single sensor, which makes it difficult to further improve the identification accuracy and has weak anti-interference ability under complex conditions. To overcome the shortcomings of single sensor identification technology, multi-source information fusion technology can make full use of the advantages of different types of sensors to achieve more comprehensive and accurate monitoring of the welding process. However, in the process of multi-information fusion, the feature mining mechanism of the deep learning model still lacks explanation, and the complementarity of different information is still unclear. In this paper, a multi-information hybrid-driven CNN-LSTM welding quality monitoring model is proposed. By fusing image and voltage signals, an average recognition accuracy of 99.72% is achieved. In addition, the visualization results show the complementary advantages between different information.
- welding forming quality,
- multi-source information fusion,
- deep learning,
- hybrid drive,
- information complementarity

FullText(HTML)

References (18)

References

[1]	白子键, 李治文, 张志芬, 等. 基于电弧光谱的核电堵管TIG焊接质量在线监测[J]. 焊接学报, 2024, 45(5): 8 − 19. Bai Zijian, Li Zhiwen, Zhang Zhifen, et al. On-line monitoring of TIG welding quality of nuclear power plug tube based on arc spectrum[J]. Transactions of the China Welding Institution, 2024, 45(5): 8 − 19.
[2]	韩旭. 焊接过程监测技术研究现状[J]. 现代制造技术与装备, 2023, 59(4): 83 − 85. Han Xu. Research status of welding process monitoring technology[J]. Modern Manufacturing Technology and Equipment, 2023, 59(4): 83 − 85.
[3]	王继锋, 陈波, 陈善本. GTAW焊接过程声音信号的分析[J]. 噪声与振动控制, 2019, 29(4): 148 − 150. Wang Jifeng, Chen Bo, Chen Shanben. Analysis of acoustic signals during GTAW welding[J]. Noise and Vibration Control, 2019, 29(4): 148 − 150.
[4]	曾安, 李迪, 潘丹, 等. 基于MSPC方法的GMAW在线监测[J]. 焊接学报, 2003, 24(1): 5 − 8. Zeng An, Li Di, Pan Dan, et al. Online monitoring platform of GMAW based on MSPC[J]. Transactions of the China Welding Institution, 2003, 24(1): 5 − 8.
[5]	洪宇翔, 杨明轩, 都东, 等. 铝合金爬坡TIG焊熔池失稳状态的视觉检测[J]. 焊接学报, 2021, 42(10): 8 − 13. Hong Xiangyu, Yang Mingxuan, Du Dong, et al. Unstable state vision detection of molten pool during aluminum alloy climbing-TIG welding[J]. Transactions of the China Welding Institution, 2021, 42(10): 8 − 13.
[6]	Gao Y F, Wang Q S, Xiao J H, et al. Penetration state identification of lap joints in gas tungsten arc welding process based on two channel arc sounds[J]. Journal of Materials Processing Technology, 2020, 285: 116762. doi: 10.1016/j.jmatprotec.2020.116762
[7]	Zhang Z F, Chen X Z, Chen H B, et al. Online welding quality monitoring based on feature extraction of arc voltage signal[J]. The International Journal of Advanced Manufacturing Technology, 2014, 70: 1661 − 1671. doi: 10.1007/s00170-013-5402-2
[8]	Wang J, Zhang Z F, Bai Z J, et al. On-line defect recognition of MIG lap welding for stainless steel sheet based on weld image and CMT voltage: Feature fusion and attention weights visualization[J]. Journal of Manufacturing Processes, 2023, 108: 430 − 444. doi: 10.1016/j.jmapro.2023.10.081
[9]	Zhang Z F, Chen S B. Real-time seam penetration identification in arc welding based on fusion of sound, voltage and spectrum signals[J]. Journal of Intelligent Manufacturing, 2017, 28: 207 − 218. doi: 10.1007/s10845-014-0971-y
[10]	Zhang Y X, You D Y, Gao X D, et al. Real-time monitoring of high-power disk laser welding statuses based on deep learning framework[J]. Journal of Intelligent Manufacturing, 2020, 31: 799 − 814. doi: 10.1007/s10845-019-01477-w
[11]	Sun H B, Zhao S C. Fault diagnosis for bearing based on 1DCNN and LSTM[J]. Shock and Vibration, 2021, 1: 1221462.
[12]	Huang J, Zhang Z F, Qin R, et al. Interpretable real-time monitoring of pipeline weld crack leakage based on wavelet multi-kernel network[J]. Journal of Manufacturing Systems, 2024, 72: 93 − 103. doi: 10.1016/j.jmsy.2023.11.004
[13]	Yu R, Kershaw J, Wang P, et al. How to accurately monitor the weld penetration from dynamic weld pool serial images using CNN-LSTM deep learning model[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 6519 − 6525. doi: 10.1109/LRA.2022.3173659
[14]	Wang J, Zhang Z F, Qin R, et al. Online identification of burn-through and weld deviation in sheet lap MIG welding based on YOLOv5[J]. Measurement Science and Technology, 2023, 35(2): 025119.
[15]	王杰, 张志芬, 秦锐, 等. 基于机器学习的不锈钢薄板MIG焊焊穿缺陷识别[J]. 电焊机, 2023, 53(9): 70 − 77. Wang Jie, Zhang Zhifen, Qin Rui, et al. Identification of MIG welding burn-through defects in stainless steel sheet based on machine learning[J]. Electric Welding Machine, 2023, 53(9): 70 − 77.
[16]	Liu J P, Wu S J, Feng Y C, et al. Optimization of the weld pool boundary calculated by the LSTM-based measurement method in GTAW[J]. Metals, 2022, 12(8): 1321. doi: 10.3390/met12081321
[17]	Joseph L P, Deo R C, Prasad R, et al. Near real-time wind speed forecast model with bidirectional LSTM networks[J]. Renewable Energy, 2023, 204: 39 − 58. doi: 10.1016/j.renene.2022.12.123
[18]	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

Cited By

Cited by

Periodical cited type(3)

1.	胡岭，余丁坤，卜永周，罗庆澄，薛松柏. Sn和Ce元素复合添加对BAg5CuZn钎料钎缝组织与性能影响. 焊接学报. 2024(04): 101-108+135 . 本站查看
2.	汪小钰，王轶，操齐高，孟晗琪，郑晶，苏瑾，胡建华，张志霄. 熔炼气雾化制备钴基粉末钎料在GH4169合金钎焊中应用. 电焊机. 2024(05): 46-51 .
3.	李淳，陈雷，司晓庆，亓钧雷，曹健. 陶瓷-金属接头残余应力调控研究综述. 机械工程学报. 2024(22): 21-39 .

Other cited types(1)

Get Citation

PDF

XML

Article views (83) PDF downloads (35) Cited by(4)

Turn off MathJax

Article Contents

Abstract

References

Welding forming quality monitoring based on CNN-LSTM hybrid drive

Abstract

References

Cited by

Periodical cited type(3)

Other cited types(1)

Catalog

Export File

Citation

Format

Content