- Ei Compendex
- Scopus
- DOAJ
- Chinese Science Citation Database (CSCD)
- World Journals Clout Index Report
- T1 level in Directory for Mechanical EngineeringDisciplines
| Citation: |
GAI Shengnan, WANG Yu, XU Bin, WANG Kai, XIAO Jun, CHEN Shujun. Monitoring of aluminum alloy weld formation using TIG based on passive vision[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2025, 46(4): 32-40. DOI: 10.12073/j.hjxb.20240102001
|
During the butt-welding process of thin-plate aluminum alloys, the base metal was affected by fluctuations in the joint gap and uneven heating and heat dissipation. As a result, the weld was usually defective. A passive vision sensing method was selected to capture the front-side welding images which contained dynamic changes in the molten pool. A weld formation image database for the thin-plate aluminum alloy with a thickness of 3 mm using butt tungsten inert gas (TIG) was established. A double-layer tandem weld formation prediction network model was proposed to predict the weld formation under conditions such as incomplete penetration, normal penetration, over-penetration, burn-through, left misalignment, and right misalignment. The first-layer weld formation prediction network predicted three types of irregular weld formations, such as burn-through, left misalignment, and right misalignment, as well as normal weld formation. The second-layer weld penetration prediction network further classified the images of normal weld formations into incomplete penetration, normal penetration, and over-penetration. Different datasets were used to train the model, respectively. The image-enhanced dataset showed the most excellent performance, and the overall prediction accuracy of the model could reach 95%. Welding tests with varying joint gap fluctuations, heat dissipation, and misalignments were carried out, verifying that the model could accurately classify six types of different weld formations in image sequences.
| [1] |
FA Y Z, ZHANG B X, YA W, et al. Welding anomaly detection based on supervised learning and unsupervised learning[J]. China Welding, 2022, 31(3): 24 − 29.
|
| [2] |
WANG X P, D’AVELLA S, LIANG Z M, et al. On the effect of the attention mechanism for automatic welding defects detection based on deep learning[J]. Expert Systems with Applications, 2025, 268: 126386. doi: 10.1016/j.eswa.2025.126386
|
| [3] |
刘秀航, 叶广文, 黄宇辉, 等. 激光-MIG复合焊根部驼峰缺陷预测[J]. 机械制造文摘-焊接分册, 2023(3): 18 − 24.
LIU Xiuhang, YE Guangwen, HUANG Yuhui, et al. Root hump defect prediction for laser-MIG hybrid welding[J]. Welding Digest of Machinery Manufacturing, 2023(3): 18 − 24.
|
| [4] |
王天琪, 孟锴权, 王传睿. 基于GA-BP神经网络的多层多道焊工艺预测及优化[J]. 焊接学报, 2024, 45(5): 29 − 37. doi: 10.12073/j.hjxb.20230523001
WANG Tianqi, MENG Kaiquan, WANG Chuanrui. Prediction and optimization of multi-layer and multi-pass welding process parameters based on GA-BP neural network[J]. [J]. Transactions of the China Welding Institution, 2024, 45(5): 29 − 37. doi: 10.12073/j.hjxb.20230523001
|
| [5] |
汲生鹏, 闫志鸿, 刘嘉, 等. 基于深度学习的薄板TIG焊焊缝成形视觉检测[J]. 热加工工艺, 2022, 51(3): 115 − 121.
JI Shengpeng, YAN Zhihong, LIU Jia, et al. Visual detection of TIG weld forming of thin sheet based on deep learning[J]. Hot Working Technology, 2022, 51(3): 115 − 121.
|
| [6] |
姚屏, 李文强, 陈威, 等. 基于鲸鱼优化算法的焊缝尺寸预测[J]. 焊接学报, 2024, 45(11): 133 − 139.
YAO Ping, LI Wenqiang, CHEN Wei, et al. Prediction of weld size prediction based on whale optimization algorithm[J]. Transactions of the China Welding Institution, 2024, 45(11): 133 − 139.
|
| [7] |
WANG Z J, ZENG Z T, WU S J, et al. Weld penetration control of wire-filled pulsed gas tungsten arc welding of pipe in the horizontal position[J]. Welding in the World, 2023, 67(7): 1793 − 1807. doi: 10.1007/s40194-023-01516-4
|
| [8] |
BACIOIU D, MELTON G, PAPAELIAS M, et al. Automated defect classification of aluminium 5083 TIG welding using HDR camera and neural networks[J]. Journal of Manufacturing Processes, 2019, 45: 603 − 613. doi: 10.1016/j.jmapro.2019.07.020
|
| [9] |
LI C N, CHE H, XIONG J. Monitoring weld penetration of laser-arc hybrid welding joints without full-penetration requirement based on deep learning[J]. Optics & Laser Technology, 2024, 172: 110538.
|
| [10] |
ZHANG X D, WANG F, Chen Y R, et al. Weld joint penetration state sequential identification algorithm based on representation learning of weld images[J]. Journal of Manufacturing Processes, 2024, 120: 192 − 204. doi: 10.1016/j.jmapro.2024.04.024
|
| [11] |
胡继涛, 马晓锋, 赵荣丽, 等. 基于轻量级DeepLabV3 + 网络的焊接熔池图像分割方法[J]. 计算机集成制造系统, 2025, 31(1): 126 − 134.
HU Jitao, MA Xiaofeng, ZHAO Rongli, et al. Welding pool image segmentation method based on lightweight DeepLabV3 + network[J]. Computer Integrated Manufacturing Systems, 2025, 31(1): 126 − 134.
|
| [12] |
LIU W B, WANG Z D, TIAN L L, et al. Melt pool segmentation for additive manufacturing: a generative adversarial network approach[J]. Computers and Electrical Engineering, 2021, 92: 107183. doi: 10.1016/j.compeleceng.2021.107183
|
| [1] | HUANG Hongxing, WU Di, ZENG Da, PENG Biao, SUN Tao, ZHANG Peilei, SHI Haichuan. Quantitative evaluation of spatter in adjustable ring mode laser welding based on In-situ OCT measurement[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(11): 128-132. DOI: 10.12073/j.hjxb.20240715002 |
| [2] | 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 |
| [3] | BAI Zijian, ZHANG Zhifen, WANG Jie, ZHANG Shuai, SU Yu, WEN Guangrui, CHEN Xuefeng. Dilution rate monitoring of DED based on a spectral physical feature perception network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(11): 95-100. DOI: 10.12073/j.hjxb.20240701002 |
| [4] | ZHU Ming, LEI Runji, WENG Jun, WANG Jincheng, SHI Yu. MIG weld seam tracking system based on image automatic enhancement and attention mechanism deep learning[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(11): 90-94. DOI: 10.12073/j.hjxb.20240718002 |
| [5] | MA Jiawei, SUN Jingbo, CHI Guanxin, ZHANG Guangjun, LI Xinlei. Weld identification and robot path planning algorithm based on stereo vision and YOLO deep learning framework[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(11): 45-49. DOI: 10.12073/j.hjxb.20240720001 |
| [6] | WANG Rui, GAO Shaoze, LIU Weipeng, WANG Gang. A lightweight and efficient X-ray weld image defect detection method[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(7): 41-49. DOI: 10.12073/j.hjxb.20230630003 |
| [7] | BAI Zijian, LI Zhiwen, ZHANG Zhifen, QIN Rui, ZHANG Shuai, XU Yaowen, WEN Guangrui. 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. DOI: 10.12073/j.hjxb.20230610002 |
| [8] | XU Donghui, MENG Fanpeng, SUN Peng, ZHENG Xuchen, CHENG Yongchao, MA Zhi, CHEN Shujun. Online monitoring of GMAW welding defect based on deep learning[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2024, 45(3): 114-119. DOI: 10.12073/j.hjxb.20230117002 |
| [9] | WANG Rui, HU Yunlei, LIU Weipeng, LI Haitao. Defect detection of weld X-ray image based on edge AI[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(1): 79-84. DOI: 10.12073/j.hjxb.20210516001 |
| [10] | LI Hexi, HAN Xinle, FANG Zaojun. A visual model of welding robot based on CNN deep learning[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2019, 40(2): 154-160. DOI: 10.12073/j.hjxb.2019400060 |
| 1. |
韩莹，何实，吕晓春，郭枭，焦帅杰. 粗晶铝合金超塑性变形机理的研究现状. 焊接. 2023(03): 11-21+26 .
| |
| 2. |
谢吉林，汪洪伟，陈玉华，刘文阔，张体明，王善林. Al/Mg搅拌摩擦点焊–钎焊接头的微观组织与拉伸剪切性能研究. 航空制造技术. 2023(11): 59-65+76 .
| |
| 3. |
刘文阔，谢吉林，陈玉华，汪洪伟，张体明，王善林. 搅拌针对FSSW-B接头界面组织与力学性能的影响. 稀有金属材料与工程. 2023(07): 2468-2477 .
| |
| 4. |
舒伟. 基于铝合金先进焊接工艺的探索. 现代制造技术与装备. 2022(03): 171-173 .
| |
| 5. |
余光伟，谢清程，杨珺柳，施睿赟，蔡翔宇，李文海. 油管模型建立及结构对称性对其残余应力影响. 焊接学报. 2022(03): 101-112+119-120 .
本站查看
|
Supported by:
Beijing Renhe Information Technology Co. Ltd
DownLoad: