Research Progress of Welding Defect Detection Based on Machine Vision
DOI:
https://doi.org/10.61173/14k2c164Keywords:
Machine vision, Image acquisition, Artificial intelligence, Welding defects, Detection technologyAbstract
Welding defect detection is an important technical method and means to ensure welding quality in the welding process. The traditional manual inspection has the problems of low accuracy and low measurement efficiency, which cannot meet the requirements of modern industrial production. With the continuous development of artificial intelligence, using machine vision instead of human to detect welding defects intelligently has become the direction of development. The main processes of welding defect detection based on machine vision is to first collect images, then analyze and preprocess images, and finally use artificial intelligence to identify and classify welding defects. Therefore, this paper mainly summarizes and analyzes the current research progress of welding defect detection from two aspects: welding image acquisition and preprocessing, and defect detection and classification methods. It focuses on the defect detection and classification methods based on machine learning. Furthermore, this paper puts forward the problems to be improved and solved, and looks forward to the future development trend.References
defect detection can be further improved and optimized, Jiaotong University, 2016, 50(S1): 55-58. welding defect detection systems based on machine vision [2] Wu Yifei, Fu Qiang, Qi Jiacheng. Automatic welding can also play an increasingly important role in modern in- technology for circular seam of spherical tank based on passive
dustrial production. vision sensor. Electric Welding Machine, 2019, 49(09): 91-94. At present, the welding defect detection research based [3] Xu Yanling, Yu Huanwei, Zhong Jiyong, et al. Real-time Dean&Francis seam tracking control technology during welding robot GTAW [13] D’Angelo Gianni, Salvatore Rampone. Feature extraction process based on passive vision sensor. Journal of Materials and soft computing methods for aerospace structure defect
Processing Technology, 2012, 212(8): 1654-1662. classification. Measurement, 2016, 85: 192-209. [4] Niu Zhangqi. Research on the geometric parameter [14] Tang Maojun. Research on welding seam defect detection measurement and the surface defect recognition for the weld of system based on machine vision. Guizhou University, 2022. steel structural components based on machine vision. Chang’an [15] Guo Junlei. Surface defect detection system for welding
University, 2023. product based on machine vision. Nanjing University of [5] Huang Seji. Research on typical weld seam feature extraction Aeronautics and Astronautics, 2014. and real-time seam tracking base on active vision. Shanghai Jiao [16] Gao Changlin. Key technology of welding defect diagnosis
Tong University, 2017. and process optimization expert system for large aluminum alloy [6] Lu Jun, Zhang Jun, Luo Jun, et al. Plate additive, seam- tank. Wuhan University of Technology, 2022. tracking technology based on feature segmentation. Optics and [17] Malarvel Muthukumaran, Harjeet Singh. An autonomous
Laser Technology, 2024, 168. technique for weld defects detection and classification using [7] Zhao Xinyu, Jiang Deshun, Li Zhengguang, et al. Welding multi-class support vector machine in X-radiography image.
defect identification based on high-frequency ultrasonic testing. Optik, 2021, 231.
Nondestructive Testing, 2023, 45(11): 20-23+52. [18] Xu Jingyuan, Yu Huanwei, Xiao Runquan, et al. Features [8] Zeng Wei, Cai Fangming, Wang Fei, et al. Finite element detection of Al alloy porosity during GTAW process based on simulation of laser-generated ultrasonic waves for quantitative arc spectrum and improved porosity-focus decision tree. Journal
detection of internal defects in welds. Optik, 2020, 221. of Manufacturing Processes, 2023, 88: 71-83. [9] Luo H, Chen Q. H, Lin W. Graphic augmented defect [19] Ho Mei-Po, Ngai Wing-Kit, Chan Tai-Wing, et al. An recognition for phased array ultrasonic testing on tubular TKY artificial neural network approach for parametric study on
joints. Journal of Nondestructive Evaluation, 2020, 39(3). welding defect classification. International Journal of Advanced [10] Li Yanfeng. Welding Seam Image Recognition and Manufacturing Technology, 2022, 120(1-2): 527-535.
Intelligent Detection. Beijing: Chemical Industry Press, 2023. [20] Zhu Haixing, Ge Weimin, Liu Zhenzhong. Deep learning- [11] Vilar R, Zapata J, Ruiz R. Classification of welding defects based classification of weld surface defects. Applied Sciences,
in radiographic images using an adaptive-network-based fuzzy 2019, 9(16). system. International Work-conference on the Interplay between [21] Chang Yasheng, Wang Weiku. A deep learning-based weld
Natural and Artificial Computation, 2011. defect classification method using radiographic images with a [12] Boaretto Neury, Tania Mezzadri Centeno. Automated cylindrical projection. IEEE Transactions on Instrumentation
detection of welding defects in pipelines from radiographic and Measurement, 2021, 70.
images DWDI. NDT & E International, 2017, 86: 7-13.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
