Abstract
In this paper, aiming at the online monitoring of weld quality in welding process, a real-time monitoring system based on visual sensing technology was proposed. Based on the SDM method, the edge features of molten pool image are extracted, and the features of molten pool area, width, half-length, and back width are further obtained. Based on the extracted image features and welding process parameters, a stochastic forest penetration model was built to classify and identify the penetration status in the welding process and to predict the weld back penetration width regression. The classification and recognition rate of random forest penetration model is 89.8%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen SB, Lv N (2014) Research evolution on intelligentized technologies for arc welding process. J Manuf Process 16(1):109–122
Lv N et al (2014) Real-time control of welding penetration during robotic GTAW dynamical process by audio sensing of arc length. Int J Adv Manuf Technol 74(1–4):235–249
Lv N et al (2017) Automated control of welding penetration based on audio sensing technology. J Mater Process Technol 250:81–98
Lv N et al (2014) Real-time control of welding penetration during robotic GTAW dynamical process by audio sensing of arc length. Int J Adv Manuf Technol 74(1–4):235–249. [18] Wang Y, Zhao P (2001) Plasma-arc welding sound signature for on-line quality control. ISIJ Int 41(2):164–167
Zeng J, Chang B, Du D et al (2016) A visual weld edge recognition method based on light and shadow feature construction using directional lighting. J Manuf Process 24(Part 1):19–30
Xu Y, Fang G, Lv N et al (2015) Computer vision technology for seam tracking in robotic GTAW and GMAW. Robot Comput-Integr Manuf 32:25–36
Zhang G, Wu CS, Liu X (2015) Single vision system for simultaneous observation of keyhole and weld pool in plasma arc welding. J Mater Process Technol 215:71–78
Gao J, Qin G, Yang J et al (2011) Image processing of weld pool and keyhole in Nd: YAG laser welding of stainless steel based on visual sensing. Trans Nonferrous Metals Soc China 21(2):423–428
Fan C, Lv F, Chen S (2009) Visual sensing and penetration control in aluminum alloy pulsed GTA welding. Int J Adv Manuf Technol 42(1–2):126–137
Wu D et al (2017) VPPAW penetration monitoring based on fusion of visual and acoustic signals using t-SNE and DBN model. Mater Des 123:1–14
Zhou ZF (2005) Welding metallurgy: weldability of metal. China Machine Press, Beijing, pp 125–129
Ma H, Wei S, Lin T et al (2010) Binocular vision system for both weld pool and root gap in robot welding process. Sens Rev 30(2):116–123
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 51969001), the Guangxi Major Science and Technology Projects of China (No. GuikeAA17204030), the Guangxi Natural Science Foundation of China (No. 2018GXNSFAA138080), and the Guangxi Science and Technology Base and Talent Project of China (No. GuikeAD18281007).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Han, J., Feng, Z., Jiao, Z., Han, X. (2021). The Research of Real-Time Welding Quality Detection via Visual Sensor for MIG Welding Process. In: Chen, S., Zhang, Y., Feng, Z. (eds) Transactions on Intelligent Welding Manufacturing. Transactions on Intelligent Welding Manufacturing. Springer, Singapore. https://doi.org/10.1007/978-981-33-6502-5_4
Download citation
DOI: https://doi.org/10.1007/978-981-33-6502-5_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6501-8
Online ISBN: 978-981-33-6502-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)