Key Technologies of Intelligentized Welding Manufacturing

Dr. Yiming  Huang received his B.S. degree and Ph.D. degree in Materials Processing Engineering from the School of Materials Science and Engineering, Shanghai Jiao Tong University, in 2011 and 2017 respectively. He joined the School of Materials Science and Engineering, Tianjin University in 2017, and he is currently as a lecturer. His research interests include welding process modeling, machine learning, and defect detection. He has published several papers in international conferences and reputed journals in his research area.Dr. Shanben Chen received his BS degree in industrial automation from Dalian Railway Institute (Dalian Jiao Tong University) in 1982, and received his MS and PhD in control theory and application from Harbin Institute of Technology, China, in 1987 and 1991, respectively. He worked as a postdoctoral fellow at the National Key Laboratory of Advanced Welding Production of China in Harbin Institute of Technology (HIT) from 1993 to 1995, and as a professor from 1995 to 2000. From 2000 to present, he has served as the Special Professor, Cheung Kong Scholar Program of the Ministry of Education of China & Li Ka Shing Foundation, Hong Kong, and engaged at Shanghai Jiao Tong University, China, where he is also director of the Intelligentized Robotic Welding Technology Laboratory. Prof. Chen has also been a visiting professor at the University of Western Sydney (UWS) in connection with the ARC Linkage collaboration since 2009. Currently, Prof. Chen is a senior member of the IEEE; a member of the American Welding Society; Chair of the Robotics & Automation Committee of the Chinese Welding Society (CWS); Deputy Secretary-General of the Chinese Welding Society; and a standing member of the Board of Directors, CWS.

• Introduction.- Monitoring principle of welding process based on arc emission spectrum.- Experimental setup made of welding and spectral acquisition subsystems.- Prediction of welding status based on features extracted from the whole arc spectrum.- Prediction of welding status based on features extracted from spectral lines of interest.- The control of welding quality based on spectral features.- Summary and conclusions.