IEEE North Jersey Section: RAS Chapter and SMC Chapter joint seminar

IEEE North Jersey Section: RAS Chapter and SMC Chapter joint seminar on

Human-Robot Collaborative Learning of Human Welder Intelligence for Enhancing Human Welder Skills and Robotizing Complex Welding Processes

YuMing Zhang

James R. Boyd Professor of Electrical Engineering, University of Kentuck

Place: https://njit.webex.com/meet/zhou

Time: 9:30am-10:30am, May 21, 2022

For precision joining, skilled welders currently overperform welding robots due to their adaptation to the process. This is a kind of human intelligence that may be used to equip welding robots for them to become more intelligent and help welders to reduce the needed training time. A major challenge in learning such intelligence arises from the specular nature of pool surface that disqualifies diffuse reflection-based laser triangulation methods. To overcome this issue, the mirror surface is advantageously used to reflect a laser pattern away from the arc, simultaneously eliminating the arc illumination problem. To allow welders to freely demonstrate their skills, a human-robot collaborative system has been established where a welder carries a virtual torch, similarly as operating an actual one, without a sensor. The movement is measured at the virtual system and then followed by a robot which carries the sensor and performs the actual welding. The measured weld pool is displayed to the operator at the virtual site such that the welder can observe the change in the operation result to adjust his/her torch movement and other parameters. The true intelligence of the welder is thus contained in and can thus be extracted from the resultant data. For more complex welding processes that require operations of multiple welding torches/tools, their robotization are more challenging complex. A possible solution is also to learn from human welders as they are quicker learners who can adjust their operations to stabilize the complex welding process. This involves simultaneous operations from multiple welders and capture of the data needed to learn. Human-robot collaboration again provides an environment to enable the operation and capture the “true” data for learning of the intelligence needed despite the complexity of multiple operations.

Bio: Dr. YuMing Zhang’s research focuses on intelligent robotic and human-robot collaborative welding systems. His research has been supported by the NSF, Navy, National Labs and industry, brought him 12 US patents, and over 200 journal publications. His recognition includes Fellow of the American Welding Society (AWS), Fellow of the American Society of Mechanical Engineers (ASME), and Fellow of the Society of Manufacturing Engineers (SME); Dean’s Award for Excellence in Research from the College of Engineering. Five of his graduate students won the IIW (International Welding Institute) Henry Granjon Prize on behalf of the US against IIW member countries’ national winners for dissertation/thesis research. Dr. Zhang is currently one of the two Editors for the Journal of Manufacturing Processes published by the SME. He is, and has been, Associate Editor/Editorial Board Member for a number of major international journals including the IEEE Transactions on Automation Science and Engineering.

Speaker(s): Yuming Zhang,

323 Dr Martin Luther King Jr Blvd., ECE-NJIT, Newark, New Jersey, United States, 07102-1982