Online tool condition monitoring for ultrasonic metal welding via sensor fusion and machine learning

Ultrasonic Metal Welding, Machine Learning, Smart Manufacturing, Predictive Maintenance

Nazir, Qasim ; Shao ; Chenhui

关键词: Ultrasonic Metal Welding, Machine Learning, Smart Manufacturing, Predictive Maintenance;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/108054/NAZIR-THESIS-2020.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Ultrasonic metal welding (UMW) is an important manufacturing process used for joining multi-layer, thin and conductive metals. In UMW, tool wear significantly affects the weld quality and tool maintenance constitues a substantial part of production cost. Thus, tool condition monitoring (TCM) is crucial for UMW. Despite extensive literature focusing on TCM for other manufacturing processes, limited studies are available on online TCM for UMW. Existing TCM methods for UMW require a high-resolution measurement of tool surface profiles, which leads to undesirable production downtime and delayed decision making. This research proposed a completely online TCM system for UMW using sensor fusion and machine learning (ML) techniques. A data acquisition system was designed and implemented to obtain sensor signals during welding processes. A large feature pool was then extracted from the sensing signals. A subset of features were selected and subsequently used by ML based classification models. A variety of classification models were trained and tested using experimental data. The best model achieved consistent prediction accuracy of close to 100%. The proposed TCM system not only provides real-time TCM for UMW but also can support optimal decision-making in tool maintenance. The TCM system can be extended to predict remaining useful life (RUL) of tools and and integrated with a controller to adjust welding parameters accordingly.