Online quality inspection of ultrasonic composite welding by combining artificial intelligence technologies with welding process signatures
Yang Li, Bo Yu, Baicun Wang, Tae Wha Lee, Mihaela Banu
Abstract
Ultrasonic welding is a joining technology suitable for carbon-fiber-reinforced thermoplastic (CFRTP) components because of its high throughput, and ease of automation. An effective online weld-quality inspection technology can promote the industrial application of ultrasonic composite welding. Literature focused on the quality inspection of ultrasonic composite welding is scarce. To address this, the present study proposes an online weld-quality inspection method for ultrasonic composite welding by combining artificial intelligence (AI) technologies with welding process signatures. The failure load in a tensile-shear test and the weld quality level (i.e., under weld, normal weld, and over weld) are predicted simultaneously using artificial neural network (ANN) and random forest (RF) models. Eight features consisting of the duration and energy at each welding stage are extracted from the process signatures as independent variables. The results indicate that both the ANN and RF models exhibit high prediction accuracies. The weld quality can be assessed comprehensively and reasonably by considering both the failure load and weld quality level. The findings of this study demonstrate the feasibility of online weld-quality inspection for ultrasonic composite welding.