Non-destructive evaluation of the friction stir welding process, generalizing a deep neural defect detection network to identify internal weld defects across different aluminum alloys

Friction stir welding (FSW) is a solid-state welding process, which has significantly disrupted welding technology particularly for aluminum alloy applications. Due to its high-quality welds in all aluminum alloys, comparatively low heat input with high energy efficiency and ecological friendliness, FSW is used in a rapidly growing number of applications. Currently, destructive and non-destructive testing methods are attached as a separate process step to verify weld seam quality, detecting imperfections late in production and requiring costly rework or scrapping of the assembly. Various studies have shown the possibility of using deep neural networks (DNN) to evaluate weld quality and detect welding defects based on recorded data. In this study, conducted within the scope of RWTH Aachen's Cluster of Excellence, Internet of Production, recurrent neural networks (RNN), and convolutional neural networks (CNN) were successfully trained to classify FSW force data sets, generated while joining different aluminum alloys over a wide range of welding parameters. For internal weld defects bigger than 0.08 mm, detection accuracies over 95% were achieved using bidirectional long short-term memory (BiLSTM) networks when limited to a single alloy and thickness. The classification accuracy dropped to similar to 90% when using multiple alloys and sheet thicknesses. The comparison between different network types' classification accuracy as well as their ability to generalize the defect detection across different welding tasks with varying sheet thicknesses, respective welding tools, and different Al alloys is shown. The systems aim at offering a reliable and cost-efficient quality monitoring solution with a wide range of applicability, increasing the acceptance of the friction stir welding process as well as confidence in the resulting weld seam quality.