New monitoring criteria for instability detection by Machine Learning in Additive Manufacturing: Application to Wire Arc Additive Manufacturing process

Process monitoring is crucial for ensuring both part quality and process stability in Wire Arc Additive Manufacturing (WAAM). Arc electrical signals have been shown to be valuable indicators of process dynamics, as they reflect variations in stability during deposition. This study explores the application of signal processing and machine learning techniques to analyze these arc signals, aiming to extract relevant features for detecting instability. A machine learning classifier is used to distinguish between stable and unstable process states. The results demonstrate the potential of these monitoring criteria for instability detection, offering a tool for quality assurance and improved performance in WAAM. Finally, a case study is presented to show the practical application of the model in detecting local instability within a deposition layer.