| Abstract Scope |
Process stability is essential for the successful creation of parts and materials using wire-arc additive manufacturing (WAAM). Since WAAM defects can be generated through multiple mechanisms, no single sensor can provide a comprehensive process evaluation. A multi-mode monitoring scheme is under exploration as optical, thermal, chemical and acoustic sensors have been synchronized with arc waveform and robot motion trajectories. Data acquisition is performed using threaded Python scripts with C++ and vendor software development kits (SDKs). Disparate sensor modalities afford the opportunity to interrogate the deposition process across melt pool, part surface and equipment scales. On-going work is focused on identifying critical process signatures and developing multi-signature correlations with process outcomes such as melt pool behavior, material interpass temperature, deposited bead geometry and final part shape. These correlations have been examined using data analytic techniques ranging from conventional regression to machine learning and neural networks. |