Development and integration of feature detection algorithms for metal-based direct deposition processes
Metal-based direct energy deposition processes, such as robotic welding and laser powder fed additive manufacturing, ideally require feedback sensing of the deposition quality using vision detectors. Image processing algorithms are challenging to develop due to changing process operating conditions. Despite challenges, implementing in-process image processing algorithms is beneficial for traceability and quality assurance, for calibrating process models, and for developing closed loop control algorithms which are able to maintain deposition quality within acceptable quality margins. The objective of this research is to develop and integrate feature detection algorithms which are adaptive to the changing operating conditions typically present in metal-based direct energy deposition processes. Such algorithms are directly applicable to low-cost and industrially relevant high dynamic vision detectors. The outcomes will apply directly to future in-process vision-based sensing of features such as, but not limited to, process signatures (melt-pool size and shape, plasma plume characteristics, intensity map, particle ejections) and/or deposition qualities (geometry, continuity).