Machine Learning-Based Laser Powder Bed Fusion In-Situ Monitoring Package

Additive Manufacturing (AM) is a modern and increasingly popular manufacturing process for metallic components, but it suffers from well-known problems of inconsistent quality of the finished product. As such, develop an in-situ monitoring technology for metal AM components is critically important. The developed technology must be able to perform real-time monitoring, and close-loop machine feedback, and enable the commercial machine integration. To address this critical need, X-wave Innovations, Inc. (XII) and Johns Hopkins University Applied Physics Laboratory (JHU/APL) propose to develop an advance machine learning-based in-situ monitoring (ML-ISM) package for powder bed fusion processes. This technology provides a real-time laser powder bed fusion (LPBF) process monitoring and machine learning solution to produce high-quality metallic end products. The technology development involved in-situ monitoring and advanced machine learning correlation algorithms. Upon completion, this technology is expected to be applicable to powder bed fusion AM processes for improved productivity and reduced rejected components due to inferior quality. In Phase I program, XII will demonstrate the feasibility of the machine learning-based in-situ monitoring package. In Phase II program, we will integrate the ML-ISM suite into commercial LPBF system, and accompanying software tools for operation of the ML-ISM system.