Machine Learning Tools to Optimize Metal Additive Manufacturing Process Parameters to Enhance Fatigue Performance of Aircraft Components

In this SBIR effort, TDA and its team partners propose to develop a comprehensive toolset based on an Integrated Computational Material Engineering (ICME) framework using Machine Learning (ML) and Artificial Intelligence (AI) algorithms to predict mechanical performance and fatigue life in additively manufactured (AM) metallic components. The toolset addresses fatigue contributing factors, including defect distribution, surface roughness, residual stress, and microstructure effects, including the influence of post-processing treatments. It provides suggested design, process, and post-process parameters to optimize fatigue and mechanical performances.   The key products from the proposed framework are: (1) combined in-situ process monitoring methods of acoustic monitoring of laser/melt pool interactions to identify flaw formation, high speed imaging to identify splat formation; and thermal imaging to identify hot spot formation, all enabled by machine vision and machine learning analyses; (2) ML and AI based algorithms to forecast fatigue contributing factors (e.g., defects distribution, surface roughness residual stress and microstructure) based on in-situ process monitoring, ex-situ process analysis and FEM models; (3) Fatigue prediction algorithms based on database built upon crystal plasticity and stored energy theories, and AI algorithms; (4) critical verification and validation experiments; and (5) surrogate based optimization toolsets.