MSAM Research on Process Optimization for Offsize Ti6Al4V Powders Featured in Metal AM Magazine
August 14, 2024MSAM Lab’s research, featured in Metal AM Magazine, explores the use of machine learning algorithms to optimize process parameters for Ti6Al4V alloys in LPBF, accounting for variations in powder particle size distributions. By testing multiple predictive models trained on photodiode-based melt pool monitoring data, the study found that the Random Forest algorithm was the most effective for predicting key process parameters. Read the full paper here.
A graphical abstract illustrating the application of machine learning on MPM data, analysis of part properties, and the impact of various powder particle size distributions for estimating process parameters. (F Liravi et al. “Tailoring Laser Powder Bed Fusion Process Parameters for Standard and Off-Size Ti6Al4V Metal Powders: A Machine Learning Approach Enhanced by Photodiode-Based Melt Pool Monitoring.” Inventions 9.4 (2024): 87.)