TY - GEN A1 - Okolo, Chukwuemeka A1 - Eissing, Katharina A1 - Williams, Richard A1 - Jensch, Felix A1 - Fergani, Omar A1 - Härtel, Sebastian T1 - Investigation of the influence of AI-controlled process parameter adjustment on the mechanical properties of LBPF-manufactured parts T2 - Materials research proceedings N2 - This study investigates the influence of machine learning (ML) based process parameter adjustments on the microstructure, relative density, and mechanical properties of laser powder bed fusion (LPBF)-manufactured components, focusing on AlSi10Mg and Ti6Al4V. The ML algorithm optimizes the thermal history by adjusting laser power and exposure time at the vector level, ensuring consistent cooling and solidification dynamics. Microscopy revealed a refined and homogeneous microstructure in the optimized AlSi10Mg samples, with reduced grain size (4.92 µm compared to 6.37 µm in non-optimized samples). Relative density analysis showed a significant improvement for optimized samples, achieving consistent values across top, middle, and bottom sections of the specimen. Hardness measurements confirmed the homogenized mechanical properties, with more uniform and elevated hardness values observed in optimized samples. This study demonstrates that ML-based process optimization minimizes defects like porosity and microcracks, enabling improved mechanical performance and efficient process qualification for LPBF-manufactured parts. The findings underline the potential of AI-driven solutions for addressing complex geometrical and thermal challenges in LPBF process. KW - LPBF-process KW - Machine learning KW - Mechanical properties Y1 - 2025 SN - 978-1-64490-359-9 U6 - https://doi.org/10.21741/9781644903599-24 SN - 2474-395X VL - 54 SP - 218 EP - 227 PB - Materials Research Forum LLC CY - Millersville, PA ER -