Data-Driven Modeling of Mechanical Properties for 17-4 PH Stainless Steel Built by Additive Manufacturing

This study examines the link between microstructure and mechanical properties of additively manufactured metal parts by developing a predictive model that can estimate such as ultimate tensile strength, yield elongation at fracture based upon microstructural data for 17-4 PH stainless steel. The main benefit approach presented is generalizability, necessary testing further reduced in comparison with similar methods generate full process–structure–property linkages. Data were collected from available literature on AM-built steel, in-house imaging, conducted an AM company. After standardizing image size grain boundary extraction via processing, features distributions aspect ratios extracted. By using artificial neural networks, relationships established shape corresponding properties, subsequently, predicted novel samples to which network had not previously been exposed. produced correlation coefficients R2 = 0.957 0.939 0.931 elongation. These results demonstrate efficacy models focus microstructure–property highlight opportunity exploration modeling additive manufacturing continues improve.