Prediction and Optimization of Stretch-Flangeability of Advanced High Strength Steels through Microstructure-Property Correlations Utilizing Machine Learning Approaches

Advanced high strength steels (AHSS) exhibit diverse mechanical properties due to their complex microstructures. Existing machine learning (ML) studies often focus on specific steel grades, limiting generalizability in predicting and optimizing AHSS properties. Here, an ML framework was presented to predict and optimize the stretch-flangeability of AHSS based on microstructure-property correlations, using datasets from 212 steel conditions. Support vector machine, symbolic regression, and extreme gradient boosting models accurately predicted hole expansion ratio (HER), ultimate tensile strength (UTS), and total elongation (TE). Shapley additive explanations revealed the importance of bainite, martensite, and ferrite volume fractions for HER, UTS, and TE, respectively. Multi-objective optimization generated 170 optimized conditions with improved comprehensive mechanical properties. The best optimized microstructural features (7.2% ferrite, 44.5% bainite, 40.5% martensite, 7.8% tempered martensite) yielded HER of 113.6%, UTS of 999.6 MPa, and TE of 25.0%. This systematic framework enables efficient prediction and optimization of material properties, with potential applications across various fields of materials science.