Microstructure–property relation and machine learning prediction of hole expansion capacity of high-strength steels

Abstract The relationship between microstructure features and mechanical properties plays an important role in the design of materials improvement properties. Hole expansion capacity a fundamental defining formability metal sheets. Due to complexity experimental procedure testing hole capacity, where many influencing factors contribute resulting values, this relation is not yet fully understood. In present study, dataset containing phase constituents 55 microstructures as well corresponding properties, such yield strength, collected from literature. Statistical analysis these data conducted with focus on individual phases, combinations phases number phases. addition, different machine learning methods prediction based both fractions chemical content. Deep gives best accuracy composition. Meanwhile, influence revealed. Graphical abstract