Defect engineering of fatigue-resistant steels by data-driven models.

As inclusions are inevitable from the material-producing processes, an engineering concept regarding multiple features of them is needed for material design. In this study, a unique approach integrating physical-meaningful microstructure-sensitive models with the machine-learning-based data-driven model is proposed to reveal the complex relationship between the fatigue life of materials with intrinsic features of inclusions including size, stiffness, thermal properties, and extrinsic stress amplitudes. This high-fidelity presentation of the relation of these variables enables a detailed and systematic analysis of the effects of inclusions on fatigue life. The data-based phase map provides a designing envelope of inclusion features for fatigue-resistant steels. [Display omitted] • Machine-learning-based approach is integrated with microstructure-sensitive modeling for fatigue life prediction. • The integrated approach shows great predictive capability in the effect of multiple inclusions features on fatigue. • These features include size, Young's modulus, and thermal expansion coefficient of inclusions and applied stresses. • High-fidelity big data is generated by the machine-learning-based model within seconds. • The data-driven phase map provides an instant prediction of fatigue life and a guide for inclusion engineering. [ABSTRACT FROM AUTHOR]