A property-oriented design strategy of high-strength ductile RAFM steels based on machine learning

Abstract

Property-oriented design of RAFM steels can greatly enhance the opportunity to discover high-performance structural materials for fusion reactors, which has always been a big challenge. In the present work, the forward and reverse models are established, which are used to capture the mutual relationship of compositions and heat treatment conditions to tensile properties. The intelligent design model, combining the forward model with the reverse model, is developed to design the compositions and heat treatment parameters for RAFM steels with the targeted tensile properties. The validity of the intelligent design model is verified by the experimental data of three RAFM steels reported in the relevant literatures. Using this intelligent design model, a new type of RAFM steel was designed and prepared. In the test temperature range of 25–600 °C, the ultimate tensile strength of the new RAFM steel is ∼100–400 MPa higher than the conventional RAFM steels while maintaining comparable elongation. Therefore, this strategy is suitable for the property-oriented design of RAFM steels and can also be considered as a very promising approach to develop high-performance structural materials.