New insights into hydrogen trapping and embrittlement in high strength aluminum alloys

An attractive approach to mitigate hydrogen embrittlement (HE) is to use nano-sized particles to immobilize hydrogen. However, the atomic scale relationship between different particle-matrix characteristics in aluminum alloys and the susceptibility to HE is unknown. In this study, the effects of interactions between various interfaces and...

On the use of transfer modeling to design new steels with excellent rotating bending fatigue resistance even in the case of very small calibration datasets

In this research a machine learning model for predicting the rotating bending fatigue strength and the high-throughput design of fatigue resistant steels is proposed. In this transfer prediction framework, machine learning models are first trained to estimate tensile properties (yield strength, tensile strength and elongation) on the basis of...

A first step towards computational design of W-containing self-healing ferritic creep resistant steels

In this work, we combine a generic alloy-by-design model with a novel concept, the nucleation barrier for the formation of Laves phase to fill the creep cavities, in order to develop multi-component creep resistant steels with kinetically tuned self-healing behaviour. In the model the high-temperature long-term strength is estimated by...

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including high-end steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its...