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 highend steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its effects have not been demonstrated and systematically analysed nor experimentally validated with prototype alloys. To address this issue, a physical metallurgy (PM) -guided ML model was developed, wherein intermediate parameters were generated based on original inputs and PM principles, e.g., equilibrium volume fraction (V f ) and driving force (D f ) for precipitation, and these were added to the original dataset vectors as extra dimensions to participate in and guide the ML process. As a result, the ML process becomes more robust when dealing with small datasets by improving the data quality and enriching data information. Therefore, a new material design method is proposed combining PM-guided ML regression, ML classifier and a genetic algorithm (GA). The model was successfully applied to the design of advanced ultrahigh-strength stainless steels using only a small database extracted from the literature. The proposed prototype alloy with a leaner chemistry but better mechanical properties has been produced experimentally and an excellent agreement was obtained for the predicted optimal parameter settings and the final properties. In addition, the present work also clearly demonstrated that implementation of PM parameters can improve the design accuracy and efficiency by eliminating intermediate solutions not obeying PM principles in the ML process. Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.

No abstract

Modeling retained austenite in quenching and partitioning (Q&P) steels remains a challenge, and the conventional 'constrained carbon equilibrium' (CCE) model fails to predict the optimal condition for achieving the maximal amount of retained austenite in various systems, which impedes the optimization of the Q&P process. One of the main limitations is that the possible decomposition of austenite to bainite during partitioning is completely ignored by the essential assumptions of the Q&P process and hence the associated CCE model. In this study, a CCET model that combines the conventional CCE model with the T0 model for the bainitic transformation and incorporates the effect of the isothermal bainitic transformation to describe the austenite stability during the Q&P process has been proposed. A detailed comparison between the experimental observation and model predictions demonstrated that the retained austenite could be better described by the CCET model, including its carbon content. The current model therefore provides a more accurate approach for tailoring the amount and stability of retained austenite after the Q&P processing of Fe-C-Mn-Si steels.

No abstract

No abstract