Abstract
The stabilisation of austenite, a phenomenon that frequently occurs, renders the transformation from austenite to martensite difficult. The straightforward method of analysing the effect of a specific factor on the stabilisation of austenite is through its influence on the martensite start temperature M s. The present work outlines the use of an artificial neural network to model the M s of engineering steels based on their chemical composition and austenite grain size. The results are focused on elucidating the role in the stabilisation of austenite of alloying elements in steels, including less common elements such as vanadium and niobium, as well as the austenite grain size. Moreover, a physical interpretation of the results is presented.