Revisiting Stacking Fault Energy of Steels

The stacking fault energy plays an important role in the transition of deformation microstructure. This energy is strongly dependent on the concentration of alloying elements and the temperature under which the alloy is exposed. Extensive literature review has been carried out and investigated that there are inconsistencies in findings on the influence of alloying elements on stacking fault energy. This may be attributed to the differences in chemical compositions, inaccuracy in measurements, and the methodology applied for evaluating the stacking fault energy. In the present research, a Bayesian neural network model is created to correlate the complex relationship between the extent of stacking fault energy with its influencing parameters in different austenitic grade steels. The model has been applied to confirm that the predictions are reasonable in the context of metallurgical principles and other data published in the open literature. In addition, it has been possible to estimate the isolated influence of particular variables such as nickel concentration, which exactly cannot in practice be varied independently. This demonstrates the ability of the method to investigate a new phenomenon in cases where the information cannot be accessed experimentally.