Modeling the reversion of martensite in the cold worked AISI 304 stainless steel by artificial neural networks

Abstract

In this paper, the effect of annealing temperature and time on the reversion of strain-induced martensite to austenite in the cold worked AISI 304 stainless steel alloy was modeled by means of artificial neural networks (ANNs). The optimal ANN architecture and training algorithm were determined. The results of the ANN model were in good agreement with experimental data taken from the literature. This model can be used for determination of appropriate annealing temperature and time for grain refining of austenite through the martensite to austenite transformation.