Modelling the continuous cooling transformation diagram of engineering steels using neural networks

Abstract

Abstract The neural network model of Van der Wolk et al. [1] describes the effect of composition on the phase regions of the continuous cooling transformation (CCT) diagram, yet does not consider the fractions of microstructural components and the hardness data that are often quoted in CCT diagrams. In the present paper, the construction of two more neural network models, one for the fractions of ferrite, pearlite, bainite and martensite in the microstructure, and one for the hardness after cooling, using the data of 338 and 412 diagrams, respectively. The accuracy of each model was found to be similar to the expected experimental error; moreover, the models were found to be mutually consistent, although they have been constructed independently. Furthermore, the trends in these properties for alloying elements can be quantified with the models, and are largely in line with metallurgical expectations.