PREDICTION OF THE CONTINUOUS COOLING TRANSFORMATION DIAGRAM OF SOME SELECTED STEELS USING ARTIFICIAL NEURAL NETWORKS

Continuous cooling transformation (CCT) diagrams play an important rol e in the description of the transformation behaviour of steels. The ex perimental determination of a CCT diagram is a very time consuming and expensive task. It would therefore be very attractive to be able to p redict CCT diagrams from the chemical composition of the steel and its austenitising temperature. In this article the use of artificial neur al networks for the prediction of the transformation start and finish lines in CCT diagrams is described. The data were selected from a sing le source: The vanadium steels, atlas of continuous cooling transforma tion diagrams [4]. Three neural networks with different numbers of hid den nodes (5-10-15) were trained. The number of hidden nodes did not s ignificantly influence the accuracy in the prediction. The network wit h the least number of hidden nodes (5) was therefore chosen for the ev aluation of the performance of the neural networks. This neural networ k was able to predict the general trends in the CCT diagrams quite wel l. The relative standard deviation in the prediction of start and end temperatures of each transformation depended on the cooling rate. For the high and low cooling rates it was similar to 40 degrees C, for the intermediate it rose to 90 degrees C for the ferrite start formation and to 75 degrees C for the other diffusional transformations (pearlit e and bainite). The accuracy of the predicted CCT diagram was primaril y restricted by the modest quality of the input data used to train the neural network.