Effects of carbon concentration and cooling rate on continuous cooling transformations predicted by artificial neural network

Employing 151 continuous cooling transformation (CCT) diagrams, an artifici al neural network (ANN) has been modeled and trained. The CCT diagrams of a class of Fe-xC-0.4Si-0.8Mn-1.0Cr-0.003P-0.002S (x within 0.1 through 0.6) steels are predicted by the model developed. It indicates that an increase in carbon concentration (C%) gives rise to a decrease in ferrite start (Fs) , bainite start (BS), and martensite start (MS) temperatures, but the carbo n concentration has weak effect on the pearlite end (Pe) temperature. The r ate of decrease, partial derivative Fs/partial derivative C, further depend s on the carbon concentration. The carbon dependence predicted by the ANN i s consistent with what is predicted by thermodynamic models. The Fs tempera ture is a Iso affected by the cooling rate (nu), especially for high carbon steels and nu > 0.1 degrees C/s. C prolongs the incubation period of ferri te formation, but accelerates the overall growth kinetics of the pearlite r eaction. The Fs and Pe temperatures at low cooling rates predicted by the A NN model are in agreement with those predicted by thermodynamic models. The deviations of Re and Fs from their thermodynamic equilibrium counterparts are nearly independent of the carbon concentration. The minimum undercoolin g for both ferrite and pearlite reactions is around 50 degrees C. It increa ses up to 100 degrees C at higher cooling rates. Pre-bainite decomposition of austenite retards bainite formation. Employing the Ms temperature, the c ritical driving force for heterogeneous athermal nucleation is also estimat ed and related to the Ms temperature. Ms temperatures predicted by this mod el prove to be consistent with those predicted by several empirical linear models. It can be concluded that the current ANN model is reliable and effe ctive.