A Robust RBF-ANN Model to Predict the Hot Deformation Flow Curves of API X65 Pipeline Steel

Abstract

Abstract In this research, a radial basis function artificial neural network (RBF-ANN) model was developed to predict the hot deformation flow curves of API X65 pipeline steel. The results of the developed model was compared with the results of a new phenomenological model that has recently been developed based on a power function of Zener-Hollomon parameter and a third order polynomial function of strain power m (m is a constant). Root mean square error (RMSE) criterion was used assess the prediction performance of the investigated models. According to the results obtained, it was shown that the RBF-ANN model has a better performance than that of the investigated phenomenological model. Very low RMSE value of 0.41 MPa was obtained for RBF-ANN model that shows the robustness of it to predict the hot deformation flow curves of tested steel. The results can be further used in mathematical simulation of hot metal forming processes.