Artificial neural network modeling for undercooled liquid region of glass forming alloys

Abstract

Abstract A computer model based on radial base function artificial neural network (RBFANN) was designed for the simulation and prediction of undercooled liquid region Δ T x of glass forming alloys. The model was trained using data from the published literature as well as own experimental data. The performance of RBFANN model is examined by the predicted and simulated results of the influence of kinds of alloys and elements, large and minor change of element content on the reduced glass transition temperature, and composition dependence of Δ T x for La–Al–Ni ternary alloy system. The results show that the RBFANN model is reliable and adequately. Moreover, a group of new Zr–Al–Ni–Cu bulk metallic glasses is designed by RBFANN model. Their predicted Δ T x s are in agreement with the corresponding experimental values.