Prediction of melt rate of vibrating-electrode Electroslag Remelting process using artificial neural network

This paper presents an artificial neural network (ANN) model for the prediction of melt rate of the improved Vibrating-electrode Electroslag Remelting (VESR) process, optimization of the proposed ANN with respect to different train algorithms, transfer function, and number of the hidden layer neurons is performed. The comprehensive analysis of the prediction error and the correlation coefficient shows that the resulted ANN model is reasonable, and has a better generalization and prediction accuracy.