Model Reference Adaptive Control based on Neural Network for Electrode System in Electric Arc Furnace

Abstract

Control strategy of model reference adaptive control (MRAC) based on radial basis function neural network (RBFNN) online identification is proposed, and a controller is also designed. Which in accordance with the characteristics of the electrode system in electric arc furnace as the high nonlinearity, time-variant, uncertainty and multivariable input and output coupling. The validity of control strategy is verified by result of experimentation