Decoupling Control for Electrode System in Electric Arc Furnace based on Neural Network Inverse Identification

Abstract

RBF neural network based on nearest neighbor clustering algorithm is applied for three-phase electrode system in electric arc furnace. Real-time on-line decoupling of MIMO inverse system is realized, and transfers MIMO system with strong coupling into individual pseudo linear plant. On the base of these, the method dealing linear system can be used for the pseudo linear system. The simulation and experiments indicate that this strategy is suitable for engineering