Application of Fuzzy Neural Control in the Electrode regulator system of arc furnace

The fuzzy neural control is applied in the electrode regulator systems of arc furnace. The detailed design method is presented. The fuzzy neural networks are used as both controller and identifier. The parameters of the controller could be on-line adjusted according to the information of the identifier. The self-learning arithmetic of the fuzzy neural network is derived. The initial rules parameters of fuzzy neural controller are determined from experience, therefore the on-line learning speed of the controller is improved. Simulation results show that the method can effectively reject the disturbance of arc length by on-line learning and thus possess the good robustness. The proposed control system is superior to the conventional PID control system