Fuzzy Neuron Hybrid Control for Continuous Steel Casting

Authors:	Tao Jili, Zhejiang University, China Wang Ning, Zhejiang University, China
Topic:	6.2 Mining, Mineral & Metal Processing
Session:	Technology in Mining and Metal Processing Industry
Keywords:	continuous casting, mold level control, fuzzy neuron hybrid control, model-free control

Abstract

The fuzzy neuron hybrid control method is proposed for mold level control of the continuous steel casting in this paper. The dynamic characteristics of the continuous steel casting process is described. To the plant with big uncertainties and grave nonlinearities, the fuzzy neuron hybrid control system is set up and the new model-free controller is designed. In this control system, the fuzzy neuron hybrid controller is constructed by the fuzzy PI controller and the neuron controller, the gain of the neuron controller is tuned by using a fuzzy algorithm. The simulation tests of mold level control are made under various conditions with different casting speeds, new gate valve and old gate valve, changing in the valve position loop gain. The results demonstrate that the new controller has good performances, very strong robustness and adaptability.