MODELING AND CONTROL OF AN ELECTRIC-ARC FURNACE USING A FEEDFORWARD ARTIFICIAL NEURAL-NETWORK

Previous studies have shown that the electric arc furnace is chaotic i n nature and hence standard control techniques are not effective. Howe ver, human (heuristic) control is used every day on electric arc furna ces. A furnace operator assesses the performance of the furnace and ma kes judgments based on past experience and intuition. In order to impr ove the effectiveness of this control, a qualitative understanding of the operating conditions of the furnace is required. Artificial neural networks are capable of learning the system dynamics of the electric arc furnace. This article describes a feedforward neural network train ed to model arc furnace electrical wave forms taken from an experiment al arc furnace. The output of this model is then used in estimating th e future state of the furnace for control purposes.