An Artificial Intelligence Approach to Develop a Time-Series Prediction Model of the Arc Furnace Resistance

Abstract

The control scheme of an arc furnace electrode positioning system aims to deliver an optimum stable reaction zone below the electrodes by maintaining a fixpoint resistance. However, because of random movement of melted materials during melting period, the resistance of the arc furnace changes randomly. As a result, the electrodes have to move accordingly to obtain a fix-point resistance. Moreover, it is often found that the arc furnace resistance changes very fast and it is impossible for the electrode to track the random change of resistance. Consequently, the furnace becomes unstable and it is often impossible to achieve required production per unit power. Hence, the control system often relies on prediction tools. However, it is difficult to predict the arc furnace resistance using conventional mathematical models. As a result, in this paper, Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to capture the random and time-varying nature of arc furnace resistance. The performance of the proposed model is evaluated by presenting a case study where the outputs of the proposed model are compared with the data recorded from an actual metallurgical plant.

A novel power management control strategy for a renewable stand-alone power system

“…An accurate wind and load prediction is a key factor that ensures a robust performance of the EMPRS. In several studies conducted earlier, it was demonstrated that an accurate forecasting system can be developed for the short-term (up to 15 minutes) forecasting of wind and load conditions [23]- [27]. An integration of wind and load forecasting in the EMPRS will allow to implementing the load curtailment in advance, and thus avoid system blackouts as demonstrated below.…”

“…From (27), during high wind conditions, the excess power (P EX ) is consumed by the battery storage system as follows:…”

“…The energy balance equation can be obtained by integrating (27): (19) where, E W_out is the total energy of wind energy conversion system, , E L is the total energy consumed by the load, E B is battery from the battery.…”