Predicting foaming slag quality in electric arc furnace using power quality indices and fuzzy method

Abstract

In this paper, a new method based on adaptive neuro fuzzy inference system (ANFIS) and fuzzy logic is presented to determine the slag quality in electric arc furnace using power quality indices. To train ANFIS, all electrical power quality parameters are measured for 13 meltings using a power quality analyzer. Twelve different sets of power quality parameters are examined to predict the slag quality. Finally, one parameter set consisting of total current harmonic distortion, seventh current harmonic, and three phase current unbalance is selected, which shows the best prediction accuracy. Although the trained ANFIS can accurately predict the slag quality, it is not a robust predictor. If the power quality analyzer model or furnace capacity is changed, then the predictor accuracy will be decreased. To overcome this problem, the fuzzy method is used to predict the slag quality using selected power quality parameters. The predictor reports the slag quality every 1 min in experimental test. The designed fuzzy slag quality predictor can also be used in an automatic slag control process. © 2011 IEEE.