Acoustic Monitoring of Plasma Arcs in Direct Current Electric Arc Furnaces

Abstract

In this article, the extraction of features from acoustic signals generated by a 60-kW direct current electric arc furnace and the use of these features to infer the arc length of the plasma jets in the furnace were considered. A sensor capable of such measurements would be more robust to the unobservable fluctuations of the arc length and would, in principle, allow better control of smelting operations. The collected data comprised sets of five separate 10-second recordings of the acoustic signal, furnace current, and voltage, each at nominal arc lengths of 5, 15, and 25 mm. In the approach, time-frequency features initially were obtained through filter bank analysis of the signals. Reduction of the dimensionality of these filter bank features was then performed using a nonlinear subspace method called kernel Fisher discriminant analysis. Finally, kernel discriminant features were used to infer the arc length via a nearest neighbor classification model that associated three classes of arc lengths (5, 15, and 25 mm) with their corresponding features. The results of the small number of experiments suggest that a significant statistical relationship exists between the length of a plasma arc and its acoustic signal despite potentially large variations in arc phenomena inside the furnace.