A Support Vector machine-Based method for parameter estimation of an electric arc furnace model

In the iron and steel industry, electric arc furnaces (EAFs) are used in melting refining process of metals. They known to demand large amounts reactive power cause significant quality (PQ) problems due their highly non-linear time varying voltage-current characteristic. Several EAF models have been proposed with purpose predict voltage current waveforms, assess performance different compensating devices such as static var compensator, synchronous active filters, –still under study– energy storage systems, also for planning installation facilities considering existing real data from similar facilities. An important aspect these is related estimation parameters. This paper presents a new method estimate parameters an model. The utilizes multiple-input multiple-output regressor based on support vector machine, that maps characteristics values model multidimensional (M-SVR) designed training phase, using several simulations These carried out adjusting within search space, input Then, validation waveform, estimated obtained each M-SVR. validated by comparison between waveforms actual plant. Results show relative error fundamental component voltage, simulated 2.1% 6.3% respectively.