The chapter covers general issues related to power quality in Electric Arc Furnaces. The use of electric arc furnaces (EAF) for steelmaking has grown dramatically in the last decade. Of the steel made today 36% is produced by the electric arc furnace route and this share will increase to 50 by 2030. The electric arc furnaces are used for melting and refining metals, mainly iron in the steel pro...

In this paper we compare different evolutionary algorithm approaches and parameters used to optimize the output of neural network committee trained on regression problems. This is especially useful for large and complex datasets. We used the methodology presented in this paper to optimize the output of the committee to predict the temperature in the electric arc furnace in one of the steelworks.

The article describes measurement of currents and voltages in submerged arc-resistance electric furnace which were done to identify arc parameters. Waveforms of registered currents and voltages have been shown. Characteristics of arc developed in original C# software have been presented. Streszczenie. Artykuł opisuje pomiary prądów i napięć w obwodzie pieca elektrycznego łukowo-oporowego z łuki...

This paper presents guidelines for the accurate evaluation of harmonics and flicker generated by ac electric arc furnaces, and its propagation through transmission and distribution systems. It is presented a typical case where a HV system supplies a high capacity arc furnace. The electrical network is simulated using the ATP version of the EMTP where a non-linear time-varying three-phase arc mo...

Powderous crystalline materials of the composition Fe3−xMnxC have been prepared by first synthesizing Fe3C via mechanical alloying in a planetary mill followed by the addition of elemental manganese and arc-plasma melting or via the classic ceramic route in an electric furnace. The milling time for the synthesis of Fe3C was significantly reduced through adjusting the parameters of the planetary...

This study investigated electric arc furnace dust (EAFD) reuse as a raw material in concrete mixes. A comprehensive experimental program consisting of two phases of testing was carried out. The first phase included the replacement of ordinary Portland (Type I) cement by unsieved dust with the percentages of 0, 2.5, 5, 7.5 and 10%. The second phase included the replacement of quartz (filler) by ...

This paper presents a neural network tree regression system with dynamic optimization of input variable transformations and post-training optimization. The decision tree consists of MLP neural networks, which optimize the split points and at the leaf level predict final outputs. The system is designed for regression problems of big and complex datasets. It was applied to the problem of steel te...