Electric arc furnaces (EAFs) contribute to almost one third of the global steel production.\nArc furnaces use a large amount of electrical energy to process scrap or reduced iron and are relevant\nto study because small improvements in their efficiency account for significant energy savings.\nOptimal controllers need to be designed and proposed to enhance both process performance and\nenergy consumption. Due to the random and chaotic nature of the electric arcs, neural networks\nand other soft computing techniques have been used for modeling EAFs. This study proposes a\nmethodology for modeling EAFs that considers the time varying arc length as a relevant input\nparameter to the arc furnace model. Based on actual voltages and current measurements taken\nfrom an arc furnace, it was possible to estimate an arc length suitable for modeling the arc furnace\nusing neural networks. The obtained results show that the model reproduces not only the stable arc\nconditions but also the unstable arc conditions, which are difficult to identify in a real heat process.\nThe presented model can be applied for the development and testing of control systems to improve\nfurnace energy efficiency and productivity.
Loading....