Energy optimization of submerged arc furnace

To reduce the production cost, it is necessary to optimize the energy cost. In this paper, we focus on power as energy can be directly determined by power. In general, it is compulsory to have an objective function before using an optimization algorithm to find the optimal result. However, modeling is difficult using mathematical functions according to the mechanisms of the actual furnace plant system because of its complexity and many disturbances. The neural networks have been chosen because of its easy to use in modeling nonlinear functions such as the furnace plant. Then the particle swarm optimization is used to optimize neural network model of the three-phase submerged arc furnace. Finally, the optimization result is validated using the real samples as the objective function is not the real furnace plant.