Internal Model Control Based on GANN for a Temperature Control Electrical Furnace

Industrial electrical furnaces present many challenging control problems due to their non-linear dynamic behavior, uncertain and time varying parameters. We know that the temperature of the furnace is a physical quantity with nonlinearity and long time delay, it is difficult for us to use an accurate mathematic model to express, and in this case, we cannot use a model with fix parameters to control the temperature. According to the characteristic of the temperature, this paper-comes up with a internal model control using GA-NN approach for an electrical furnace is presented. The dynamics model of the neural network of the system is identified by the genetic algorithm. Another neural network is trained to learn the inverse dynamics of the electric furnace so that it can be used as a nonlinear controller. Because of the limitation of BP algorithm, the genetic algorithm is used to find the fitness weights and thresholds of the neural network model, and the simulation results testify that the method proposed for controlling the temperature of electrical furnace has good robustness and effectively compensates the influences of parameter variations.