Genetic neural-based modeling of AC resistance of heating coil used for high-frequency inverter-fed induction cooker

The present paper deals with modeling of AC resistance of twisted litz wires used for high-frequency inverter-fed induction cooker. Several traditional approaches are available, most of which have concentrated in deriving the analytical relationships between the AC resistances with the parameters of the wire. However, it is very difficult to get the exact relationship, due to several reasons. An attempt is made in this paper to model the AC resistance using a three-layered feed-forward Neural Network. For this purpose, four inputs (wire type, number of strand, number of spiral turn and operating frequency) and one output as AC resistance have been considered. Since the performance of Neural Network alone might not be optimal; it is optimized using a binary-coded Genetic Algorithm. Performances of the proposed approach were compared with the method of AC resistance computation proposed by Ferreira. Genetic-neural system has given a very close accuracy, and the computational complexity was found to be very low. Thus, it is suitable for online implementations.