Nonlinear modelling of a switched reluctance drive based on neural networks

Switched reluctance motors (SRMs) are almost always operated within the saturation region for a very large operation region. This yields very strong nonlinearities, which makes it very difficult to derive a comprehensive mathematical model for the behaviour of the machine. Artificial neural networks (ANNs) have been used to overcome such problems. This paper presents ANNs as a new tool to handle one of the key problems in an SRM based drive system. A back propagation algorithm is used to train the network. To explore the validity of the proposed technique, the results of ANNs were compared with the experimentally measured results. The comparison between these results have validated the applicability of the proposed method.