Neural network modeling of magnetic hysteresis

This paper presents the application of artificial neural networks to implement a magnetic hysteresis model. Accurate modelling of hysteresis is essential for both the design and the performance evaluation of electromagnetic devices. It is shown that artificial neural networks (ANNs) provide natural settings whereby the Preisach model can be readily implemented. The comparison with the experiments shows that the proposed approach is able to satisfactorily reproduce many features of observed hysteresis phenomena and in turn can be used for many applications of interest.