A new neural networks-based model of hysteresis

A new approach to constructing hysteretic operator is proposed in this paper. Based on the hysteretic operator, the input space of neural networks is expanded from 1-dimension to 2-dimension and the multi-value mapping of hysteresis is transformed into one-to-one mapping. Based on the expanded input space, a neural network is employed to approximate hysteresis. The result of an experimental example suggests the proposed approach is effective.