科研之友
微信
新浪微博
Facebook
分享链接
摘要
A new approach to constructing hysteretic operator (HO) is proposed in this paper. Based on the HO, the input space of neural networks is expanded from one-dimension to two-dimension and the multi-value mapping of hysteresis is transformed into a continuous mapping comprised of one-to-one mapping and multiple-to-one mapping. Based on the expanded input space, a neural network is employed to approximate hysteresis. The results of experimental examples suggest the proposed approach is effective.
- 出版日期2014-8
- 单位浙江科技学院
