Neural-Preisach-type models and their application to the identification of magnetic hysteresis from noisy data |
| |
| Affiliation: | 1. Department of Electrical Engineering, University of Napoli “Federico II”, Via Clandio 42, 80142 Napoli, Italy;2. Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA;3. Department of Electric Power and Machines, University of Cairo, Giza, Egypt |
| |
| Abstract: | A novel class of Preisach-type hysteresis transducers is introduced and their properties are investigated. These transducers can be numerically implemented by using feed-forward neural networks and their identification can be performed by learning algorithms. Numerical examples that provide evidence of the capability of this approach of filtering noise embedded in the data used for identification, are presented. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
