Wang_Zhao.pdf (1.54 MB)
Download file

Implementation of Preisach-Krasnoselskii Hysteresis Model with the Use of Artificial Neural Networks

Download (1.54 MB)
thesis
posted on 23.05.2021, 18:09 by Zhao Wang
Accurate modeling of hysteresis is essential for both the design and performance evaluation of electromagnetic devices. This project proposes the use of feedforward meural networks to implement an accurate magnetic hysteresis model based on the mathematical difinition provided by the Preisach-Krasnoselskii (P-K) model. Feedforward neural networks are a linear association networks that relate the ouput patterns to input patterns. By introducing the multi-layer feedforward neural networks make the hysteresis modeling accurate without estimation of double integrals. Simulation results provide the detailed illustrations. The comparisons with the experiments show that the proposed approach is able to satisfactorily reproduce many features of obsereved hysteresis phenomena an in turn can be used for many applications of interest.

History

Language

eng

Degree

Master of Engineering

Program

Electrical and Computer Engineering

Granting Institution

Ryerson University

LAC Thesis Type

Thesis

Thesis Advisor

Alireza Sadeghian

Usage metrics

Keywords

Exports