Affordable Access

Publisher Website

Identification and testing of an efficient hopfield neural network magnetostriction model

Authors
Journal
Journal of Magnetism and Magnetic Materials
0304-8853
Publisher
Elsevier
Publication Date
Volume
263
Issue
3
Identifiers
DOI: 10.1016/s0304-8853(03)00066-0
Keywords
  • Magnetostriction
  • Preisach-Type Model
  • Discrete Hopfield Neural Network
  • Linear Neural Network
Disciplines
  • Computer Science

Abstract

Abstract Magnetostriction models are indispensable to different crucial computational activities such as those dealing with active vibration damping devices and optimum clamping stresses for transformer sheets. This paper presents an efficient magnetostriction Preisach-type model based on the effective field approach. According to this approach, the total applied field may be regarded as a super position of the actual magnetic field and a stress-dependent feedback term. Construction and identification of the model is carried out by providing experimental training data to a modular discrete Hopfield neural network–linear neural network combination. Experimental testing suggests that this model can lead to good qualitative and quantitative simulation results.

There are no comments yet on this publication. Be the first to share your thoughts.