Author:
Kuczmann Miklós,Iványi Amália
Abstract
On the basis of the Kolmogorov‐Arnold theory, the feedforward type artificial neural networks (NNs) are able to approximate any kind of nonlinear, continuous functions represented by its discrete set of measurements. A NN‐based scalar hysteresis model has been constructed preliminarily on the function approximation ability of NNs. An if‐then type knowledge‐base represents the properties of the hysteresis characteristics. Vectorial generalization to describe isotropic and anisotropic magnetic materials in two and three dimensions with an original identification method has been introduced in this paper.
Subject
Applied Mathematics,Electrical and Electronic Engineering,Computational Theory and Mathematics,Computer Science Applications
Reference12 articles.
1. Adly, A.A. and Abd‐El‐Hazif, S.K. (1998), “Using neural networks in the identification of Preisach‐type hysteresis models”, IEEE Trans. Magn., Vol. 34, pp. 629–35.
2. Adly, A.A., Abd‐El‐Hafiz, S.K. and Mayergoyz, I.D. (2000), “Identification of vector Preisach models from arbitrary measured data using neural networks”, Journal of Applied Physics, Vol. 87 No. 9, pp. 6821–3.
3. Christodoulou, C. and Georgiopoulos, M. (2001), Applications of Neural Networks in Electromagnetics, Artech House, Norwood.
4. Füzi, J. (2000), “Anisotropic vector Preisach particle”, Journal of Magnetism and Magnetic Materials, Vol. 215‐16, pp. 597–600.
5. Iványi, A. (1997), Hysteresis Models in Electromagnetic Computation, Akadémia Kiadó, Budapest.
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献