论文信息 - Vector hysteresis model based on neural network

Vector hysteresis model based on neural network

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.

Miklós Kuczmann | Amália Iványi

[1] Mayergoyz,et al. Mathematical models of hysteresis. , 1986, Physical review letters.

[2] A. Ivanyi,et al. A new neural-network-based scalar hysteresis model , 2002 .

[3] Michael Georgiopoulos,et al. Applications of Neural Networks in Electromagnetics , 2001 .

[4] Amr A. Adly,et al. Identification of vector Preisach models from arbitrary measured data using neural networks , 2000 .

[5] Amr A. Adly,et al. Using neural networks in the identification of Preisach-type hysteresis models , 1998 .

[7] Maurizio Repetto,et al. Accurate analysis of magnetic devices with anisotropic vector hysteresis , 2000 .

[8] Miklós Kuczmann,et al. Neural network model of magnetic hysteresis , 2002 .

[9] Amr A. Adly,et al. Simulation of field-temperature effects in magnetic media using anisotropic Preisach models , 1998 .

[10] Anisotropic vector Preisach particle , 2000 .

[11] C. Visone,et al. Magnetic hysteresis modeling via feed-forward neural networks , 1998 .