A neural networks model for hysteresis nonlinearity

This paper presents a new approach for modeling hysteresis nonlinearity in piezo-actuators. Under a mild assumption, a mapping, which can be approximated by multi-layer neural networks (MNN), is defined to describe Preisach model. Then, the neural networks (NN) hysteresis model is extended to describe hysteresis function, which relaxes the requirements on hysteresis to be described by Preisach model. An advantage is that the proposed model simplifies the identification procedure for it can be trained by any algorithm designed for NN. Output prediction using the NN model is performed on an exponentially decayed sinusoidal input signal and the results confirm that the model can accurately predict the response of hysteresis nonlinearity in piezo-actuators.

[1]  D.A. Lowther,et al.  A Neural Network Model Of Magnetic Hysteresis For Computational Magnetics , 1997, 1997 IEEE International Magnetics Conference (INTERMAG'97).

[2]  D. A. Lowther,et al.  Modeling magnetic materials using artificial neural networks , 1998 .

[3]  I. Mayergoyz,et al.  Preisach modeling of magnetostrictive hysteresis , 1991 .

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

[5]  Jonq-Jer Tzen,et al.  Modeling of piezoelectric actuator for compensation and controller design , 2003 .

[6]  Ralph C. Smith,et al.  A Domain Wall Model for Hysteresis in Piezoelectric Materials , 1999 .

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

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

[9]  A. Kurdila,et al.  Hysteresis Modeling of SMA Actuators for Control Applications , 1998 .

[10]  I. Mayergoyz,et al.  Generalized Preisach model of hysteresis , 1988 .

[11]  Ye-Hwa Chen,et al.  Piezomechanics using intelligent variable-structure control , 2001, IEEE Trans. Ind. Electron..

[12]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[13]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[14]  Musa Jouaneh,et al.  Generalized preisach model for hysteresis nonlinearity of piezoceramic actuators , 1997 .

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

[16]  John T. Wen,et al.  Preisach modeling of piezoceramic and shape memory alloy hysteresis , 1997 .