Novel Neural Network application to nonlinear electronic devices: building a Volterra series model

In this work we want to present a novel application of Neural Networks as a Black-Box model, which allows representing the nonlinear behavior of a vast number of RF electronic devices with the Volterra series approximation. We propose a simple approach for the generation of the Volterra model for a device, even in the case of a nonlinearity that depends on more than one variable, which allows obtaining a general model, independent of the physical circuit. In particular, we will show the results obtained for the analysis of a transistor and the generation of its analytical Volterra series model, built using a standard Neural Network model and its parameters.

[1]  Andreas Bauer,et al.  Circuit analysis and optimization with automatically derived Volterra kernels , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[2]  D. Weiner,et al.  A Scattering Variable Approach to the Volterra Analysis of Nonlinear Systems , 1976 .

[3]  Stephen A. Maas,et al.  Nonlinear microwave circuits , 1988 .

[4]  Jose C. Pedro,et al.  Modeling MESFETs and HEMTs intermodulation distortion behavior using a generalized radial basis function network , 1999 .

[5]  Hiroshi Kashiwagi,et al.  Identification of Volterra kernels of nonlinear systems by separating overlapped kernel slices , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[6]  Vasilis Z. Marmarelis,et al.  Volterra models and three-layer perceptrons , 1997, IEEE Trans. Neural Networks.

[7]  Leon O. Chua,et al.  Measuring Volterra kernels , 1983 .

[8]  Jonathan J. Kaufman,et al.  Volterra characterization of neural networks , 1991, [1991] Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers.

[9]  Jose C. Pedro,et al.  Theoretical basis for extraction of mildly nonlinear behavioral models , 2003 .

[10]  Qi-Jun Zhang,et al.  Artificial neural networks for RF and microwave design - from theory to practice , 2003 .

[11]  W. Rugh.  Nonlinear System Theory: The Volterra / Wiener Approach , 1981 .

[12]  Gary G. R. Green,et al.  Calculation of the Volterra kernels of non-linear dynamic systems using an artificial neural network , 1994, Biological Cybernetics.

[13]  M. Schetzen.  The Volterra and Wiener Theories of Nonlinear Systems , 1980 .

[14]  Marco Pirola,et al.  Towards a Volterra series representation from a Neural Network model , 2004 .

[15]  W. R. Curtice,et al.  A Nonlinear GaAs FET Model for Use in the Design of Output Circuits for Power Amplifiers , 1985, 1985 IEEE MTT-S International Microwave Symposium Digest.

[16]  J. T. Bialasiewicz,et al.  Neural network modeling of nonlinear systems based on volterra series extension of a linear model , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.

[17]  Magali R. G. Meireles,et al.  A comprehensive review for industrial applicability of artificial neural networks , 2003, IEEE Trans. Ind. Electron..

[18]  Stephen P. Boyd,et al.  Analytical Foundations of Volterra Series , 1984 .