Artificial neural network model for HEMTs constructed from large-signal time-domain measurements

A methodology to construct behavioural models for microwave devices from time-domain large-signal measurements has been modified by using artificial neural networks (ANNs) for the multivariate fitting functions instead of polynomials. The behavioural models for the class of devices (microwave transistors) considered can be defined by expressing the terminal currents as functions of the state variables, the embedded voltages. In this work, we show that ANNs are valuable candidates to represent these relationships. They outperform models based on multivariate polynomials, because they can better model the typical physical characteristics of the devices considered. Experimental results are quantitatively confirmed by using comparison metrics.

[1]  Jan Verspecht,et al.  System Level Simulation Benefits from Frequency Domain Behavioral Models of Mixers and Amplifiers , 1999, 1999 29th European Microwave Conference.

[2]  M.C.E. Yagoub,et al.  A robust algorithm for automatic development of neural network models for microwave applications , 2001, 2001 IEEE MTT-S International Microwave Sympsoium Digest (Cat. No.01CH37157).

[3]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[4]  M. Fernandez-Barciela,et al.  Direct extraction of nonlinear FET Q-V functions from time domain large signal measurements , 2000 .

[5]  Qi-Jun Zhang,et al.  Neural Networks for RF and Microwave Design , 2000 .

[6]  A. Barel,et al.  Accurate on wafer measurement of phase and amplitude of the spectral components of incident and scattered voltage waves at the signal ports of a nonlinear microwave device , 1995, Proceedings of 1995 IEEE MTT-S International Microwave Symposium.

[7]  Dominique Schreurs,et al.  Large-signal modelling and measuring go hand-in-hand: Accurate alternatives to indirect S-parameter methods (invited paper) , 2000 .

[8]  G. Kompa,et al.  A new on-wafer large-signal waveform measurement system with 40 GHz harmonic bandwidth , 1992, 1992 IEEE Microwave Symposium Digest MTT-S.

[9]  S. Vandenberghe,et al.  Automatically Controlled Coverage of the Voltage Plane of Quasi-Unilateral Devices , 2001, 57th ARFTG Conference Digest.

[10]  Dominique Schreurs.  Overview of large-signal measurements based equivalent circuit and behavioural modelling techniques with regard to non-linear circuit design enhancement , 2001 .

[11]  Vijay Devabhaktuni,et al.  A robust algorithm for automatic development of neural network models for microwave applications , 2001, IMS 2001.

[12]  Dominique Schreurs,et al.  The construction and evaluation of behavioral models for microwave devices based on time-domain large-signal measurements , 2000, International Electron Devices Meeting 2000. Technical Digest. IEDM (Cat. No.00CH37138).

[13]  K.A. Remley,et al.  Repeat measurements and metrics for nonlinear model development , 2002, 2002 IEEE MTT-S International Microwave Symposium Digest (Cat. No.02CH37278).

[14]  P. J. Tasker,et al.  A Vector Corrected High Power On-Wafer Measurement System with a Frequency Range for the Higher Harmomcs up to 40 GHz , 1994, 1994 24th European Microwave Conference.

[15]  H. Kantz,et al.  Nonlinear time series analysis , 1997 .