Artificial neural networks for RF and microwave design - from theory to practice

Neural-network computational modules have recently gained recognition as an unconventional and useful tool for RF and microwave modeling and design. Neural networks can be trained to learn the behavior of passive/active components/circuits. A trained neural network can be used for high-level design, providing fast and accurate answers to the task it has learned. Neural networks are attractive alternatives to conventional methods such as numerical modeling methods, which could be computationally expensive, or analytical methods which could be difficult to obtain for new devices, or empirical modeling solutions whose range and accuracy may be limited. This tutorial describes fundamental concepts in this emerging area aimed at teaching RF/microwave engineers what neural networks are, why they are useful, when they can be used, and how to use them. Neural-network structures and their training methods are described from the RF/microwave designer's perspective. Electromagnetics-based training for passive component models and physics-based training for active device models are illustrated. Circuit design and yield optimization using passive/active neural models are also presented. A multimedia slide presentation along with narrative audio clips is included in the electronic version of this paper. A hyperlink to the NeuroModeler demonstration software is provided to allow readers practice neural-network-based design concepts.

[1]  Fang Wang,et al.  Knowledge based neural models for microwave design , 1997, IMS 1997.

[2]  James T. Kwok,et al.  Constructive algorithms for structure learning in feedforward neural networks for regression problems , 1997, IEEE Trans. Neural Networks.

[3]  Fang Wang,et al.  A new macromodeling approach for nonlinear microwave circuits based on recurrent neural networks , 2000, IMS 2000.

[4]  J.W. Bandler,et al.  Neuromodeling of microwave circuits exploiting space mapping technology , 1999, 1999 IEEE MTT-S International Microwave Symposium Digest (Cat. No.99CH36282).

[5]  M.C.E. Yagoub,et al.  Neural based dynamic modeling of nonlinear microwave circuits , 2002, 2002 IEEE MTT-S International Microwave Symposium Digest (Cat. No.02CH37278).

[6]  Jacques de Villiers,et al.  Backpropagation neural nets with one and two hidden layers , 1993, IEEE Trans. Neural Networks.

[7]  Fang Wang,et al.  A hierarchical neural network approach to the development of library of neural models for microwave design , 1998, 1998 IEEE MTT-S International Microwave Symposium Digest (Cat. No.98CH36192).

[8]  Fang Wang,et al.  Robust training of microwave neural models , 1999, 1999 IEEE MTT-S International Microwave Symposium Digest (Cat. No.99CH36282).

[9]  Fang Wang,et al.  Robust training of microwave neural models , 2002 .

[10]  M. Vai,et al.  Microwave circuit analysis and design by a massively distributed computing network , 1995 .

[11]  Vijay Devabhaktuni,et al.  Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks and space mapping , 2002, IMS 2002.

[12]  Robert J. Trew,et al.  A large-signal, analytic model for the GaAs MESFET , 1988 .

[13]  Emile Fiesler,et al.  High-order and multilayer perceptron initialization , 1997, IEEE Trans. Neural Networks.

[14]  Qi-Jun Zhang,et al.  Neural Networks for Microwave Modeling: Model Development Issues and Nonlinear Modeling Techniques , 2001 .

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

[16]  Fang Wang,et al.  Knowledge based neural models for microwave design , 1997, 1997 IEEE MTT-S International Microwave Symposium Digest.

[17]  M.C.E. Yagoub,et al.  Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks and space mapping , 2002, 2002 IEEE MTT-S International Microwave Symposium Digest (Cat. No.02CH37278).

[18]  K. C. Gupta,et al.  EM-ANN models for microstrip vias and interconnects in dataset circuits , 1996 .

[19]  Michel Nakhla,et al.  The application of neural networks to EM-based simulation and optimization of interconnects in high-speed VLSI circuits , 1997 .

[20]  K. C. Gupta,et al.  Emerging trends in millimeter-wave CAD , 1998 .

[21]  Songxin Qi,et al.  Time-domain analysis of lossy coupled transmission lines , 1992 .

[22]  Fang Wang,et al.  A hierarchical neural network approach to the development of library of neural models for microwave design , 1998, IMS 1998.

[23]  Jeffrey A. Jargon,et al.  Applications of artificial neural networks to RF and microwave measurements , 2002 .

[24]  John W. Bandler,et al.  Neuromodeling of microwave circuits exploiting space mapping technology , 1999, IMS 1999.

[25]  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).

[26]  K. C. Gupta,et al.  Design and optimization of CPW circuits using EM-ANN models for CPW components , 1997 .

[27]  Qi-Jun Zhang,et al.  Neural Network Structures and Training Algorithms for RF and Microwave Applications , 1999 .

[28]  Michel Nakhla,et al.  A neural network modeling approach to circuit optimization and statistical design , 1995 .

[29]  Kuldip Gupta,et al.  Electromagnetic‐artificial neural network model for synthesis of physical dimensions for multilayer asymmetric coupled transmission structures (invited article) , 1999 .

[30]  S. Prasad,et al.  Reverse modeling of microwave circuits with bidirectional neural network models , 1998 .

[31]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[32]  G. L. Creech,et al.  Artificial neural networks for fast and accurate EM-CAD of microwave circuits , 1997 .

[33]  John W. Bandler,et al.  Circuit optimization: the state of the art , 1988 .