Application of Two-Dimensional AWE Algorithm in Training Multi-Dimensional Neural Network Model
Keywords:
Application of Two-Dimensional AWE Algorithm in Training Multi-Dimensional Neural Network ModelAbstract
Artificial neural network (ANN) plays very important role in microwave engineering. Training a neural network model is the key of neural network technique. The conventional methods for training, such as method of moment (MoM), are time-consuming when the training parameters are a bit more. In order to aid the training process by reducing the amount of costly and time-consuming sampling cycles, a lot of algorithms have been developed, such as asymptotic waveform evaluation (AWE). In this paper, MoM in conjunction with the two-dimensional AWE is applied to accelerate the process of training the neural network model based on the input impedance response on frequency and that on other parameters of a microstrip antenna. In AWE method, the derivatives of Green’s function are required. A closed form of microstrip Green’s function is used for this requirement. Then, the derivative matrices respect to both frequency and permittivity can be obtained from the original matrix. With these matrices in hand, coefficients of the two-dimensional Padé polynomial can be obtained. So the sampling data for training neural network model can be obtained and the process of training neural net model can be completed quickly and accurately. Numerical results demonstrate the efficiency of this technique.
Downloads
References
V. Devabhaktuni, M. C. E.Yagoub, Y. Fang,
J. Xu and Q. J. Zhang, “Neural networks for
microwave modeling: model development
issues and nonlinear modeling technique,”
International Journal of RF and Microwave
CAE, (invited, to be published).
J. W. Bandler, M. A. Ismail, J. E. Rayas-
Sanchez and Q.J.Zhang, “Neuromodeling of
microwave circuits exploiting space
mapping technology,” IEEE Trans.
Microwave Theory Tech., vol. 47, pp.
-2427, December 1999.
E. K. Miller, “Model-based parameter
estimation in electromagnetic Pt.1,” IEEE
Antennas and Propagation Magazine, vol.
, no. 1, pp. 40-52, 1998.
E. K. Miller, “Model-based parameter
estimation in electromagnetic Pt. 2,” IEEE
Antennas and Propagation Magazine, vol.
, no.1, pp. 51-65, 1998.
E. K. Miller, “Model-based parameter
estimation in electromagnetic Pt. 3,” IEEE
Antennas and Propagation Magazine, vol.
, no. 3, pp. 49-66, 1998.
M. Li, Q. J. Zhang and M.S.Nakhla, “Finite
difference solution of EM fields by
asymptotic waveform techniques,” IEE
Proceedings on Microwaves, Antennas and
Propagation, vol. 143, pp. 512-520, 1996
D. Jiao and J. M. Jin, “Asymptotic
Waveform Evaluation for Scattering by a
Dispersive Dielectric Object,” Microwave
Opt. Tech Lett., vol. 24, no. 4, pp. 232-234,
Feb. 2000
C. M. Tong and W. Hong, “Fast Calculation
of Wide Angle Mono-static RCS of
Dielectric Cylinders Based on Asymptotic
Wave Evaluation Technique,” Chinese
Journal of Radio Science, vol. 16, no. 1, pp.
-75, 2001
Y. Xiong, D. G. Fang and F. Ling,
“Two-Dimensional AWE Technique in Fast
Calculation,” ICMMT’2002, pp. 393-396
Ahmad Hoorfar, “Simple Closed-Form
Expressions for Microstrip Green’s
Functions in a Magneto-dielectric
Substrate,” Mircrowave Opt. Tech. Letters,
vol. 8, no.1, pp. 33-36, Jan. 1995
ACES JOURNAL, VOL. 18, NO. 2, JULY 2003, SI: NEURAL NETWORK APPLICATIONS IN ELECTROMAGNETICS
Q. J. Zhang and K.C.Cupta, Neural
Networks for RF and Microwave Design,
Artech House, 2000.
Q. J. Zhang and his research team, software
“NeuralModeler”, Version 1.2.2 for
windows NT 4.0
