ANN Synthesis Models Trained with Modified GA-LM Algorithm for ACPWs with Conductor Backing and Substrate Overlaying

Accurate synthesis models based on artificial neural networks (ANNs) are proposed to directly obtain the physical dimensions of an asymmetric coplanar waveguide with conductor backing and substrate overlaying (ACPWCBSO). First, the ACPWCBSO is analyzed with the conformal mapping technique (CMT) to obtain the training data. Then, a modified geneticalgorithm -Levenberg-Marquardt (GA-LM) algorithm is adopted to train ANNs. In the algorithm, the maximal relative error (MRE) is used as the fitness function of the chromosomes to guarantee that the MRE is small, while the mean square error is used as the error function in LM training to ensure that the average relative error is small. The MRE of ANNs trained with the modified GA-LM algorithm is less than 8.1%, which is smaller than those trained with the existing GA-LM algorithm and the LM algorithm (greater than 15%). Lastly, the ANN synthesis models are validated by the CMT analysis, electromagnetic simulation, and measurements.

[1]  Jose I. Alonso,et al.  ULTRA-BROADBAND DIRECTIONAL COUPLERS USING MICROSTRIP WITH DIELECTRIC OVERLAY IN MILLIMETER-WAVE BAND , 2011 .

[2]  Hao Ling,et al.  Application of Artificial Neural Networks to Broadband Antenna Design Based on a Parametric Frequency Model , 2007, IEEE Transactions on Antennas and Propagation.

[3]  Kerim Guney,et al.  New and accurate synthesis formulas for asymmetric coplanar waveguides , 2011 .

[4]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[5]  Ceyhun Karpuz,et al.  Effect of upper shielding and conductor backing on quasistatic parameters of asymmetric coplanar waveguides , 1999 .

[6]  D. Thebault,et al.  Theoretical and Experimental Investigation of Asymmetric Coplanar Waveguides (Short Papers) , 1984 .

[7]  Mustafa Turkmen,et al.  New and accurate synthesis formulas for asymmetric conductor‐backed coplanar waveguides , 2011 .

[8]  Shaojun Fang,et al.  Analysis of asymmetric coplanar waveguide with conductor backing , 1999 .

[9]  Ceyhun Karpuz,et al.  Fast and simple analytical expressions for quasistatic parameters of asymmetric coplanar lines , 1995 .

[10]  Elif Derya Übeyli,et al.  Multilayer perceptron neural networks to compute quasistatic parameters of asymmetric coplanar waveguides , 2004, Neurocomputing.

[11]  Mustafa Turkmen,et al.  Neural Models for Coplanar Strip Line Synthesis , 2007 .

[12]  Jigui Sun,et al.  A Novel GA-LM Based Hybrid Algorithm , 2007, Third International Conference on Natural Computation (ICNC 2007).

[13]  Bing-Hao Zeng,et al.  CPW-Fed Circular Fractal Slot Antenna Design for Dual-Band Applications , 2008, IEEE Transactions on Antennas and Propagation.

[14]  Vassilis P. Plagianakos,et al.  Learning in multilayer perceptrons using global optimization strategies , 2001 .

[15]  Ceyhun Karpuz,et al.  Quasistatic TEM characteristics of overlayed supported asymmetric coplanar waveguides , 1996 .

[16]  R. Simons.  Coplanar waveguide circuits, components, and systems , 2001 .

[17]  Sungjoon Lim,et al.  A Compact Zeroth‐Order Resonant Antenna on Vialess CPW Single Layer , 2010 .

[18]  Zhongbao Wang,et al.  A Broadband 3 dB Coplanar Waveguides Directional Coupler with Conductor-backed Asymmetric Coplanar Waveguides Compensation , 2012 .

[19]  Zhongbao Wang,et al.  An Inmarsat BGAN Terminal Patch Antenna Array With Unequal Input Impedance Elements and Conductor-Backed ACPW Series-Feed Network , 2012, IEEE Transactions on Antennas and Propagation.

[20]  Qi-Jun Zhang,et al.  Smart Modeling of Microwave Devices , 2010, IEEE Microwave Magazine.

[21]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[22]  Ricardo B. C. Prudêncio,et al.  Neural Network Hybrid Learning: Genetic Algorithms & Levenberg-Marquardt , 2003 .

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

[24]  Jiunn-Jye Chang,et al.  Characteristics of asymmetrical conductor-backed coplanar waveguides , 1992 .

[25]  D. Thebault,et al.  Theoretical and Experimental Investigation of Asymmetric Coplanar Waveguide , 1984 .

[26]  Singaravelu Raghavan,et al.  Neural Model for Circular-Shaped Microshield and Conductor-Backed Coplanar Waveguide , 2009 .

[27]  Mustafa Turkmen,et al.  Synthesis formulas for conductor-backed coplanar waveguide , 2008 .

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