ANN Synthesis Models for Asymmetric Coplanar Waveguides with Finite Dielectric Thickness

Novel and accurate Computer-aided design (CAD) models based on Artificial neural networks (ANNs) are proposed for the synthesis of Asymmetric coplanar waveguides (ACPWs) with finite dielectric thickness. First, the ACPWs are analyzed by using the Conformal mapping technique (CMT) to obtain the training data sets. Then, six training algorithms are used to train the ANNs for finding proper training algorithm. Highprecision models are obtained by using the Levenberg- Marquardt (LM) training algorithm. The models also can be used for symmetric coplanar waveguides. At last, the models are validated by the comparison with the CMT analysis, HFSS electromagnetic simulation, and experimental results available in the literature. The proposed CAD models are extremely useful to microwave engineers for accurately calculating the physical dimensions of ACPWs with finite dielectric thickness.