A CAD neural model for shielded and conductor backed CPW

In this paper a CAD approach based on ANNs was successfully introduced to determine the parasitic effects occurred in (effective dielectric and characteristics impedance) Coplanar Wave guide (CPW) with upper shielding and conductor backing. ANNs were trained with three learning algorithms to obtain better performance and faster convergence with simpler structure. The best results were obtained with Levenberg-marquardt algorithms. The quasi-static parameters of two different CPW configurations can be calculated using the neural model proposed in this work very accurately.