论文信息 - Modeling of microwave devices with artificial neural networks using segmentation and finite elements

Modeling of microwave devices with artificial neural networks using segmentation and finite elements

The CAD of microwave devices involves extensively computing their electromagnetic response. Using segmentation and finite elements, a neural model for an arbitrary device is developed efficiently, even if the number of design parameters is high. This is made clear with an example of a transition between coaxial and rectangular waveguides.

Juan M. Cid | Juan Zapata | Jesús García

[1] Juan Zapata,et al. CAD of rectangular-waveguide H-plane circuits by segmentation, finite elements and artificial neural networks , 2001 .

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

[3] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[4] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[5] J. Zapata,et al. Analysis of passive microwave circuits by using a hybrid 2-D and 3-D finite-element mode-matching method , 1999, IEEE Transactions on Microwave Theory and Techniques.