Design of gratings and frequency selective surfaces using Fuzzy ARTMAP neural networks

This paper presents a study of the Fuzzy ARTMAP neural network in designing cascaded gratings and frequency selective surfaces (FSS) in general. Conventionally, trial and error procedures are used until an FSS matches the design criteria. One way of avoiding this laborious process is to use neural networks (NNs). A neural network can be trained to predict the dimensions of the elements comprising the FSS structure, their distance of separation, and their shape required to produce the desired frequency response. In the past, the multi-layer perception architecture trained with the back-prop learning algorithm (back-prop network) was used to solve this problem. Unfortunately, the back-prop network experiences, at times, convergence problems and these problems become amplified as the size of the training set increases. In this work, the Fuzzy ARTMAP neural network is used to address the FSS design problem. The Fuzzy ARTMAP neural network converges much faster than the back-prop network, and most importantly its convergence to a solution is guaranteed. Several results (frequency responses) from cascaded gratings corresponding to various angles of wave incidence, layer separation, width strips, and interstrip separation are presented and discussed.