DESIGN OF GRATINGS AND FREQUENCY-SELECTIVE SURFACES USING FUZZY ARTMAP NEURAL NETWORKS

This paper presents a study of the Fuzzy ARTMAP neural network in desi gning cascaded gratings and frequency selective surfaces (FSS) in gene ral. Conventionally, trial and error procedures are used until an FSS matches the design criteria. One way of avoiding this laborious proces s is to use neural networks (NNs). A neural network can be trained to predict the dimensions of the elements comprising the FSS structure, t heir distance of separation, and their shape required to produce the d esired frequency response. In the past, the multi-layer perception arc hitecture trained with the back-prop learning algorithm (back-prop net work) was used to solve this problem. Unfortunately, the back-prop net work experiences, at times, convergence problems and these problems be come amplified as the size of the training set increases. In this work , the Fuzzy ARTMAP neural network is used to address the FSS design pr oblem. 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 gra tings corresponding to various angles of wave incidence, layer separat ion, width strips, and interstrip separation are presented and discuss ed.