APERTURE ANTENNA SHAPE PREDICTION BY FEEDFORWARD NEURAL NETWORKS

sThe emergence of adaptive ''smart'' materials has led to the design o f active aperture antennas, Inherent in these antennas is the ability to change their shape in real time to meet various performance charact eristics. When examining the usefulness of these antennas, one of the primary concerns is the antenna shape needed for a particular radiatio n pattern, Aperture antenna shape prediction is also a concern in the industrial production of semi-paraboloidal antennas, The work in this study employs an artificial neural network to model the aperture anten na shape in real time, To test the accuracy of the network, the ''thre efold holdout technique'' was employed, In this technique, sets of exa mples are ''held out'' of the training process and used to obtain the ''true error'' of the network. The network accurately predicted the ap erture shape exactly, to within three significant digits, 96% of the t ime.