DETECTION OF IMPACT LOCATION AND MAGNITUDE FOR ISOTROPIC PLATES USINGNEURAL NETWORKS

A neural network-based method of determining the location and magnitud e of transverse impact events on isotropic plates is investigated expe rimentally. Time data from four sensors mounted in the corners of an a luminum plate was processed to provide inputs for two backpropagation neural networks. The first neural network was responsible for detectin g impact location. After 1 million iterations of training, this neural network was able to locate impacts with an average RMS error of 1.55 radial centimeters on a 58.5 centimeter by 36.8 centimeter (23 inch by 14.5 inch) fully-clamped plate. The second neural network was respons ible for impact magnitude detection. This neural network was able to d etermine the impact magnitude with an average of 13.8% error.