Munitions classification using an acoustic resonance spectroscopic technique

A nondestructive evaluation technique for classifying artillery munitions is presented. This technique, based on acoustic resonance measurements, has been successfully demonstrated on a wide variety of high explosive and chemical munitions. The technique consists of building templates of spectral features from sets of known munitions. Spectral features of unknown munitions are compared with a library of templates, and the degree of match between the features and the templates is used to classify the munition. The paper describes the technique, including the feature extraction, clustering and classification algorithms.<<ETX>>