Acoustic emmision signal classiefiation using fuzzy C-means clustering - Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference o

Fuzzy C-means (FCM) clustering is used to classify the Acoustic Emission (AE) signal to merent sources of signals. FCM has the ability to discover the duster among the data, wen wben the boundaries between the subgroup E. oft lap ping. FCM based tectnique . has an advantage Ov& umventional statistical technique like maximum likelihwd estimate, nearest neighbor classifier e t ~ , because they are distribution fiee (i.e.) no knowledge is required about the distribution of data AE test is carried out using pulse, pencil and Spark signal source on the surface of solid steel block. Four p m e t e r s Event duration (Ed, Peak amplitude (P,) Rise time (RJ and Ring down count oh) are measured using AET 5000 s!istem. These-data's are used to train and validate the FCM . -