Acoustic emission signal classification using fuzzy c-means clustering

Author

Omkar, S.N. ; Suresh, S. ; Raghavendra, T.R. ; Mani, V.

Author_Institution

Aerosp. Eng. Dept., Indian Inst. of Sci., Bangalore, India

Volume

4

fYear

2002

fDate

18-22 Nov. 2002

Firstpage

1827

Abstract

Fuzzy c-means (FCM) clustering is used to classify the acoustic emission (AE) signal to different sources of signals. FCM has the ability to discover the cluster among the data, even when the boundaries between the subgroup are overlapping, FCM based technique has an advantage over conventional statistical technique like maximum likelihood estimate, nearest neighbor classifier etc, because they are distribution free (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 parameters-event duration (E_d), peak amplitude (P_a), rise time (R_t) and ring down count (R_d) are measured using AET 5000 system. These data are used to train and validate the FCM based classification.

Keywords

acoustic emission testing; acoustic signal processing; fuzzy set theory; pattern classification; pattern clustering; AE; AET 5000 system; FCM; acoustic emission signal classification; cluster discovery; event duration; fuzzy c-means clustering; overlapping subgroup boundaries; peak amplitude; pencil signal source; pulse signal source; ring down count; rise time; signal classification; solid steel block; spark signal source; Acoustic emission; Acoustic materials; Acoustic noise; Nearest neighbor searches; Neural networks; Pattern classification; Signal analysis; Signal processing; Sparks; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

Print_ISBN

981-04-7524-1

Type

conf

DOI

10.1109/ICONIP.2002.1198989

Filename

1198989