DocumentCode :
3368825
Title :
Feasibility of statistical classifiers for monitoring rollers
Author :
Wittenberg, Sören ; Wolff, Matthias ; Hoffmann, Rüdiger
Author_Institution :
Lab. of Acoust. & Speech Commun., Tech. Univ. Dresden, Dresden
fYear :
2008
fDate :
14-17 Sept. 2008
Firstpage :
463
Lastpage :
466
Abstract :
In this paper we present our investigations on statistical classification of acoustic signals which is one special assignment in condition monitoring. We compare three pattern recognition methods and three selected feature extraction algorithms with regard to their capability to distinguish between structure-borne sound signatures emitted by intact and worn-out rollers in a drawframe. Our goal is to provide a tool that predicts a forthcoming malfunction of the machine. For this purpose we trained and tested GMM, HMM and SVM based classifiers with spectral, LSF and LCQ features computed from recordings of the operating noise of rollers with varying degrees of abrasion.
Keywords :
acoustic signal processing; cepstral analysis; condition monitoring; feature extraction; hidden Markov models; mechanical engineering computing; pattern classification; rollers (machinery); signal classification; support vector machines; GMM based classifiers; HMM based classifiers; LCQ features; LSF features; SVM based classifiers; acoustic signals; condition monitoring; feature extraction algorithm; hidden Markov model; line cepstral quefrencies; line spectral frequencies; machine malfunction prediction; pattern recognition; roller monitoring; statistical classification; statistical classifiers; structure-borne sound signatures; support vector machines; worn-out rollers; Acoustic noise; Acoustic sensors; Cepstral analysis; Condition monitoring; Feature extraction; Hidden Markov models; Support vector machine classification; Support vector machines; Testing; Working environment noise; Condition monitoring; Hidden Markov model; Line cepstral quefrencies; Line spectral frequencies; Support vector machines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signals and Electronic Systems, 2008. ICSES '08. International Conference on
Conference_Location :
Krakow
Print_ISBN :
978-83-88309-47-2
Electronic_ISBN :
978-83-88309-52-6
Type :
conf
DOI :
10.1109/ICSES.2008.4673468
Filename :
4673468
Link To Document :
بازگشت