Service station experts examine the sound patterns of the motorcycles to diagnose the faults. Automatic fault diagnosis is a challenging task and more so is recognition of multiple faults. This study presents a methodology for localisation of multiple faults in motorcycles. The sound signatures of multiple faults are constructed by fusing the individual signatures of faults from engine and exhaust subsystems. Energy distributions in the approximation coefficients of wavelet packets are used as features. Among the classifiers used, artificial neural network is found suitable for detecting the presence of multiple faults. The recognition accuracy is over 78% when trained with individual fault signatures and over 88% when trained with combined fault signatures.
Localisation of multiple faults in motorcycles based on the wavelet packet analysis of the produced sounds
IET Intelligent Transport Systems ; 7 , 3 ; 296-304
2013-09-01
9 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
wavelet packet analysis , artificial neural network , fault diagnosis , fault recognition , fault signature , engine , exhaust subsystem , wavelet transforms , mechanical engineering computing , approximation theory , neural nets , energy distribution , motorcycles , sound patterns , multifault localisation , engines , exhaust systems , automatic fault diagnosis , approximation coefficient , sound signature , motorcycle , automotive engineering
IET | 2013
|Acoustic signal based detection and localisation of faults in motorcycles
Wiley | 2014
|Acoustic signal based detection and localisation of faults in motorcycles
IET | 2014
|Online Contents | 2001
Online Contents | 2010