Header menu link for other important links
Bearing Fault Diagnosis using Wavelet Packet Transform, Hybrid PSO and Support Vector Machine
, Sathiyabhama B, , Manivannan K.
Published in Elsevier BV
Volume: 97
Pages: 1772 - 1783
A new intelligent methodology in bearing condition diagnosis analysis has been proposed to predict the status of rolling bearing based on vibration signals by multi class support vector machine (MSVM), a classification algorithm. Wavelet packet transform (WPT) is used for signal processing and standard statistical feature extraction process. Feature reduction is a method used to deselect the irrelevant features acquired from the large dataset. Recent survey shows feature reduction is used widely in the field of machine learning to discover the knowledge with reduced features. Rough set is hybridized with particle swarm optimization (PSO), an population based stochastic optimization technique, to reduce the features. The efficiency of classification algorithm is compared based on their classification accuracy before and after feature reduction. Four states of bearing health conditions such as normal, defective inner race, defective outer race and defective ball conditions are simulated and used in this proposed work. © 2014 Published by Elsevier Ltd.
About the journal
JournalData powered by TypesetProcedia Engineering
PublisherData powered by TypesetElsevier BV
Open AccessNo