In the present study an attempt has been made to identify various bearing faults using machine learning algorithm. Vibration signals obtained from faults in inner race, outer race, rolling element and combined faults are considered. Raw vibration signal cannot be used directly since vibration signals are masked by noise. To overcome this difficulty combined time frequency domain method such as wavelet transform is used. Further wavelet selection criteria based on minimum permutation entropy is employed to select most appropriate base wavelet. Statistical features from selected wavelet coefficients are calculated to form feature vector. To reduce size of feature vector information gain attribute selection method is employed. Modified feature set is fed in to machine learning algorithm such as random forest and self-organizing map for getting maximize fault identification efficiency. Results obtained revealed that attribute selection method shows improvement in fault identification accuracy of bearing components.

Date Published: 1 April 2015
PDF: 8 pages
Proc. SPIE 9437, Structural Health Monitoring and Inspection of Advanced Materials, Aerospace, and Civil Infrastructure 2015, 94370Q (1 April 2015); doi: 10.1117/12.2180511

Published in SPIE Proceedings Vol. 9437:
Structural Health Monitoring and Inspection of Advanced Materials, Aerospace, and Civil Infrastructure 2015
Peter J. Shull, Editor(s)