- Title
- Envelope-Wavelet Packet Transform for Machine Condition Monitoring
- Creator
- Yaqub, Muhammad; Gondal, Iqbal; Kamruzzaman, Joarder
- Date
- 2011
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/156724
- Identifier
- vital:11477
- Identifier
- ISBN:2010-376X
- Abstract
- Wavelet transform has been extensively used in machine fault diagnosis and prognosis owing to its strength to deal with non-stationary signals. The existing Wavelet transform based schemes for fault diagnosis employ wavelet decomposition of the entire vibration frequency which not only involve huge computational overhead in extracting the features but also increases the dimensionality of the feature vector. This increase in the dimensionality has the tendency to 'over-fit' the training data and could mislead the fault diagnostic model. In this paper a novel technique, envelope wavelet packet transform (EWPT) is proposed in which features are extracted based on wavelet packet transform of the filtered envelope signal rather than the overall vibration signal. It not only reduces the computational overhead in terms of reduced number of wavelet decomposition levels and features but also improves the fault detection accuracy. Analytical expressions are provided for the optimal frequency resolution and decomposition level selection in EWPT. Experimental results with both actual and simulated machine fault data demonstrate significant gain in fault detection ability by EWPT at reduced complexity compared to existing techniques.
- Publisher
- World Academy of Science, Engineering and Technology (WASET)
- Relation
- 2011 International Conference on Control, Automation, Robotics and Vision (ICCARV); Venice, Italy; 23rd-25th November 2011; published in Proceedings of the World Academy of Science, Engineering and Technology, International Journal of Mechanical, Aerospace, Industrial, Mechatronic and Manufacturing Engineering Vol. 5, p. 1597-1603
- Rights
- Unknown
- Rights
- Open Access
- Rights
- This metadata is freely available under a CCO license
- Subject
- MD Multidisciplinary; Envelope detection; Wavelet transform; Bearing faults; Machine health monitoring
- Full Text
- Reviewed
- Hits: 1141
- Visitors: 1252
- Downloads: 163
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Published version | 547 KB | Adobe Acrobat PDF | View Details Download |