Envelope-Wavelet Packet Transform for Machine Condition Monitoring

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. Keywords—Envelope Detection, Wavelet Transform, Bearing Faults, Machine Health Monitoring.

[1]  I. S. Bozchalooi,et al.  A joint resonance frequency estimation and in-band noise reduction method for enhancing the detectability of bearing fault signals , 2008 .

[2]  Kenneth A. Loparo,et al.  Estimation of the running speed and bearing defect frequencies of an induction motor from vibration data , 2004 .

[3]  M. F. Yaqub,et al.  Resonant frequency band estimation using adaptive wavelet decomposition level selection , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[4]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble , 2007 .

[5]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[6]  F Zhao,et al.  Condition prediction based on wavelet packet transform and least squares support vector machine methods , 2009 .

[7]  W. Marsden.  I and J , 2012 .

[8]  Mohamed El Hachemi Benbouzid.  A review of induction motors signature analysis as a medium for faults detection , 2000, IEEE Trans. Ind. Electron..

[9]  H. W. Ngan,et al.  Detection of Motor Bearing Outer Raceway Defect by Wavelet Packet Transformed Motor Current Signature Analysis , 2010, IEEE Transactions on Instrumentation and Measurement.

[10]  Zhixin Yang,et al.  Machine condition monitoring and fault diagnosis based on support vector machine , 2010, 2010 IEEE International Conference on Industrial Engineering and Engineering Management.

[11]  Fulei Chu,et al.  Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography , 2004 .

[12]  M. F. Yaqub,et al.  Machine fault severity estimation based on adaptive wavelet nodes selection and SVM , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[13]  Kuo-Chung Lin,et al.  Wavelet packet feature extraction for vibration monitoring , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[14]  Iqbal Gondal,et al.  Severity invariant feature selection for machine health monitoring , 2011 .

[15]  Robert B. Randall,et al.  THE RELATIONSHIP BETWEEN SPECTRAL CORRELATION AND ENVELOPE ANALYSIS IN THE DIAGNOSTICS OF BEARING FAULTS AND OTHER CYCLOSTATIONARY MACHINE SIGNALS , 2001 .

[16]  Peter W. Tse,et al.  Wavelet Analysis and Envelope Detection For Rolling Element Bearing Fault Diagnosis—Their Effectiveness and Flexibilities , 2001 .

[17]  Michael J. Devaney,et al.  Adjustable Speed Drive Bearing Fault Detection via Wavelet Packet Decomposition , 2006, 2006 IEEE Instrumentation and Measurement Technology Conference Proceedings.

[18]  James S. Walker,et al.  A Primer on Wavelets and Their Scientific Applications , 1999 .

[19]  Michael G. Pecht,et al.  Support Vector Prognostics Analysis of Electronic Products and Systems , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.

[20]  Michael J. Devaney,et al.  Bearing damage detection via wavelet packet decomposition of the stator current , 2004, IEEE Transactions on Instrumentation and Measurement.

[21]  Robert X. Gao,et al.  Wavelet transform with spectral post-processing for enhanced feature extraction , 2002, IMTC/2002. Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.00CH37276).

[22]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[23]  Yann LeCun,et al.  Measuring the VC-Dimension of a Learning Machine , 1994, Neural Computation.