In this paper, we introduce a new bearing fault detection and diagnosis scheme based on hidden Markov modeling (HMM) of vibration signals. Features extracted from amplitude demodulated vibration signals from both normal and faulty bearings were used to train HMMs to represent various bearing conditions. The features were based on the reflection coefficients of the polynomial transfer function of an autoregressive model of the vibration signals. Faults can be detected online by monitoring the probabilities of the pretrained HMM for the normal case given the features extracted from the vibration signals. The new technique also allows for diagnosis of the type of bearing fault by selecting the HMM with the highest probability. The new scheme was also adapted to diagnose multiple bearing faults. In this adapted scheme, features were based on the selected node energies of a wavelet packet decomposition of the vibration signal. For each fault, a different set of nodes, which correlates with the fault, is chosen. Both schemes were tested with experimental data collected from an accelerometer measuring the vibration from the drive-end ball bearing of an induction motor (Reliance Electric 2 HP IQPreAlert) driven mechanical system and have proven to be very accurate.
Skip Nav Destination
e-mail: hxo9@cwru.edu
e-mail: kal4@cwru.edu
Article navigation
August 2005
Technical Papers
HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings
Hasan Ocak,
Hasan Ocak
Department of Electrical Engineering and Computer Science,
e-mail: hxo9@cwru.edu
Case Western Reserve University
, Cleveland, OH
Search for other works by this author on:
Kenneth A. Loparo
Kenneth A. Loparo
Department of Electrical Engineering and Computer Science,
e-mail: kal4@cwru.edu
Case Western Reserve University
, Cleveland, OH
Search for other works by this author on:
Hasan Ocak
Department of Electrical Engineering and Computer Science,
Case Western Reserve University
, Cleveland, OHe-mail: hxo9@cwru.edu
Kenneth A. Loparo
Department of Electrical Engineering and Computer Science,
Case Western Reserve University
, Cleveland, OHe-mail: kal4@cwru.edu
J. Vib. Acoust. Aug 2005, 127(4): 299-306 (8 pages)
Published Online: September 23, 2004
Article history
Received:
May 10, 2002
Revised:
September 23, 2004
Citation
Ocak, H., and Loparo, K. A. (September 23, 2004). "HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings." ASME. J. Vib. Acoust. August 2005; 127(4): 299–306. https://doi.org/10.1115/1.1924636
Download citation file:
Get Email Alerts
Related Articles
A Combination of W K NN to Fault Diagnosis of Rolling Element Bearings
J. Vib. Acoust (December,2009)
Feature Selection for Fault Detection in Rolling Element Bearings Using Mutual Information
J. Vib. Acoust (December,2011)
Defect Detection for Bearings Using Envelope Spectra of Wavelet Transform
J. Vib. Acoust (October,2004)
Rotary Machine Health Diagnosis Based on Empirical Mode Decomposition
J. Vib. Acoust (April,2008)
Related Proceedings Papers
Related Chapters
Experimental and Statistical Study on the Noise Generated by Surface Defects of Bearing Rolling Bodies
Bearing and Transmission Steels Technology
Application of Independent Component Analysis in Rolling Element Bearing Vibration Signal Analysis
Proceedings of the 2010 International Conference on Mechanical, Industrial, and Manufacturing Technologies (MIMT 2010)
Fault Diagnosis based on Rough Set and Dependent Feature Vector for Rolling Element Bearings
International Conference on Control Engineering and Mechanical Design (CEMD 2017)