A multichannel fusion approach based on coupled hidden Markov models for rolling element bearing fault diagnosis

This paper presents a novel multichannel fusion approach based on coupled hidden Markov models (CHMMs) for rolling element bearing fault diagnosis. Different from a hidden Markov model (HMM), a CHMM contains multiple state sequences and observation sequences, and hence has powerful potential for multichannel fusion. In this study, a two-chain CHMM is employed to integrate the two-channel vibration signals collected from bearings, i.e. the horizontal and vertical vibration signals. Efficient probabilistic inference and parameter estimation algorithms are developed for the model. An experiment was carried out to validate the proposed approach. Normalized wavelet packet energy and wavelet packet energy entropy are extracted as features for classification respectively. Then, the results of the proposed approach are compared with those of the currently used approach based on HMMs and one-channel signals. The results show that the proposed approach is feasible and effective to improve the classification rate.

[1]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[2]  Louis A. Liporace,et al.  Maximum likelihood estimation for multivariate observations of Markov sources , 1982, IEEE Trans. Inf. Theory.

[3]  P. D. McFadden,et al.  Vibration monitoring of rolling element bearings by the high-frequency resonance technique — a review , 1984 .

[4]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  Matthew Brand,et al.  Coupled hidden Markov models for modeling interacting processes , 1997 .

[7]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Shih-Fu Ling,et al.  Machinery Diagnosis Based on Wavelet Packets , 1997 .

[9]  Michael I. Jordan,et al.  Probabilistic Independence Networks for Hidden Markov Probability Models , 1997, Neural Computation.

[10]  Chris K. Mechefske,et al.  OBJECTIVE MACHINERY FAULT DIAGNOSIS USING FUZZY LOGIC , 1998 .

[11]  Jing Lin,et al.  Feature Extraction Based on Morlet Wavelet and its Application for Mechanical Fault Diagnosis , 2000 .

[12]  Gary G. Yen,et al.  Wavelet packet feature extraction for vibration monitoring , 2000, IEEE Trans. Ind. Electron..

[13]  Asoke K. Nandi,et al.  Support vector machines for detection and characterization of rolling element bearing faults , 2001 .

[14]  Joydeep Ghosh,et al.  HMMs and Coupled HMMs for multi-channel EEG classification , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[15]  Thomas S. Huang,et al.  Audio-visual speech modeling using coupled hidden Markov models , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Ioannis Antoniadis,et al.  Rolling element bearing fault diagnosis using wavelet packets , 2002 .

[17]  Kevin P. Murphy,et al.  A coupled HMM for audio-visual speech recognition , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[19]  H. Van Brussel,et al.  Machine Condition Monitoring Using Signal Classification Techniques , 2003 .

[20]  Jong Min Lee,et al.  Diagnosis of mechanical fault signals using continuous hidden Markov model , 2004 .

[21]  Ruxu Du,et al.  Hidden Markov Model based fault diagnosis for stamping processes , 2004 .

[22]  Vincenzo Crupi,et al.  Neural-Network-Based System for Novel Fault Detection in Rotating Machinery , 2004 .

[23]  Franz Pernkopf 3D surface inspection using coupled HMMs , 2004, ICPR 2004.

[24]  K. Loparo,et al.  HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings , 2005 .

[25]  P. Baruah,et al.  HMMs for diagnostics and prognostics in machining processes , 2005 .

[26]  Clarence W. de Silva,et al.  Vibration and Shock Handbook , 2005 .

[27]  Svend Gade,et al.  Non-stationary Signal Analysis Using Wavelet Transform, Short-time Fourier Transform and Wigner-ville Distribution the Use of Impulse Response Function for Modal Parameter Estimation Complex Modulus and Damping Measurements Using Resonant and Non-resonant Methods (damping Part Ii) 1 -1994 Digital Fi , 2005 .

[28]  Yongyong He,et al.  Hidden Markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery , 2005 .

[29]  V. Purushotham,et al.  Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition , 2005 .

[30]  Lei Xie,et al.  Speech Animation Using Coupled Hidden Markov Models , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[31]  Sadettin Orhan,et al.  Vibration monitoring for defect diagnosis of rolling element bearings as a predictive maintenance tool : Comprehensive case studies , 2006 .

[32]  M. Zuo,et al.  Gearbox fault detection using Hilbert and wavelet packet transform , 2006 .

[33]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[34]  David,et al.  A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size , 2006 .

[35]  H. Karagülle,et al.  Vibration analysis of rolling element bearings with various defects under the action of an unbalanced force , 2006 .

[36]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[37]  Fulei Chu,et al.  Fault Recognition Method Based on Independent Component Analysis and Hidden Markov Model , 2007 .

[38]  K. Loparo,et al.  Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling : A method for bearing prognostics , 2007 .

[39]  Q. Du,et al.  Application of the EMD method in the vibration analysis of ball bearings , 2007 .

[40]  Anoushiravan Farshidianfar,et al.  Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine , 2007 .

[41]  Ke Zhang,et al.  Adaptive Observer-Based Fault Diagnosis with Application to Satellite Attitude Control Systems , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[42]  Gary D. Bernard,et al.  Multirate Coupled Hidden Markov Models and Their Application to Machining Tool-Wear Classification , 2007, IEEE Transactions on Signal Processing.

[43]  Wei Xue,et al.  APPLICATION OF A BANK OF KALMAN FILTERS AND A ROBUST KALMAN FILTER FOR AIRCRAFT ENGINE SENSOR / ACTUATOR FAULT DIAGNOSIS , 2008 .

[44]  P. Shi,et al.  ADAPTIVE OBSERVER BASED FAULT DIAGNOSIS FOR SATELLITE ATTITUDE CONTROL SYSTEMS , 2008 .

[45]  Robert B. Randall,et al.  Rolling element bearing fault diagnosis based on the combination of genetic algorithms and fast kurtogram , 2009 .

[46]  Cristina Castejón,et al.  Automated diagnosis of rolling bearings using MRA and neural networks , 2010 .

[47]  Applying improved multi-scale entropy and support vector machines for bearing health condition identification , 2010 .