Acoustic Emission Fault Diagnosis of Rolling Bearing Based on Discrete Hidden Markov Model
Conference paper
First Online:
- 271 Downloads
Abstract
Acoustice emission (AE) technology has emerged as a promising diagnostic approach for rolling bearing fault detection. In this paper, the discrete hidden Markov chain model (DHMM) is used to diagnose faults based on AE signals. A tool built by MATLAB software is used to collect the acoustic emission signals of the rolling bearings for data reading and frame processing and then extract the vector that reflects the characteristics of the rolling bearing. The feature vectors are analyzed and diagnosed by using the DHMM. The results show that the DHMM method can provide reliable fault diagnosis for a rolling bearing.
Keywords
Rolling bearing Acoustic emission Markov model Framing Wavelet packet decomposition Fault diagnosisReferences
- 1.J. Han, R.L. Zhang, Failure Mechanism and Diagnostic Technology of Rotating Machinery (Machinery Industry Press, Beijing, 1997)Google Scholar
- 2.B.Y. Wang, Y.Q. Liu, Y.Y. Liao, Sensitivity analysis of rolling bearing fault signal time-domain characteristic index. Bearing 43(10), 45–48 (2015)Google Scholar
- 3.Y.Z. Liu, X. Zhang, J. Wu, Contact fatigue microcosmic mechanism and influencing factors of rolling bearings. Bearing 43(10), 53–57 (2015)Google Scholar
- 4.K.S. Andrew, D.L. Jardine, D. banjevic, A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal Process. 20, 1483–1510 (2006)ADSGoogle Scholar
- 5.R.J. Hao, W.X. Lu, F.L. Zhu, Acoustic emission detection technology used for rolling bearing fault diagnosis research. Vib. Shock 27(3), 75–79 (2008)Google Scholar
- 6.M.Y. Li, Z.D. Shang, H.C. Cai, Acoustic Emission Detection and Signal Processing (Science Press, Beijing, 2010)Google Scholar
- 7.F. Qi Minfang, J. Zhongguang, et al., Comprehensive evaluation method of thermal power unit based on information entropy and principal component analysis. J. Elect. Eng. China 33(2), 58–64 (2013)Google Scholar
- 8.L. Jiang, J.P. Xuan, T.L. Shi, Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis. Mech. Syst. Signal Process. 41, 113–126 (2013)ADSGoogle Scholar
- 9.Y.M. Hou, J.B. Sun, Y. Zhang, Fault diagnosis of rolling bearings based on PSO-BP neural network and Hilbert spectrum singular value. Comb. Mach. Tool Auto. Mach. Tech. (7), 77–83 (2014)Google Scholar
- 10.C.J. Feng, HMM Dynamic Pattern Recognition Theory and Method, and Its Application in Rotating Machinery Fault Diagnosis, PhD thesis, Hangzhou: Zhejiang University, 2002Google Scholar
- 11.H.F. Yuan, C. Ji, H.Q. Wang, Intelligent diagnosis method for rolling bearing based on GA and DHMM and KPCA-RS improvement research. Measur. Cont. Tech. 33(11), 21–28 (2014)Google Scholar
- 12.W. Fan, P. Fu, Q.Q. Zheng, Rolling bearing fault diagnosis based on DHMM. Mech. Eng. Auto. 4, 132–135 (2015)Google Scholar
- 13.Z. Wu, S.X. Yang, A New Method for Fault Feature Extraction and Pattern Classification of Rotating Machinery (Science Press, Beijing, 2012)Google Scholar
- 14.L.R. Rabiner, A tutorial on models and selected applications in speech recognition. Proc. TEES 77(2), 257–286 (1989)Google Scholar
- 15.R.J. Elliott, J. Deng, Change point estimation for continuous-time hidden Markov models. Syst. Cont. Lett. 62(2), 112–114 (2013)MathSciNetzbMATHGoogle Scholar
- 16.D.A. Tobon-Mejia, K. Medjaher, N. Zerhouni, A data-driven failure prognostics method based on mixture of Gaussians Hidden Markov Models. IEEE Trans. Reliab. 61(2), 491–503 (2012)Google Scholar
Copyright information
© Springer Nature Switzerland AG 2019