Bearing Health Monitoring Using Relief-F-Based Feature Relevance Analysis and HMM
Source abstract
Abstract
Nowadays, bearings installed in industrial electric motors are constituted as the primary mode of a failure affecting the global energy consumption. Since industries’ energy demand has a growing tendency, interest for efficient maintenance in electric motors is decisive. Vibration signals from bearings are employed commonly as a non-invasive approach to support fault diagnosis and severity evaluation of rotating machinery. However, vibration-based diagnosis poses a challenge concerning the signal properties, e.g., highly dynamic and non-stationary. Here, we introduce a knowledge-based tool to analyze multiple health conditions in bearings. Our approach includes a stochastic feature selection method, termed Stochastic Feature Selection (SFS), highlighting and interpreting relevant multi-domain attributes (time, frequency, and time–frequency) related to the bearing faults discriminability. In particular, a relief-F-based ranking and a Hidden Markov Model are trained under a windowing scheme to achieve our SFS. Obtained results in a public database demonstrate that our proposal is competitive compared to state-of-the-art algorithms concerning both the number of features selected and the classification accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Engineering Diagnostics and Reliability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Automatics Research Group, Engineering Faculty, Universidad Tecnológica de Pereira, Pereira 660001, Colombia
Signal Processing and Recognition Group, Universidad Nacional de Colombia sede Manizales, Manizales 170001, Colombia
Funding
Universidad Tecnologica de Pereira
References (77)
Show source-provided references
1. Rotating machinery prognostics: State of the art, challenges and opportunities10.1016/j.ymssp.2008.06.009 ↗
2. A survey of faults on induction motors in offshore oil industry, petrochemical industry, gas terminals, and oil refineries10.1109/28.464536 ↗
3. Fault detection via recurrence time statistics and one-class classification10.1016/j.patrec.2016.07.019 ↗
4. Zhu, Y., and Gao, Z. (2014, January 9–11). Robust observer-based fault detection via evolutionary optimization with applications to wind turbine systems. Proceedings of the 2014 IEEE 9th Conference on Industrial Electronics and Applications (ICIEA), Hangzhou, China.10.1109/ICIEA.2014.6931428 ↗
5. A survey of fault diagnosis and fault tolerant techniques Part I: Fault diagnosis with model-based and signal-based approaches10.1109/TIE.2015.2417501 ↗
6. Imani, M., and Braga-Neto, U.M. (November, January 29). Optimal finite-horizon sensor selection for Boolean Kalman Filter. Proceedings of the 2017 51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.10.1109/ACSSC.2017.8335602 ↗
7. Fault diagnosis in internal combustion engines using extension neural network10.1109/TIE.2013.2261033 ↗
8. Application of the EEMD method to rotor fault diagnosis of rotating machinery10.1016/j.ymssp.2008.11.005 ↗
9. Detection of gear failures via vibration and acoustic signals using wavelet transform10.1006/mssp.2001.1435 ↗
10. Automatic gear and bearing fault localization using vibration and acoustic signals10.1016/j.apacoust.2015.04.016 ↗
11. Holguín-Londoño, M., Cardona-Morales, O., Sierra-Alonso, E.F., Mejia-Henao, J.D., Orozco-Gutiérrez, Á., and Castellanos-Dominguez, G. (2016). Machine Fault Detection Based on Filter Bank Similarity Features Using Acoustic and Vibration Analysis. Math. Probl. Eng., 2016.10.1155/2016/7906834 ↗
12. Bearing condition diagnosis and prognosis using applied nonlinear dynamical analysis of machine vibration signal10.1016/j.jsv.2008.02.051 ↗
13. Attoui, I., Boutasseta, N., Fergani, N., Oudjani, B., and Deliou, A. (2015, January 25–27). Vibration-based bearing fault diagnosis by an integrated DWT-FFT approach and an adaptive neuro-fuzzy inference system. Proceedings of the 2015 3rd International Conference on Control, Engineering & Information Technology (CEIT), Tlemcen, Algeria.10.1109/CEIT.2015.7233098 ↗
14. Feature Trend Extraction and Adaptive Density Peaks Search for Intelligent Fault Diagnosis of Machines10.1109/TII.2018.2810226 ↗
15. A review on machinery diagnostics and prognostics implementing condition-based maintenance10.1016/j.ymssp.2005.09.012 ↗
16. Method of shaft crack detection based on squared gain of vibration amplitude10.1007/s11071-019-05221-0 ↗
17. A new method for the estimation of bearing health state and remaining useful life based on the moving average cross-correlation of power spectral density10.1016/j.ymssp.2020.106617 ↗
18. LMD method and multi-class RWSVM of fault diagnosis for rotating machinery using condition monitoring information10.3390/s130708679 ↗
19. Prognosis of gear failures in dc starter motors using hidden Markov models10.1109/TIE.2010.2052540 ↗
20. Permutation entropy: A nonlinear statistical measure for status characterization of rotary machines10.1016/j.ymssp.2011.11.022 ↗
21. Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference10.1016/j.eswa.2010.02.118 ↗
22. Bearing fault diagnosis based on multi-scale permutation entropy and adaptive neuro fuzzy classifier10.1177/1077546313490778 ↗
23. Permutation entropy: A natural complexity measure for time series10.1103/PhysRevLett.88.174102 ↗
24. Aziz, W., and Arif, M. (2005, January 23–25). Multiscale permutation entropy of physiological time series. Proceedings of the 9th International Multitopic Conference, Karachi, Pakistan.10.1109/INMIC.2005.334494 ↗
25. Generalized composite multiscale permutation entropy and Laplacian score based rolling bearing fault diagnosis10.1016/j.ymssp.2017.06.011 ↗
26. A novel method of composite multiscale weighted permutation entropy and machine learning for fault complex system fault diagnosis10.1016/j.measurement.2020.107748 ↗
27. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM10.1016/j.measurement.2015.03.017 ↗
28. Khamoudj, C.E., Benbouzid-Si Tayeb, F., Benatchba, K., Benbouzid, M., and Djaafri, A. (2020). A Learning Variable Neighborhood Search Approach for Induction Machines Bearing Failures Detection and Diagnosis. Energies, 13.10.3390/en13112953 ↗
29. Imani, M., and Ghoreishi, S.F. (2020, January 1–3). Bayesian Optimization Objective-Based Experimental Design. Proceedings of the 2020 American Control Conference (ACC 2020), Denver, CO, USA.10.23919/ACC45564.2020.9147824 ↗
30. Ghoreishi, S.F., and Imani, M. (2020, January 1–3). Bayesian Optimization for Efficient Design of Uncertain Coupled Multidisciplinary Systems. Proceedings of the 2020 American Control Conference (ACC 2020), Denver, CO, USA.10.23919/ACC45564.2020.9147526 ↗
31. Detection and diagnosis of bearing faults using shift-invariant dictionary learning and hidden Markov model10.1016/j.ymssp.2015.11.022 ↗
32. A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders10.1016/j.ymssp.2017.09.026 ↗
33. Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine10.1016/j.knosys.2017.10.024 ↗
34. Rolling element bearing fault diagnosis using convolutional neural network and vibration image10.1016/j.cogsys.2018.03.002 ↗
35. Wang, Y., Ning, D., and Feng, S. (2020). A Novel Capsule Network Based on Wide Convolution and Multi-Scale Convolution for Fault Diagnosis. Appl. Sci., 10.10.3390/app10103659 ↗
36. Shen, C., Xie, J., Wang, D., Jiang, X., Shi, J., and Zhu, Z. (2019). Improved hierarchical adaptive deep belief network for bearing fault diagnosis. Appl. Sci., 9.10.3390/app9163374 ↗
37. Li, J., Li, X., He, D., and Qu, Y. (2020). Unsupervised rotating machinery fault diagnosis method based on integrated SAE–DBN and a binary processor. J. Intell. Manuf., 1–18.10.1007/s10845-020-01543-8 ↗
38. Tao, H., Wang, P., Chen, Y., Stojanovic, V., and Yang, H. (2020). An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks. J. Frankl. Inst.10.1016/j.jfranklin.2020.04.024 ↗
39. Convolutional neural network-based hidden Markov models for rolling element bearing fault identification10.1016/j.knosys.2017.12.027 ↗
40. Robust diagnosis of rolling element bearings based on classification techniques10.1109/TII.2012.2231084 ↗
41. Bearing fault detection by a novel condition-monitoring scheme based on statistical-time features and neural networks10.1109/TIE.2012.2219838 ↗
42. PCA-based feature selection scheme for machine defect classification10.1109/TIM.2004.834070 ↗
43. The fault feature extraction and classification of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform10.1016/j.measurement.2014.04.016 ↗
44. Feature selection for machine fault diagnosis using clustering of non-negation matrix factorization10.1016/j.measurement.2016.08.003 ↗
45. A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection10.1016/j.knosys.2016.10.022 ↗
46. Bearing-fault diagnosis using non-local means algorithm and empirical mode decomposition-based feature extraction and two-stage feature selection10.1049/iet-smt.2014.0228 ↗
47. Early fault detection and diagnosis in bearings for more efficient operation of rotating machinery10.1016/j.energy.2016.08.039 ↗
48. Euclidean distance based feature ranking and subset selection for bearing fault diagnosis10.1016/j.eswa.2020.113400 ↗
49. Intelligent fault diagnosis of rotating machinery using improved multiscale dispersion entropy and mRMR feature selectionn10.1016/j.knosys.2018.09.004 ↗
50. Hotait, H., Chiementin, X., and Rasolofondraibe, L. (2020). AOC-OPTICS: Automatic Online Classification for Condition Monitoring of Rolling Bearing. Processes, 8.10.3390/pr8050606 ↗
51. Feature relevance estimation for vibration-based condition monitoring of an internal combustion engine
52. Observer-biased bearing condition monitoring: From fault detection to multi-fault classification10.1016/j.engappai.2016.01.038 ↗
53. Monitoring and diagnosis for the DC–DC converter using the magnetic near field waveform10.1109/TIE.2010.2051939 ↗
54. Nelwamondo, F.V., and Marwala, T. (2006, January 8–11). Faults detection using gaussian mixture models, mel-frequency cepstral coefficients and kurtosis. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Taipei, Taiwan.10.1109/ICSMC.2006.384397 ↗
55. Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition10.1016/j.specom.2011.11.004 ↗
56. Kononenko, I. (1994, January 6–8). Estimating attributes: Analysis and extensions of RELIEF. Proceedings of the European Conference on Machine Learning, Catania, Italy.10.1007/3-540-57868-4_57 ↗
57. Theoretical and empirical analysis of ReliefF and RReliefF10.1023/A:1025667309714 ↗
58. Cappé, O., Moulines, E., and Rydén, T. (2009, January 20–24). Inference in hidden markov models. Proceedings of the EUSFLAT Conference, Lisbon, Portugal.
59. Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model10.1016/j.engappai.2015.03.007 ↗
60. Murphy, K. (2020, July 07). Hidden Markov Model (hmm) Toolbox for Matlab. Available online: https://www.cs.ubc.ca/~murphyk/Software/HMM/hmm.html.
61. Relief-based feature selection: Introduction and review10.1016/j.jbi.2018.07.014 ↗
62. On the memory complexity of the forward–backward algorithm10.1016/j.patrec.2009.09.023 ↗
63. Loparo, K.A. (2003). Bearing Data Center, Case Western Reserve University.
64. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study10.1016/j.ymssp.2015.04.021 ↗
65. Analysis of Statistical Time-Domain Features Effectiveness in Identification of Bearing Faults from Vibration Signal10.1109/JSEN.2017.2727638 ↗
66. Estimation of the running speed and bearing defect frequencies of an induction motor from vibration data10.1016/S0888-3270(03)00052-9 ↗
67. Unsupervised learning of human action categories using spatial-temporal words10.1007/s11263-007-0122-4 ↗
68. Dynamic feature extraction: An application to voice pathology detection
69. ART–KOHONEN neural network for fault diagnosis of rotating machinery10.1016/S0888-3270(03)00073-6 ↗
70. Orozco-Gutierrez, G.C.D. Kernel-based relevance analysis with enhanced interpretability for detection of brain activity patterns10.3389/fnins.2017.00550 ↗
71. Jian, X., Li, W., Guo, X., and Wang, R. (2019). Fault Diagnosis of Motor Bearings Based on a One-Dimensional Fusion Neural Networkk. Sensors, 19.10.3390/s19010122 ↗
72. Identification of bearing faults using time domain zero-crossings10.1016/j.ymssp.2011.06.001 ↗
73. Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings10.1016/j.neucom.2012.07.019 ↗
74. Roller element bearing fault diagnosis using singular spectrum analysis10.1016/j.ymssp.2012.08.019 ↗
75. Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier10.1016/j.measurement.2012.12.011 ↗
76. Bearing faults diagnosis using fuzzy expert system relying on an Improved Range Overlaps and Similarity method10.1016/j.eswa.2018.04.025 ↗
77. HMM-based fault detection and diagnosis scheme for rolling element bearings10.1115/1.1924636 ↗