Abstract
Purpose
The bearing that supports the rotor shaft is one of the essential aspects of any spinning machine, particularly in induction motors. Maintaining the bearing condition with some degree of assurance is essential.
Methods
In the present research, a two-level Wavelet Packet transform (WPT) has been employed for the filtration to investigate the meaningful vibration signal. An ANOVA F test and Mutual information method have been used for feature selection. The Logistic Regression (LR) and Support Vector Classifier (SVC) has been considered to classify the fault.
Results
Eleven statistical features from each of the original signals and wavelet decomposed signals were calculated. The present work investigates the existence of a fault, the type of fault, and its severity. The LR and SVC Model are used to evaluate the performance of the optimum feature set obtained from feature selection techniques.
Conclusion
The sub-band signal DD2 with SVC gives the best results for all three cases from the results obtained with the full set feature as compared to the LR technique. The grid search method along with SVC produced the greatest results, with three features provided. Thus the classification accuracy of 100 percent was achieved with only three features in the case of two classes, a maximum accuracy of 96.3% was obtained from four classes with optimal feature 8, and an accuracy of 94.6% with optimal 8 features for 10 class problems. Thus the present technique for bearing fault diagnosis can be implemented for practical purposes.
Similar content being viewed by others
References
Tavner P, Ran L, Penman J, Sedding H (2008) Condition monitoring of rotating electrical machines, The Institution of Engineering and Technology, London, pp 1–306
de Almeida LF, Bizarria JW, Bizarria FC, Mathias MH (2014) Condition-based monitoring system for rolling element bearing using a generic multi-layer perceptron. J Vib Control. https://doi.org/10.1177/1077546314524260
Samanta B, Al-Balushi KR, Al-Araimi SA (2003) Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Eng Appl Artif Intell 16(7–8):657–665. https://doi.org/10.1016/j.engappai.2003.09.006
Kankar PK, Sharma SC, Harsha SP (2011) Fault diagnosis of ball bearings using continuous wavelet transform. Appl Soft Comput 11(2):2300–2312. https://doi.org/10.1016/j.asoc.2010.08.011
Vakharia V, Gupta VK, Kankar PK (2015) A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings. JVC/J Vib Control 21(16):3123–3131. https://doi.org/10.1177/1077546314520830
“Bearing Data Center.” https://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website. Accessed 15 Oct 2019
Patel RK, Giri VK (2017) ANN based performance evaluation of BDI for condition monitoring of induction motor bearings. J Inst Eng Ser B 98(3):267–274. https://doi.org/10.1007/s40031-016-0251-7
Vakharia V, Gupta VK, Kankar PK (2017) Efficient fault diagnosis of ball bearing using ReliefF and random forest classifier. J Brazilian Soc Mech Sci Eng. https://doi.org/10.1007/s40430-017-0717-9
Kumar HS, Pai SP, Sriram NS, Vijay GS (2016) Rolling element bearing fault diagnostics: Development of health index. Proc Inst Mech Eng Part C J Mech Eng Sci. https://doi.org/10.1177/0954406216656214
Gangsar P, Tiwari R (2020) Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: a state-of-the-art review. Mech Syst Signal Process 144:106908. https://doi.org/10.1016/j.ymssp.2020.106908
Anwarsha A, Narendiranath Babu T (2022) A review on the role of tunable Q-factor wavelet transform in fault diagnosis of rolling element bearings. J Vib Eng Technol 10:1793–1808. https://doi.org/10.1007/s42417-022-00484-1
Li X, Jia L, Yang X (2015) Fault diagnosis of train axle box bearing based on multifeature parameters. Discret Dyn Nat Soc. https://doi.org/10.1155/2015/846918
Elssied NOF, Ibrahim O, Osman AH (2014) A novel feature selection based on one-way ANOVA F-test for e-mail spam classification. Res J Appl Sci Eng Technol 7(3):625–638. https://doi.org/10.19026/rjaset.7.299
Li B, Zhang PL, Tian H, Mi SS, Liu DS, Ren GQ (2011) A new feature extraction and selection scheme for hybrid fault diagnosis of gearbox. Expert Syst Appl 38(8):10000–10009. https://doi.org/10.1016/j.eswa.2011.02.008
Battiti R (1994) Using mutual information for selecting features in supervised neural net learning. IEEE Trans Neural Netw 5(4):537–550. https://doi.org/10.1109/72.298224
Pandya DH, Upadhyay SH, Harsha SP (2013) Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Comput 18(2):255–266. https://doi.org/10.1007/s00500-013-1055-1
Shahriar M, Ahsan T, Chong U (2013) Fault diagnosis of induction motors utilizing local binary pattern-based texture analysis. EURASIP J Image Video Process 2013(1):29. https://doi.org/10.1186/1687-5281-2013-29
Kavathekar S, Upadhyay N, Kankar PK (2016) Fault classification of ball bearing by rotation forest technique. Procedia Technol 23:187–192. https://doi.org/10.1016/j.protcy.2016.03.016
De Wu S, Wu CW, Wu TY, Wang CC (2013) Multi-scale analysis based ball bearing defect diagnostics using mahalanobis distance and support vector machine. Entropy 15(2):416–433. https://doi.org/10.3390/e15020416
Wang X, Zheng Y, Zhao Z, Wang J (2015) Bearing fault diagnosis based on statistical locally linear embedding. Sensors (Switzerland) 15(7):16225–16247. https://doi.org/10.3390/s150716225
Li Y, Xu M, Wei Y, Huang W (2016) A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree. Meas J Int Meas Confed 77:80–94. https://doi.org/10.1016/j.measurement.2015.08.034
Zhang S, Li W (2014) Bearing condition recognition and degradation assessment under varying running conditions using NPE and SOM. Math Probl Eng. https://doi.org/10.1155/2014/781583
Sánchez RV, Lucero P, Vásquez RE, Cerrada M, Macancela JC, Cabrera D (2018) Feature ranking for multi-fault diagnosis of rotating machinery by using random forest and KNN. J Intell Fuzzy Syst 34(6):3463–3473. https://doi.org/10.3233/JIFS-169526
Dubey R, Agrawal D (2015) Bearing fault classification using ANN-based Hilbert footprint analysis. IET Sci Meas Technol 9(8):1016–1022. https://doi.org/10.1049/iet-smt.2015.0026
Vakharia V, Gupta VK, Kankar PK (2014) A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings. J Vib Control. https://doi.org/10.1177/1077546314520830
Sharma A, Amarnath M, Kankar PK (2016) Feature extraction and fault severity classification in ball bearings. JVC/J Vib Control 22(1):176–192. https://doi.org/10.1177/1077546314528021
Van M, Kang HJ (2015) Bearing-fault diagnosis using non-local means algorithm and empirical mode decomposition-based feature extraction and two-stage feature selection. IET Sci Meas Technol 9(6):671–680. https://doi.org/10.1049/iet-smt.2014.0228
Deng W, Zhang S, Zhao H, Yang X (2018) A novel fault diagnosis method based on integrating empirical wavelet transform and fuzzy entropy for motor bearing. IEEE Access 6:35042–35056. https://doi.org/10.1109/ACCESS.2018.2834540
Babouri MK, Djebala A, Ouelaa N, Oudjani B, Younes R (2020) Rolling bearing faults severity classification using a combined approach based on multi-scales principal component analysis and fuzzy technique. Int J Adv Manuf Technol 107(9–10):4301–4316. https://doi.org/10.1007/s00170-020-05342-6
Acknowledgements
The authors would like to express their gratitude to Prof. KA Loparo and Case Western Reserve University for making the bearing data set accessible and granting permission to use it.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yadav, S., Patel, R.K. & Singh, V.P. Multiclass Fault Classification of an Induction Motor Bearing Vibration Data Using Wavelet Packet Transform Features and Artificial Intelligence. J. Vib. Eng. Technol. 11, 3093–3108 (2023). https://doi.org/10.1007/s42417-022-00733-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42417-022-00733-3