This article analyzes a data-driven fault diagnosis method for rolling element bearing under different operating conditions. The work is aimed to incorporate the filter-type feature selection algorithms, namely, neighborhood component analysis, minimum redundancy maximum relevance, chi-square, and ReliefF algorithms for the feature ranking of the extracted time-domain statistical features from the collected vibration data of the five different bearing defect conditions (normal, outer race defect, ball defect, inner race defect, and combined inner and ball defect). The vibration data have been recorded and an envelope analysis technique for pre-processing the signal is used to identify the fundamental defect frequencies of all the bearings. The artificial neural network and the support vector machine are used to predict the comparative performance of the feature selection algorithms. The results demonstrate that the neighborhood component analysis algorithm achieves the highest accuracies for the bearing fault detection with both the support vector machine and artificial neural network among all the feature selection methods. Therefore, the effective feature ranking before the fault classification by the machine learning algorithms can lead to an efficient and reliable bearing fault diagnosis.
JardineAKSLinDBanjevicD. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process2006; 20: 1483–1510.
2.
LaceySJ. An overview of bearing vibration analysis. Maint Asset Manag2008; 23: 32–42.
3.
StackJRHabetlerTGHarleyRG. Fault classification and fault signature production for rolling element bearings in electric machines. IEEE Int Symp Diagn Electr Mach Power Electron Drives2003; 40: 172–176.
4.
McFaddenPDSmithJD. Model for the vibration produced by a single point defect in a rolling element bearing. J Sound Vib1984; 96: 69–82.
5.
MeyerLDAhlgrenFFWeichbrodtB. An analytic model for ball bearing vibrations to predict vibration response to distributed defects. J Mech Des1980; 102: 205–210.
6.
HarshaSP. Nonlinear dynamic analysis of a high-speed rotor supported by rolling element bearings. J Sound Vib2006; 290: 65–100.
7.
SawalhiNRandallRB. Simulating gear and bearing interactions in the presence of faults: part I. The combined gear bearing dynamic model and the simulation of localised bearing faults. Mech Syst Signal Process2008; 22: 1924–1951.
8.
PandyaDHUpadhyaySHHarshaSP. Nonlinear dynamic analysis of high speed bearings due to combined localized defects. J Vib Control2014; 20: 2300–2313.
9.
HarshaSPKankarPK. Stability analysis of a rotor bearing system due to surface waviness and number of balls. Int J Mech Sci2004; 46: 1057–1081.
10.
KhanamSTandonNDuttJK. Multi-event excitation force model for inner race defect in a rolling element bearing. J Tribol2016; 138: 1–15.
11.
McInernySADaiY. Basic vibration signal processing for bearing fault detection. IEEE Trans Educ2003; 46: 149–156.
12.
SawalhiNRandallRB. The application of spectral kurtosis to bearing diagnostics. Proc Acoust2004; 2004: 393–398.
13.
KankarPKSharmaSCHarshaSP. Rolling element bearing fault diagnosis using wavelet transform. Neurocomputing2011; 74: 1638–1645.
14.
YanRGaoRX. Rotary machine health diagnosis based on empirical mode decomposition. J Vib Acoust Trans ASME2008; 130: 1–12.
15.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
16.
DengXLiYWengJ, et al. Feature selection for text classification: a review. Multimed Tools Appl2019; 78: 3797–3816.
WuSDWuCWWuTY, et al. Multi-Scale analysis based ball bearing defect diagnostics using Mahalanobis distance and support vector machine. Entropy2013; 15: 416–433.
19.
ZhengJChengJYangY, et al. A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination. Mech Mach Theory2014; 78: 187–200.
20.
SánchezRVLuceroPVásquezRE, et al. A comparative feature analysis for gear pitting level classification by using acoustic emission, vibration and current signals. IFAC PapersOnLine2018; 51: 346–352.
21.
SharmaAAmarnathMKankarPK. Use of feature ranking techniques for defect severity estimation of rolling element bearings. Int J Acoust Vib2018; 23: 49.
22.
RauberTWDe Assis BoldtFVarejãoFM. Heterogeneous feature models and feature selection applied to bearing fault diagnosis. IEEE Trans Ind Electron2015; 62: 637–646.
23.
KappaganthuKNatarajC. Feature selection for fault detection in rolling element bearings using mutual information. J Vib Acoust Trans ASME2011; 133: 1–11.
24.
ZhangKLiYScarfP, et al. Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks. Neurocomputing2011; 74: 2941–2952.
25.
IslamMRIslamMMMKimJM. Feature selection techniques for increasing reliability of fault diagnosis of bearings. In: Proceedings of the 9th international conference on electrical and computer engineering (ICECE), Dhaka, Bangladesh, 20–22 December 2016, pp.396–399. New York: IEEE.
26.
YuanSFChuFL. Fault diagnostics based on particle swarm optimisation and support vector machines. Mech Syst Signal Process2007; 21: 1787–1798.
27.
PengHWChiangPJ. Control of mechatronics systems: ball bearing fault diagnosis using machine learning techniques. In: Proceedings of the 8th Asian control conference (ASCC), 2011, pp.175–180, http://toc.proceedings.com/11902webtoc.pdf
28.
YuJ. Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring. Mech Syst Signal Process2017; 83: 149–162.
29.
AmarnathMSugumaranVKumarH. Exploiting sound signals for fault diagnosis of bearings using decision tree. Measurement2013; 46: 1250–1256.
30.
WidodoAYangBS. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process2007; 21: 2560–2574.
31.
GrylliasKCAntoniadisIA. A support vector machine approach based on physical model training for rolling element bearing fault detection in industrial environments. Eng Appl Artif Intell2012; 25: 326–344.
32.
Manjurul IslamMMKimJM. Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector machines. Reliab Eng Syst Saf2019; 184: 55–66.
33.
SharmaA. Fault diagnosis of bearings using recurrences and artificial intelligence techniques2022; 5: 031004.
34.
SamantaBAl-BalushiKR. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech Syst Signal Process2003; 17: 317–328.
35.
UnalMOnatMDemetgulM, et al. Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network. Measurement2014; 58: 187–196.
36.
SharmaABhardwajSKumarP. Fault diagnosis of rolling element bearings using fractional linear prediction and AI techniques. Life Cycle Reliab Saf Eng2019; 8: 11–19.
37.
Haj MohamadTNatarajC. Fault identification and severity analysis of rolling element bearings using phase space topology. J Vib Control2021; 27: 295–310.
38.
LeeSHMazumderJParkJ, et al. Ranked feature-based laser material processing monitoring and defect diagnosis using k-NN and SVM. J Manuf Process2020; 55: 307–316.
39.
GoyalDDhamiSSPablaBS. Vibration response-based intelligent non-contact fault diagnosis of bearings. J Nondestruct Eval Diagn Progn Eng Syst2021; 4: 1–11.
Robnik-SikonjaMKononenkoI. Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn2003; 53: 23–69.
45.
SharmaAPavanMAKankarK. Novel ensemble techniques for classification of rolling element bearing faults. J Braz Soc Mech Sci Eng2017; 39: 709–724.
46.
SugumaranVSabareeshGRRamachandranKI. Fault diagnostics of roller bearing using kernel based neighborhood score multi-class support vector machine. Exp Syst Appl2008; 34: 3090–3098.
47.
KankarPKSharmaSCHarshaSP. Fault diagnosis of ball bearings using continuous wavelet transform. Appl Soft Comput J2011; 11: 2300–2312.
48.
ChenFTangBSongT, et al. Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization. Measurement2014; 47: 576–590.
49.
SaidiLBen AliJFnaiechF. Application of higher order spectral features and support vector machines for bearing faults classification. ISA Trans2015; 54: 193–206.
50.
GoyalDDhamiSSPablaBS. Non-contact fault diagnosis of bearings in machine learning environment. IEEE Sens J2020; 20: 4816–4823.
