Abstract
Feature selection is critical to maintain high performance of classification-based fault diagnosis with a large feature size. In this paper, we propose a criterion to evaluate features effectiveness by class separability that is defined on cosine similarity in the kernel space of the Gaussian radial basis function. We develop a feature selection algorithm accordingly using the proposed criterion together with sequential backward selection and a feature re-ranking mechanism. We then employ the proposed feature selection algorithm to determine fault-sensitive features and select them for fault level diagnosis of planetary gearboxes. The experimental results demonstrate that the proposed algorithm can effectively reduce the feature size and improve accuracy of fault level diagnosis simultaneously.
Similar content being viewed by others
References
Apaydin T, Ferhatosmanoglu H (2006) Access structures for angular similarity queries. IEEE Trans Knowl Data Eng 18:1512–1525
Cai D, He X, Han J (2008) SRDA: An efficient algorithm for large-scale discriminant analysis. IEEE Trans Knowl Data Eng 20:1–12
Chen FL, Li FC (2010) Combination of feature selection approaches with SVM in credit scoring. Expert Syst Appl 37:4902–4909
Chong EKP, Żak SH (2008) An introduction to optimization, 3rd edn. Wiley, Hoboken
Decker HJ (2002) Crack detection for aerospace quality spur gears. In: Proceedings of the American Helicopter Society 58th annual forum. Montreal, Canada, pp 1–17
Decker HJ, Lewicki DG (2003) Spiral bevel pinion crack detection in a helicopter gearbox. Proceedings of the American Helicopter Society 59th annual forum. Phoenix, USA, pp 1222–1232
Faloutsos C, Oard DW (1995) A survey of information retrieval and filtering methods. Technical Report CS-TR-3514. Department of Computer Science, University of Maryland, College Park, USA, pp 1–24
Frank A, Asuncion A (2010) UCI machine learning repository. School of Information and Computer Science, University of California, Irvine, USA. http://archive.ics.uci.edu/ml
Gheyas IA, Smith LS (2010) Feature subset selection in large dimensionality domains. Pattern Recognit 43:5–13
Hsu PH (2007) Feature extraction of hyperspectral images using wavelet and matching pursuit. ISPRS J Photogram 62:78–92
Inalpolat M, Kahraman A (2009) A theoretical and experimental investigation of modulation sidebands of planetary gear sets. J Sound Vib 323:677–696
Jiang Q, Jia M, Hu J, Xu F (2009) Machinery fault diagnosis using supervised manifold learning. Mech Syst Signal Process 23:2301–2311
Kaindl H, Kainz G (1997) Bidirectional heuristic search reconsidered. J Artif Intell Res 7:283–317
Keller J, Grabill P (2003) Vibration monitoring of UH-60A main transmission planetary carrier fault. In: Proceedings of the American Helicopter Society 59th annual forum. Phoenix, USA, pp 1–11
Kuo BC, Landgrebe DA (2004) Nonparametric weighted feature extraction for classification. IEEE Trans Geosci Remote 42:1096–1105
Lei Y, Zuo MJ (2009) Gear crack level identification based on weighted k nearest neighbour classification algorithm. Mech Syst Signal Process 23:1535–1547
Li CH, Kuo BC, Lin CT (2011) LDA-based clustering algorithm and its application to an unsupervised feature extraction. IEEE Trans Fuzzy Syst 19:152–163
Li CH, Ho HH, Liu YL et al (2012) An automatic method for selecting the parameter of the normalized kernel function to support vector machines. J Inf Sci Eng 28:1–15
Liu Z, Zuo MJ, Xu H (2011) A Gaussian radial basis function based feature selection algorithm. In: Proceedings of IEEE international conference on computational intelligence for measurement systems and applications. Ottawa, Canada, pp 53–56
Pudil P, Novovicová J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15:1119–1125
Qu J, Liu Z, Zuo MJ, Huang HZ (2011) Feature selection for damage degree classification of planetary gearboxes using support vector machine. Proc Inst Mech Eng C J Mech Eng Sci 225:2250–2264
Rafiee J, Arvani F, Harifi A, Sadeghi MH (2007) Intelligent condition monitoring of a gearbox using artificial neural network. Mech Syst Signal Process 21:1746–1754
Salton G, McGill MJ (1983) Introduction to modern information retrieval. McGraw-Hill Book Company, New York
Samuel PD, Pines DJ (2005) A review of vibration-based techniques for helicopter transmission diagnostics. J Sound Vib 282:475–508
Swansson NS (1980) Application of vibration signal analysis techniques to signal monitoring. In: Proceedings of conference on friction and wear in engineering. Institution of Engineers, Australia, pp 262–267
Vapnik VN (1995) The nature of statistical learning theory. Springer, London
Večeř P, Kreidl M, Šmíd R (2005) Condition indicators for gearbox condition monitoring systems. Acta Polytech 45:35–43
Wang Y, Xu X, Zhao H, Hua Z (2010) Semi-supervised learning based on nearest neighbor rule and cut edges. Knowl Based Syst 23:547–554
Wu B, Abbott T, Fishman D et al (2003) Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data. BioInformatics 19:1636–1643
Yang B-S, Kim KJ (2006) Application of Dempster–Shafer theory in fault diagnosis of induction motors using vibration and current signals. Mech Syst Signal Process 20:403–420
Yang P, Zhou B, Zhang Z et al (2010) A multi-filter enhanced genetic ensemble system for gene selection and sample classification of microarray data. BMC Bioinform 11(Suppl. 1):S5
Yang Y, Liao Y, Meng G, Lee J (2011) A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis. Expert Syst Appl 38:11311–11320
Yen CL, Lu MC, Chen JL (2013) Applying the self-organization feature map (SOM) algorithm to AE-based tool wear monitoring in micro-cutting. Mech Syst Signal Process 34:353–366
Yuan S, Chu F (2006) Support vector machines-based fault diagnosis for turbo-pump rotor. Mech Syst Signal Process 20:939–952
Zhang L, Wang C, Zhang X et al (2000) Fault diagnosis techniques and methods for machineries (in Chinese). Petroleum Industry Press, Beijing
Zhang K, Li Y, Scarf P, Ball A (2011) Feature selection for high-dimensional machinery fault diagnosis data using multiple models and radial basis function networks. Neurocomputing 74:2941–2952
Zhao X, Zuo MJ, Liu Z, Hoseini MR (2013) Diagnosis of artificially created surface damage levels of planet gear teeth using ordinal ranking. Measurement 46:132–144
Zhao X, Zuo MJ, Patel T (2010) EMD, ranking mutual information and PCA based condition monitoring. In: Proceedings of ASME 2010 international design engineering technical conferences. Montreal, Canada, pp 777–782
Acknowledgments
The project was supported by Open Research Fund (Grant No. HPCM-2013-05) of Key Laboratory of High Performance Complex Manufacturing, Central South University, the Natural Sciences and Engineering Research Council of Canada (NSERC) and the China Scholarship Council (CSC). The anonymous reviewers and editors are highly appreciated for their constructive comments and helpful suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, Z., Zhao, X., Zuo, M.J. et al. Feature selection for fault level diagnosis of planetary gearboxes. Adv Data Anal Classif 8, 377–401 (2014). https://doi.org/10.1007/s11634-014-0168-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11634-014-0168-4