×

Modeling of the safe region based on support vector data description for health assessment of wheelset bearings. (English) Zbl 1481.90327

Summary: This paper presents a modeling method, an optimization method, and two applications for the safe region concept that has been developed for the health assessment of wheelset bearings of high-speed trains. The proposed safe region model uses support vector data description to handle cases in high-speed trains where only normal data are available. The optimization process is designed with a strong physical interpretation of the relationship between the kernel parameter and the model performance. A new indicator derived from the safe region model is proposed for degradation evaluation throughout the whole life cycle. Experimental data on wheelset bearings with naturally generated faults are used to demonstrate that the proposed approach has competitive advantages in several performance aspects for anomaly detection and provides monotonic labels in assessment of increasing degradation levels.

MSC:

90C90 Applications of mathematical programming
90B25 Reliability, availability, maintenance, inspection in operations research
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Yang, J. W.; Yao, D. C.; Cai, G. Q.; Liu, H. B.; Zhang, J., A method of bearing fault feature extraction based on improved wavelet packet and Hilbert analysis, Mod. Manufact. Eng., 4, 4, 127-139 (2012)
[2] Singh, S.; Köpke, U. G.; Howard, C. Q.; Petersen, D., Analyses of contact forces and vibration response for a defective rolling element bearing using an explicit dynamics finite element model, J. Sound Vib., 333, 21, 5356-5377 (2014)
[3] Zhang, Y.; Qin, Y.; Xing, Z.; Jia, L.; Cheng, X., Roller bearing safety region estimation and state identification based on LMD-PCA-LSSVM, Measurement, 46, 3, 1315-1324 (2013)
[4] Antoni, J., Cyclic spectral analysis of rolling-element bearing signals: facts and fictions, J. Sound Vib., 304, 3, 497-529 (2007)
[5] Wu, F.; Kumagai, S., Steady-state security regions of power systems, IEEE Trans. Circ. Syst., 29, 11, 703-711 (1982) · Zbl 0527.90039
[6] Qin, Y.; Shi, J.; Zhang, Y.; Zhu, S.; Jia, L., Online security assessment of rail vehicles in service status based on safety region estimation, J. Centr. South Univ. Sci. Technol., 44, S1, 195-200 (2013)
[7] Konar, P.; Chattopadhyay, P., Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs), Appl. Soft Comput., 11, 6, 4203-4211 (2011)
[8] Liu, Z.; Cao, H.; Chen, X.; He, Z.; Shen, Z., Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings, Neurocomputing, 99, 399-410 (2013)
[9] Zhang, X.; Liang, Y.; Zhou, J.; Zang, Y., A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM, Measurement, 69, 164-179 (2015)
[10] Cerrada, M.; Sánchez, R.; Li, C.; Pacheco, F.; Cabrera, D.; Valente De Oliveira, J.; Vásquez, R. E., A review on data-driven fault severity assessment in rolling bearings, Mech. Syst. Signal Process., 99, 169-196 (2018)
[11] Tax, D. M.; Duin, R. P., Support vector data description, Mach. Learn., 54, 1, 45-66 (2004) · Zbl 1078.68728
[12] Vapnik, V. N., The Nature of Statistical Learning Theory (2000), Springer: Springer New York · Zbl 0934.62009
[13] Khatkhate, A. M.; Ray, A.; Keller, E., Modelling and system identification of an experimental apparatus for anomaly detection in mechanical systems, Appl. Math. Model., 31, 4, 734-748 (2007) · Zbl 1420.62510
[14] Pan, M. Q.; Qian, S. X.; Lei, L. Y.; Zhou, X. J., Support vector data description with model selection for condition monitoring, (Proceedings of the International Conference on Machine Learning and Cybernetics. Proceedings of the International Conference on Machine Learning and Cybernetics, Guangzhou, China (2005)), 4315-4318
[15] Li, G.; Hu, Y.; Chen, H.; Li, H.; Hu, M.; Guo, Y.; Shi, S.; Hu, W., A sensor fault detection and diagnosis strategy for screw chiller cystem using support vector data description-based D-statistic and DV-contribution plots, Energy Build., 133, 230-245 (2016)
[16] Zhao, Y.; Wang, S.; Xiao, F., Pattern recognition-based chillers fault detection method using Support Vector Data Description (SVDD), Appl. Energy, 112, 1041-1048 (2013)
[17] Luo, H.; Jiang Cui, Y. W., A SVDD approach of fuzzy classification for analog circuit fault diagnosis with FWT as preprocessor, Expert Syst. Appl., 38, 8, 10554-10561 (2011)
[18] Wang, D.; Tse, P. W.; Guo, W.; Miao, Q., Support vector data description for fusion of multiple health indicators for enhancing gearbox fault diagnosis and prognosis, Measur. Sci. Technol., 22, 2, Article 025102 pp. (2011)
[19] Wang, H.; Chen, J., Performance degradation assessment of rolling bearing based on bispectrum and support vector data description, J. Vib. Control, 20, 13, 2032-2041 (2013)
[20] Pan, Y.; Chen, J.; Guo, L., Robust bearing performance degradation assessment method based on improved wavelet packet-support vector data description, Mech. Syst. Signal Process., 23, 3, 669-681 (2009)
[21] Zhao, X.; Qin, Y.; Wang, D.; Wang, Z.; Jia, L., Research on performance degradation assessment method of train rolling bearings under incomplete data, (Proceedings of the International Conference on Distributed Multimedia Systems. Proceedings of the International Conference on Distributed Multimedia Systems, Wuhan, China (2016)), 184-189
[22] Zhu, X.; Zhang, Y.; Zhu, Y., Bearing performance degradation assessment based on the rough support vector data description, Mech. Syst. Signal Process., 34, 1-2, 203-217 (2013)
[23] Wang, Y.; Kang, S.; Jiang, Y.; Yang, G.; Song, L.; Mikulovich, V. I., Classification of fault location and the degree of performance degradation of a rolling bearing based on an improved hyper-sphere-structured multi-class support vector machine, Mech. Syst. Signal Process., 29, 404-414 (2012)
[24] Wang, W.; Xu, Z.; Lu, W.; Zhang, X., Determination of the spread parameter in the Gaussian kernel for classification and regression, Neurocomputing, 55, 3, 643-663 (2003)
[25] Xu, Z.; Dai, M.; Meng, D., Fast and efficient strategies for model selection of Gaussian support vector machine, IEEE Trans. Syst. Man Cybern. Part B Cybern., 39, 5, 1292-1307 (2009)
[26] Evangelista, P. F.; Embrechts, M. J.; Szymanski, B. K., Some properties of the Gaussian kernel for one class learning, (Proceedings of the International Conference on Artificial Neural Networks. Proceedings of the International Conference on Artificial Neural Networks, Porto, Portugal (2007), Springer), 269-278
[27] Khazai, S.; Homayouni, S.; Safari, A.; Mojaradi, B., Anomaly detection in hyperspectral images based on an adaptive support vector method, IEEE Geosci. Remote Sens. Lett., 8, 4, 646-650 (2011)
[28] Wang, H.; Zhang, L.; Xiao, Y.; Xu, W., An approach to choosing Gaussian kernel parameter for one-class SVMS via tightness detecting, (Proceedings of the Forth International Conference on Intelligent Human-Machine Systems and Cybernetics. Proceedings of the Forth International Conference on Intelligent Human-Machine Systems and Cybernetics, Nanchang, China (2012), IEEE), 318-323
[29] Theissler, A.; Dear, I., Autonomously determining the parameters for SVDD with RBF kernel from a one-class training set, Int. J. Comput. Electric. Autom. Control Inf. Eng., 7, 7, 949-957 (2013)
[30] Tax, D.; Ypma, A.; Duin, R., Support vector data description applied to machine vibration analysis, (Proceeding of Fifth Annual Conference of the Advanced School for Computing and Imaging. Proceeding of Fifth Annual Conference of the Advanced School for Computing and Imaging, Heijen, The Netherlands (1999)), 15-23
[31] Tax, D. M.; Duin, R. P., Data domain description using support vectors, (Proceedings of the European Symposium on Artificial Neural Networks. Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium (1999)), 251-256
[32] E. Pekalska, B. Duin, PRTools, http://37steps.com/prtools/data-mapping/generation/; E. Pekalska, B. Duin, PRTools, http://37steps.com/prtools/data-mapping/generation/
[33] Antoni, J., The infogram: entropic evidence of the signature of repetitive transients, Mech. Syst. Signal Process., 74, 73-94 (2016)
[34] Lei, Y.; Jia, F.; Lin, J.; Xing, S.; Ding, S. X., An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data, IEEE Trans. Indust. Electron., 5, 63, 3137-3147 (2016)
[35] Mezura-Montes, E.; Coello, C. A.C., Constraint-handling in nature-inspired numerical optimization: past, present and future, Swarm Evolut. Comput., 1, 4, 173-194 (2011)
[36] Liu, Z.; Zuo, M. J.; Zhao, X.; Xu, H., An analytical approach to fast parameter selection of Gaussian RBF kernel for support vector machine, J. Inf. Sci. Eng., 31, 2, 691-710 (2015)
[37] Zhao, X.; Zuo, M. J.; Liu, Z.; Hoseini, M. R., Diagnosis of artificially created surface damage levels of planet gear teeth using ordinal ranking, Measurement, 46, 1, 132-144 (2013)
[38] Kendall, M. G., A new measure of rank correlation, Biometrika, 30, 1/2, 81-93 (1938) · Zbl 0019.13001
[39] Liu, Z.; Zuo, M. J.; Xu, H., Fault level diagnosis for planetary gearboxes using hybrid kernel feature selection and kernel Fisher discriminant analysis, Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., 227, 9, 2064-2076 (2012)
[40] N. Li; Y. Lei; J. Lin; S. X. Ding, An improved exponential model for predicting remaining useful life of rolling element bearings, IEEE Trans. Indust. Electron., 62, 12, 7762-7773 (2015)
[41] S. Kang; D. Ma; Y. Wang; C. Lan; Q. Chen; V. I. Mikulovich, Method of assessing the state of a rolling bearing based on the relative compensation distance of multiple-domain features and locally linear embedding, Mech. Syst. Signal Process., 86, Part A, 40-57 (2017)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.