Abstract
Incipient faults are difficult to be discovered because of their slight fault symptoms. By sufficiently exploiting the distribution information of incipient faults, this chapter presents the reason why incipient faults cannot be detected by the existing FDD methods. Under PCA framework, we propose a new data-driven FDD method, which is named probability-relevant PCA (PRPCA), for traction systems in high-speed trains. The salient strengths of the PRPCA-based FDD method are: (1) it can greatly improve the fault detectability; (2) it is suitable for non-Gaussian traction systems; (3) based on the improved fault detectability, it can achieve accurate fault diagnosis via support vector machine (SVM); (4) it can be easily applied to traction systems even if neither physical models or parameters nor expert knowledge of drive systems is given; and (5) it is of highly computational efficiency that can meet requirements on the real-time FDD. A set of experiments on platform 1 are carried out to demonstrate the effectiveness of the proposed method (Chen et al. (2018) IEEE Trans Ind Electron 66(6):4716–4725, [1]).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen H, Jiang B, Chen W, Yi H (2018) Data-driven detection and diagnosis of incipient faults in electrical drives of high-speed trains. IEEE Trans Ind Electron 66(6):4716–4725
Chen H, Jiang B (2019) A review of fault detection and diagnosis for the traction system in high-speed trains. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/TITS.2019.2897583
Baratter D, Arellano-Padilla J, Gerada C (2017) Incipient fault diagnosis in ultrareliable electrical machines. IEEE Trans Ind Appli 53(3):2906–2914
Chen H, Jiang B, Lu N, Mao Z (2017) Multi-mode kernel principal component analysis-based incipient fault detection for pulse width modulated inverter of China railway high-speed 5. Adv Mech Eng 9(10):1–12
Chen Z, Ding SX, Peng T, Yang C, Gui W (2018) Fault detection for non-gaussian processes using generalized canonical correlation analysis and randomized algorithms. IEEE Trans Ind Electron 65(2):1559–1567
Yang C, Yang C, Peng T, Yang X, Gui W (2017) A fault-injection strategy for traction drive control systems. IEEE Trans Ind Electron 64(7):5719–5727
Chen H, Jiang B, Lu N, Mao Z (2018) Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains. IEEE Trans Vehic Technol 67(6):4819–4830
Zhang S (2007) Fundamental application theory and engineering technology for railway high-speed trains. Science Press, Beijing, China
Chen J, Patten RJ (1999) Robust model-based fault diagnosis for dynamic systems. Kluwer Academic, Boston, MA, USA
Ding SX (2014) Data-driven design of fault diagnosis and fault-tolerant control systems. Springer, New York
Chen H, Jiang B, Ding SX, Lu N, Chen W (2019) Probability-relevant incipient fault detection and diagnosis methodology with applications to electric drive systems. IEEE Trans Control Syst Technol 27(6):2766–2773
Zhang Y, An J, Ma C (2013) Fault detection of non-Gaussian processes based on model migration. IEEE Trans Control Syst Technol 21(5):1517–1526
Parzen E (1962) On the estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076
Ji H, He X, Shang J, Zhou D (2017) Incipient fault detection with smoothing techniques in statistical process monitoring. Control Eng Pract 62:11–21
Li W, Yue HH, Valle-Cervantes S, Qin SJ (2000) Recursive PCA for adaptive process monitoring. J Process Control 10(5):471–486
Qin SJ (2012) Survey on data-driven industrial process monitoring and diagnosis. Annu Rev Control 36(2):220–234
Murphy KP (2012) Machine learning: a probabilistic perspective. MIT Press, Cambridge, MA
Ni J, Zhang C, Yang SX (2011) An adaptive approach based on KPCA and SVM for real-time fault diagnosis of HVCBs. IEEE Trans Power Del 26(3):1960–1971
Yin S, Ding SX, Xie X, Luo H (2014) A review on basic datadriven approaches for industrial process monitoring. IEEE Trans Ind Electron 61(11):6418–6428
Chen H, Jiang B, Lu N (2018) A multi-mode incipient sensor fault detection and diagnosis method for electrical traction systems. Int J Control Autom Syst 16(4):1783–1793
Chen H, Jiang B, Lu N (2018) An improved incipient fault detection method based on Kullback-Leibler divergence. ISA Trans 79:127–136
Finch JW, Giaouris D (2008) Controlled AC electrical drives. IEEE Trans Ind Electron 55(2):481–491
Hyvärinen A, Karhunen J, Oja E (2004) independent component analysis. Wiley, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Chen, H., Jiang, B., Lu, N., Chen, W. (2020). Probability-Relevant PCA-based FDD Methods. In: Data-driven Detection and Diagnosis of Faults in Traction Systems of High-speed Trains. Lecture Notes in Intelligent Transportation and Infrastructure. Springer, Cham. https://doi.org/10.1007/978-3-030-46263-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-46263-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46262-8
Online ISBN: 978-3-030-46263-5
eBook Packages: EngineeringEngineering (R0)