Research on multi-sensors distributed fault diagnosis theory of locomotive electric system

被引：0

作者：

Li W. ^{[1
,2
]}

Chen T.-F. ^{[1
]}

Chen C.-Y. ^{[3
]}

Cheng S. ^{[1
]}

机构：

[1] School of Traffic and Transportation Engineering, Central South University

[2] CSR Zhuzhou Electric Locomotive Research Institute Company Limited

[3] School of Information Science and Engineering, Central South University

来源：

Tiedao Xuebao/Journal of the China Railway Society | 2010年 / 32卷 / 05期

关键词：

Electrical system; Fault diagnosis; Fault warning; Multi-sensors; Particle filtering; Train;

D O I：

10.3969/j.issn.1001-8360.2010.05.013

中图分类号：

学科分类号：

摘要：

This paper is mainly concerned with research of the multi-sensors distributed fault diagnosis theory for general electric systems of trains, in order to provide the relevant reference for more high-powered fault diagnosis and warning of train electric systems. The modern train electric systems comprise more and more sensors. The information of these sensors is gathered via various networks. To limit the quantity of data transferred in the networks, the local sensors send only binary decisions back to the fusion center. Also, a simple and efficient distributed fault detection algorithm based on state estimation via particle filtering is proposed. Experimental results show the superiority of the PF-based method. The system achieves good detection performance over a large range of possible correlations. For small correlation, a large number of sensors can help improve performance substantially. For large correlation, a relatively small number of sensors can achieve near optimal performance.

引用

页码：70 / 76

页数：6

共 18 条

[1]

Li W., Chen C.-L., Yang Y., Control and communication network of china star high speed train, Electric Drive for Locomotives, 5, pp. 78-82, (2003)

[2]

Doucet A., de Freitas N., Gordon N., Sequential Monte Carlo Methods in Practice, (2001)

[3]

Crisan D., Doucet A., A survey of convergence results on particle filtering methods for practitioners, IEEE Transaction on Signal Processing, 50, 3, pp. 736-746, (2002)

[4]

Andrieu A., Doucet A., Singh S., Et al., Particle methods for change detection, system identification and control, Proceedings of the IEEE, 92, 3, pp. 423-438, (2004)

[5]

Varshney P.K., Distributed Detection and Data Fusion, (1997)

[6]

Tsitsiklis J.N., Decentralized detection by a large number of sensors, Mathematics of Control, Signals, and Systems, pp. 167-182, (1988)

[7]

Chamberland J., Veeravalli V.V., Asymptotic results for detection in power constrained wireless sensor networks, Processing IEEE International Symposium Information Theory(ISIT2003), (2003)

[8]

Chamberland J., Veeravalli V.V., The impact of fading on decentralized detection in power constrained wireless sensor networks, Proc. IEEE Intl. Conf. Acoust. Speech, Sig. Proc. (ICASSP2004), (2004)

[9]

Tsitsiklis J.N., On Threshold rules in decentralized detection, Proc. 25th IEEE Conf. Decision and Control, pp. 232-236, (1986)

[10]

Li W., Microcomputer control and network system of KZ4A AC drive locomotive, Journal of Electic Drive of Locomotive, 3, pp. 8-12, (2007)

← 1 2 →