Fault Diagnosis for Rail Vehicle Suspension Systems Based on Fisher Discriminant Analysis

  • Xiukun Wei
  • Sheng Wu
  • Jianlong Ding
  • Limin Jia
  • Qu Sun
  • Minzhen Yuan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 288)


In this paper, fisher discriminant analysis (FDA) is used for fault isolation and diagnosis in rail vehicle suspension systems. The suspension systems are equipped with acceleration sensors in the corners of the car body and the two bogies. The faults considered are the lateral damper faults and the lateral spring faults in suspension systems. FDA provides an optimal projection space on the basis of the training data including the fault data and normal data to classify the test data. A vehicle model is built by SIMPACK/MATLAB software with real parameters to obtain the simulation data and the effectiveness of the proposed method is demonstrated by simulation.


Rail vehicle suspension systems Fault diagnosis Fisher discriminant analysis Fault isolation 



This work is partly supported by Chinese 863 program (Contract No. 2011AA110503-6) and Ph.D. Programs Foundation of Ministry of Education of China (grant number: 20110009120037).


  1. 1.
    Xiukun W, Limin J, Hai L (2012) Data-driven fault detection of vertical rail vehicle suspension systems. In: UKACC international conference on control, pp 589–594Google Scholar
  2. 2.
    Bruni S, Goodall R, Mei T, Tsunashima H (2007) Control and monitoring for railway vehicle dynamics. Veh Syst Dyn 45(7–8):765–771Google Scholar
  3. 3.
    Goodall R, Mei T (2006) Advanced control and monitoring for railway vehicle suspensions. In: International symposium on speed-up and service technology for railway and maglev systems (STECH’06), 1, Chengdu, China, pp 10–16Google Scholar
  4. 4.
    Goodall R, Roberts C (2006) Concepts and techniques for railway condition monitoring. In: IET international conference on railway condition monitoring, pp 90–95Google Scholar
  5. 5.
    Li P, Goodall R (2004) Model-based condition monitoring for railway vehicle systems. In: Control 2004, University of Bath, ID-058Google Scholar
  6. 6.
    Li P, Goodall R, Weston P, Ling CS, Goodman C, Roberts C (2006) Estimation of railway vehicle suspension parameters for condition monitoring. In: Control engineering practice, pp 43–55Google Scholar
  7. 7.
    Wei X, Liu H (2011) Fault diagnosis of rail vehicle suspension systems by using GLRT. In: Chinese control and decision conferenceGoogle Scholar
  8. 8.
    Xiukun W, Hai L, Yong Q (2011) Fault isolation of rail vehicle suspension systems by using similarity measure. In: International conference on intelligent railway transportation, pp 391–396Google Scholar
  9. 9.
    Yuting W, Yong Q, Xiukun W (2012) Track irregularities estimation based on acceleration measurements. In: 2012 international conference on measurement, information and control, pp 86–91Google Scholar
  10. 10.
    Duda RO, Hart PE, Stock DG (2001) Pattern classification, 2nd edn. Wiley, New YorkMATHGoogle Scholar
  11. 11.
    Zhao X, Huihe S (2006) On-line batch process monitoring and diagnosing based on fisher discriminant analysis. J Shanghai Jiaotong Univ (science) E-11(3):307–312Google Scholar
  12. 12.
    Chiang LH, Kotanchek ME, Kordon AK (2004) Fault diagnosis based on fisher discriminant analysis and support vector machines. Comput Chem Eng 28(2004):1389–1401Google Scholar
  13. 13.
    Fuente MJ, Garcia G, Sainz GI (2008) Fault diagnosis in a plant using fisher discriminant analysis. In: 16th mediterranean conference on control and automation congress centre, Ajaccio, France, June 25–27, 2008Google Scholar
  14. 14.
    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(2006):403–420CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.State Key Laboratory of Rail Traffic Control and SafetyBeijing Jiaotong UniversityBeijingChina
  2. 2.School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina
  3. 3.Guangzhou Metro CompanyGuangzhouChina

Personalised recommendations