Advertisement

International Journal of Automotive Technology

, Volume 20, Issue 5, pp 961–970 | Cite as

Model-based Sensor Fault Diagnosis of Vehicle Suspensions with a Support Vector Machine

  • Kicheol Jeong
  • Seibum ChoiEmail author
Article
  • 13 Downloads

Abstract

In this paper, a means of generating residuals based on a quarter-car model and evaluating them using a support vector machine (SVM) is proposed. The proposed model-based residual generator shows very robust performance regardless of unknown road surface conditions. In addition, an SVM classifier without empirically set thresholds is used to evaluate the residuals. The proposed method is expected to reduce the effort required to design fault diagnosis algorithms. While an unknown input observer is used to generate the residual, the relative velocity of the vehicle suspension is obtained additionally. The proposed algorithm is verified using commercial vehicle simulator Carsim with Matlab & Simulink. As a result, the fault diagnosis algorithm proposed in this paper can detect sensor faults that cannot be detected by a limit checking method and can reduce the effort required when designing algorithms.

Key words

Fault diagnosis Support vector machine Vehicle suspension Unknown input observer 

Nomenclature

ms, mu

sprung/unsprung mass, kg

ks, kt

spring/tire stiffness, N/m

cn

nominal damping coefficient, Ns/m

csky

sky-hook damping coefficient, Ns/m

β

damper bandwidth, -

zs, zu

sprung/unsprung mass position, m

zr

unknown road input, m

vs, vu

sprung/unsprung mass vertical velocity, m/s

f(x)

hyperplane of support vector machine, -

w

normal vector of hyperplane, -

r

geometrical distance, -

α

Lagrangian multiplier, -

K(xi, xj)

kernel function, -

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgement

This work was supported by the Technology Innovation Program (or Industrial Strategic Technology Development Program (10084619, Development of a Vehicle Shock Absorber (Damper) and Engine Mount using MR Fluid with a Yield Strength of 60kPa) funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea).

References

  1. Börner, M., Straky, H., Weispfenning, T. and Isermann, R. (2002). Model based fault detection of vehicle suspension and hydraulic brake systems. Mechatronics 12, 8, 999–1010.CrossRefGoogle Scholar
  2. Butsuen, T. (1989). The Design of Semi-active Suspensions for Automotive Vehicles. Ph. D. Dissertation. Massachusetts Institute of Technology. Massachusetts, USA.Google Scholar
  3. Chamseddine, A. and Noura, H. (2008). Control and sensor fault tolerance of vehicle active suspension. IEEE Trans. Control Systems Technology 16, 3, 416–433.CrossRefGoogle Scholar
  4. Cristianini, N. and Shawe-Taylor, J. (2000). An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press. Cambridge, UKCrossRefzbMATHGoogle Scholar
  5. Ding, S. X. (2008). Model-based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools. Springer-Verlag London. London, UK.Google Scholar
  6. Gao, Z., Cecati, C. and Ding, S. X. (2015). A survey of fault diagnosis and fault-tolerant techniques-XPart II: Fault diagnosis with knowledge-based and hybrid/active approaches. IEEE Trans. Industrial Electronics 62, 6, 3768–3774.Google Scholar
  7. Gertler, J. (2013). Fault Detection and Diagnosis. Springer. GermanyGoogle Scholar
  8. Joo, D. S., Al-Holou, N., Weaver, J. M., Lahdhiri, T. and Al-Abbas, F. (2000). Nonlinear modeling of vehicle suspension system. Proc. IEEE American Control Conf., Chicago, Illinois, USA.Google Scholar
  9. Kim, W., Lee, J., Yoon, S. and Kim, D. (2005). Development of mando’s new continuously controlled semi-active suspension system. SAE Paper No. 2005-01- 1721.Google Scholar
  10. Kinnaert, M. (1999). Robust fault detection based on observers for bilinear systems. Automatica 35, 11, 1829–1842.MathSciNetCrossRefzbMATHGoogle Scholar
  11. Liang, J. and Du, R. (2007). Model-based fault detection and diagnosis of HVAC systems using support vector machine method. Int. J. Refrigeration 30, 6, 1104–1114.CrossRefGoogle Scholar
  12. Rajamani, R. (2011). Vehicle Dynamics and Control. Springer. Germany.zbMATHGoogle Scholar
  13. Roh, H.-S. and Park, Y. (1998). Preview control of active vehicle suspensions based on a state and input estimator. SAE Paper No. 981121.Google Scholar
  14. Savaresi, S. M. and Spelta, C. (2009). A single-sensor control strategy for semi-active suspensions. IEEE Trans. Control Systems Technology 17, 1, 143–152.CrossRefGoogle Scholar
  15. Savaresi, S. M., Silani, E. and Bittanti, S. (2005). Acceleration-Driven-Damper (ADD): An optimal control algorithm for comfort-oriented semiactive suspensions. J. Dynamic Systems, Measurement, and Control 127, 2, 218–229.CrossRefGoogle Scholar
  16. Szászi, I., Gáspár, P. and Bokor, J. (2002). Nonlinear active suspension modelling using linear parameter varying approach. Proc. 10th Mediterranean Conf. Control and Automation, Lisboa, Portugal.Google Scholar
  17. Vapnik, V. (2013). The Nature of Statistical Learning Theory. Springer-Verlag New York. New York, USA.zbMATHGoogle Scholar
  18. Varrier, S., Morales-Menendez, R., Lozoya-Santos, J. D.-J., Hernandez, D., Molina, J. M. and Koenig, D. (2013). Fault detection in automotive semi-active suspension: Experimental results. SAE Paper No. 2013-01-1234.Google Scholar
  19. Widodo, A. and Yang, B.-S. (2007). Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing 21, 6, 2560–2574.CrossRefGoogle Scholar
  20. Zasadzinski, M., Magarotto, E., Rafaralahy, H. and Ali, H. S. (2003). Residual generator design for singular bilinear systems subjected to unmeasurable disturbances: An LMI approach. Automatica 39, 4, 703–713.MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© KSAE 2019

Authors and Affiliations

  1. 1.School of Mechanical, Aerospace & System EngineeringKAISTDaejeonKorea

Personalised recommendations