Advertisement

The Valve Electric Actuator’s Fault Diagnosis Method Based on Principle Component Analysis and Support Vector Machines

  • Yue You-jun
  • Wang Hong-jun
  • Zong Qun
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 162)

Abstract

This paper, the mechanism of valve electric actuator failures is analyzed, and the fault diagnosis method based on principle component analysis (PCA) and support vector machines (SVM) is put forward. In order to reduce the dimension of feature signals, the fault diagnosis method uses PCA to extract fault feature signals. And a multi-class Support Vector Machine classifier is constructed to develop the model of failure diagnosis. The model can identify and detect the actuator’s constant gain fault, the constant deviation fault and the dead zone fault. The simulation experiment result verified its feasibility and validity.

Keywords

Support Vector Machine Fault Diagnosis Principle Component Analysis Support Vector Machine Model Electric Actuator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shang, Q.-L., Sun, L., Wu, H.-Y.: Model-based actuator fault diagnosis. Zhejiang Daxue Xuebao (Gongxue Ban) 41(10), 1660–1663 (2007)Google Scholar
  2. 2.
    Tudoroiu, N., Zaheeruddin, M.: Fault detection and diagnosis of valve actuators in HVAC systems. In: 2005 IEEE International Conference on Control Applications, pp. 1281–1286 (2005)Google Scholar
  3. 3.
    Tudoroiu, N., Zaheeruddin, M.: Fault detection and diagnosis of valve actuators in discharge air temperature (DAT) systems, using interactive Unscented Kalman Filter estimation. In: IEEE International Symposium on Industrial Electronics, vol. 4, pp. 2665–2670 (2006)Google Scholar
  4. 4.
    Patan, K.: Fault detection of the actuators using neural networks. In: Proceedings of the 7th IEEE International Conference on Methods and Models in Automation and Robotics, Porland (2001)Google Scholar
  5. 5.
    Witczak, M., Korbicz, J., Mrugalski, M., Patton, R.J.: A GMDH neural network-based approach to robust fault diagnosis: Application to the DAMADICS benchmark problem. Control Engineering Practice 14(6), 671–683 (2006)CrossRefGoogle Scholar
  6. 6.
    Witczak, M.: Advances in model-based fault diagnosis with evolutionary algorithms and neural networks. International Journal of Applied Mathematics and Computer Science 16(1), 85–99 (2006)MathSciNetGoogle Scholar
  7. 7.
    Uppal, F.J., Patton, R.J.: Neuro-fuzzy uncertainty de-coupling: A multiple-model paradigm for fault detection and isolation. International Journal of Adaptive Control and Signal Processing 19(4), 281–304 (2005)MathSciNetzbMATHCrossRefGoogle Scholar
  8. 8.
    Lv, F., Du, H.-L., Yang, J.-H., Wang, Z.-F.: The Electric Actuator’s Fault Diagnosis Based on Information Fusion. In: 2007 International Conference on Machine Learning and Cybernetics, vol. 2, pp. 1055–1060 (2007)Google Scholar
  9. 9.
    Ma, P., Zhang, J., Wang, Y.-M.: A New Method for Diagnosing Constant Gain Failures of Electric Actuator. Power System Technology 32(1), 97–100 (2008)Google Scholar
  10. 10.
    Ma, P., Zhu, Y.-F., Niu, Z.: Main Stream Temperature Control System Based on Neural Network. Journal of North China Electric Power University 28(2), 52–55 (2001)Google Scholar
  11. 11.
    Ye, S.F.: The Application and Consideration about Principal Component Analysis. Application of Statistics and Management 20(2), 52–55, 61 (2004)Google Scholar
  12. 12.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)zbMATHGoogle Scholar
  13. 13.
    Cristianini, N., Taylor, J.S.: An Intrduction to Support Vector Machines and other kernel based learnig methods. China Machine Press (July 2005)Google Scholar
  14. 14.
    Hsu, C.-W., Liu, C.-J.: A Comparison of Methods for Multiclass Support Vector Machines. IEEE Transactions on Neural Networks 13(2), 415–425 (2002)CrossRefGoogle Scholar
  15. 15.
    Duan, K., Keerthi, S.S.: Which is the Best Multi-class SVM Method? An Empirical Study. In: 6th International Workshop on Multiple Classifier Systems. MCS, Seaside (2005)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • Yue You-jun
    • 1
    • 2
  • Wang Hong-jun
    • 2
  • Zong Qun
    • 1
  1. 1.School of Electrical Engineering and AutomationTianjin UniversityTianjinChina
  2. 2.Key Laboratory of Tianjin Complex Industrial Control Theory and ApplicationTianjin University of TechnologyTianjinChina

Personalised recommendations