Fault Diagnosis for Induction Machines Using Kernel Principal Component Analysis

  • Jang-Hwan Park
  • Dae-Jong Lee
  • Myung-Geun Chun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


For the fault diagnosis of three-phase induction motors, we set up an experimental unit and then develop a diagnosis algorithm based on pattern recognition. The experimental unit consists of induction motor drive and data acquisition module to obtain the fault signals. As the first step for diagnosis procedure, preprocessing is performed to make the acquired current simplified and normalized. To simplify the input data, three-phase currents are transformed into the magnitude of Concordia vector. As the next step, feature extraction is performed by kernel PCA. Finally, we used the linear classifier based on two types of distance measures. To show the effectiveness, the proposed fault diagnostic system has been intensively tested with the various data acquired under the different electrical and mechanical faults with varying load.


Fault Diagnosis Induction Motor Mechanical Fault Kernel Principal Component Analysis Induction Machine 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Thomson, W.T., Fenger, M.: Current Signature Analysis to Detect Induction Motor Faults. IEEE Ind. Applications Magazine, 26–34 (2001)Google Scholar
  2. 2.
    Nejjari, H., Benbouzid, M.H.: Monitoring and Diagnosis of Induction Motors Electrical Faults Using a Current Park’s Vector Pattern Learning Approach. IEEE Trans. Ind. Application 36, 730–735 (2000)CrossRefGoogle Scholar
  3. 3.
    Zidani, F.: Induction Motor Stator Faults Diagnosis by a Current Concordia Pattern-Based Fuzzy Decision System. IEEE Trans. Energy Conversion 18, 469–475 (2004)CrossRefGoogle Scholar
  4. 4.
    Peter, V.: Artificial Intelligence Based Electrical Machines and Drives. Oxford Sci. Pub. (1999)Google Scholar
  5. 5.
    Lee, D.J., Park, J., Kim, D.H., Chun, M.G.: Fault Diagnosis of Induction Motor Using Linear Discriminant Analysis. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS (LNAI), vol. 3684, pp. 860–865. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Bezdec, J.: Pattern Recognition with Function Algorithms. Plenum Press, New York (1981)Google Scholar
  7. 7.
    Scholkopf, B., Smola, A.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10, 1299–1319 (1998)CrossRefGoogle Scholar
  8. 8.
    Richard, O.D., et al.: Pattern Classification. John Wiley & Sons, Chichester (2002)Google Scholar
  9. 9.
    Wu, S., Chow, T.: Induction Machine Fault Detection using SOM-based RBF Neural Network. IEEE Trans. Ind. Electron 51, 183–194 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jang-Hwan Park
    • 1
  • Dae-Jong Lee
    • 2
  • Myung-Geun Chun
    • 2
  1. 1.Information & Control EngineeringChungju National UniversityChungjuKorea
  2. 2.Dept. of Electrical and Computer EngineeringChungbuk National UniversityKorea

Personalised recommendations