International Journal of Automotive Technology

The Korean Society of Automotive Engineers (한국자동차공학회)
권호 표지

KOHONEN NETWORK BASED FAULT DIAGNOSIS AND CONDITION MONITORING OF PRE-ENGAGED STARTER MOTORS

  • BAY O. F. (Department of Electronics and Computer Education, Gazi University) ;
  • BAYIR R. (Department of Electronics and Computer Education, Gazi University)
  • Published : 2005.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, fault diagnosis and monitoring of serial wound pre-engaged starter motors have been carried out. Starter motors are DC motors that enable internal combustion engine (ICE) to run. In case of breakdown of a starter motor, internal combustion engine can not be worked. Starter motors have vital importance on internal combustion engines. Kohonen network based fault diagnosis system is proposed for fault diagnosis and monitoring of starter motors. A graphical user interface (GUI) software has been developed by using Visual Basic 6.0 for fault diagnosis. Six faults, seen in starter motors, have been diagnosed successfully by using the developed fault diagnosis system. GUI software makes it possible to diagnose the faults in starter motors before they occur by keeping fault records of past occurrences.

Keywords

References

  1. Bolenz, K. (1995).Automotive Electric/Electronic Systems. Robert Bosch GmbH. Stuttgart. Germany. 346-375
  2. Chow, M. Y. (1997). Methodologies of Using Neural Network and Fuzzy Logic Technologies for Motor Incipient Fault Detection. World Scientific Pub. Singapore
  3. Chowdhury, B. H. and Kunyu, W. (1996). Fault classification using Kohonen feature mapping. Intelligent Systems Applications to Power Systems.Proc. ISAP '96., Int. Conference on, 194-198
  4. Denton, T. (2000). Automobile Electrical and Electronic System. 2nd Ed.. Arnold Pub. Printed in Great Britain. 134-152
  5. Fausett, L. (1994). Fundametals of Neural Networks, Prentice-Hall, Inc.. USA
  6. Fuessel, D. and Isermann, R. (2000). Hierarchical Motor Diagnosis Utilizing Structural Knowledge and a Self-Learning Neuro-Fuzzy Scheme. IEEE Trans. Ind. Elec. 47, 5, 1070-1077 https://doi.org/10.1109/41.873215
  7. Gao, X. Z. and Ovazska, S. J. (2001). Soft Computing Methods in Motor Fault Diagnosis. Applied Soft Comp., 1, 73-81 https://doi.org/10.1016/S1568-4946(01)00008-4
  8. Hajiaghajani, M., Toliyat, H. A. and Panahi, I. M. S. (2004). Advanced fault diagnosis of a DC motor. IEEE Trans. Energy Conv. 19, 1, 60-65 https://doi.org/10.1109/TEC.2003.819101
  9. Harris, T. (1993). A Kohonen S.O.M. based, machine health monitoring system which enables diagnosis of faults not seen in the training set.Neural Networks, IJCNN '93-Nagoya. Proc. 1993 Int. Joint Conf., 1, 947-950 https://doi.org/10.1109/IJCNN.1993.714067
  10. Haykin, S. (1999). Neural Networks: a Comprehensive Foundation. Prentice-Hall, Inc.. USA
  11. Hoffman, A. J. and van der Merwe, N. T. (2002). The application of neural networks to vibrational diagnostics for multiple fault conditions. Computer Standards & Interfaces 24, 2, 139-149 https://doi.org/10.1016/S0920-5489(02)00014-4
  12. Jiang, H. and Penman, J. (1993). Using Kohonen feature maps to monitor the condition of synchronous generators. Neural Network App. Tools, 89-94
  13. Kohonen, T., Oja, E., Simula, O., Visa, A. and Kangas, J. (1996). Engineering applications of the self-organizing map. Proc. IEEE 84, 10, 1358-1384 https://doi.org/10.1109/5.537105
  14. Kohonen, T. (2001). Self-Organizing Map.Springer Verlag; 3th Ed.. Berlin.Germany
  15. Kowalski, C.T. and Orlowska-Kowalska, T. (2003). Neural networks application for induction motor faults diagnosis. Mathematics and Computers in Simulation 63,3-5, 435-448
  16. Leonhardt, S. and Ayoubi, M. (1997). Methods of fault diagnosis. Control Eng. Practice 5, 5, 683-692 https://doi.org/10.1016/S0967-0661(97)00050-6
  17. Lippmann, R.P. (1987). An introduction to computing with neural nets. IEEE ASSP Magazine, 4-22
  18. Liu, X.Q., Zhang, H.Y., Liu, J. and Yang, J. (2000). Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network.IEEE Trans.Industrial Electronics 47, 5, 1021-1030 https://doi.org/10.1109/41.873210
  19. Moseler, O.and Isennann, R.(2000). Application of model-based fault detection to a brushless DC motor.IEEE Trans.Ind.Elect.47, 5, 1015-1020 https://doi.org/10.1109/41.873209
  20. Murray, A. and Penman, J. (1997). Extracting useful .higher order features for condition monitoring using artificial neural Networks. IEEE Trans. Signal Processing 45, 11, 2821-2828 https://doi.org/10.1109/78.650108
  21. Penman, J. and Yin, C.M. (1994).Feasibility of using unsupervised learning, artificial neural networks for the condition monitoring of electrical machines. Electric Power Applications. lEE Proc. 141, 6, 317-322 https://doi.org/10.1049/ip-epa:19941263
  22. Subhasis, N.and Toliyat, H.A. (1999). Condition monitoring and fault diagnosis of electrical machines - a Review. in Proc. Industry App. Conf 34th IAS Annual Meeting, 1, 197-204
  23. Tanaka, M., Sakawa, M., Shiromaru, I. and Matsumoto, T. (1995). Application of Kohonen's self-organizing network to the diagnosis system for rotating machinery. Man and Cyber., Intelligent Sys. 21st Century, IEEE Int. Conf, 5, 4039-4044 https://doi.org/10.1109/ICSMC.1995.538422
  24. Vas, P. (1993). Parameter Estimation, Condition Monitoring and Diagnosis of Electrical Machines. New York. Clarendon Press. Oxford
  25. Vas, P. (1999). Artificial- Intelligence - Based Electrical Machines and Drives.Oxford University Press.New York
  26. Yang, B.S., Han, T. and An, J.L. (2004). Art-Kohonen neural network for fault diagnosis of rotating machinery. Mechanical System and Signal Processing 18, 3, 645-657 https://doi.org/10.1016/S0888-3270(03)00073-6