Engine Fault Diagnosis using DTW, MFCC and FFT

  • Vrijendra Singh
  • Narendra Meena


Abstract. In this paper we have used a combination of three algorithms: Dynamic time warping (DTW) and the coefficients of Mel frequency Cepstrum (MFC) and Fast Fourier Transformation (FFT) for classifying various engine faults. Dynamic time warping and MFCC (Mel Frequency Cepstral Coefficients), FFT are used usually for automatic speech recognition purposes. This paper introduces DTW algorithm and the coefficients extracted from Mel Frequency Cepstrum, FFT for automatic fault detection and identification (FDI) of internal combustion engines for the first time. The objective of the current work was to develop a new intelligent system that should be able to predict the possible fault in a running engine at different-different workshops. We are doing this first time. Basically we took different-different samples of Engine fault and applied these algorithms, extracted features from it and used Fuzzy Rule Base approach for fault Classification.


Fast Fourier Transformation Dynamic Time Warping Cylinder Head Fault Classification Valve Stem 
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.
    J.C.C., Castejn O.: Incipient bearing fault diagnosis using DWT for feature extraction, World Congress, Besanon (France).Google Scholar
  2. 2.
    Ja Choi, Jong Myoung Ko, Chang Ouk Kim, Yoon Seong Kang, Seung Jun Lee.: Dynamic Time Warping Algorithms for Run-by-Run Process Fault Detection, ISSM Paper: PC-P-101Google Scholar
  3. 3.
    Fulufhelo V., Tshilidzi M., Unathi M.: Early classification of bearing faults using Hidden Markov Models, International Journal of Innovative Computing, Information and Control.Google Scholar
  4. 4.
    Wen-Xian Y.: Diagnosing the engine value faults by genetic programming, Journal of Sound and Vibration Volume 293, Issues 1–2. 5. http://www.motorera.com/dictionaryGoogle Scholar
  5. 6.
    Ren Y., Hu Tianyou, Yang P., Liu X., Approach to disel engine fault diagnosis, Mechatronics and Automation, 2005 IEEE International Conference 3, 1451–1454 (2005)Google Scholar
  6. 7.
    Ren Y., Hu Tianyou; Yang P. Liu X.: Approach to diesel engine faultdiagnosis, Mechatronics and Automation, IEEE International Conference Volume 3, 1451–1454 (2005)Google Scholar
  7. 8.
    Shiyuan L., Fengshou G., Ball A.: Detection of engine valve faults by vibration signals measured on the cylinder head, Journal of Automobile Engineering.Google Scholar
  8. 9.
    Kobayashi K.; Uchikawa, Y.; Simizu, T.; Nakai, K.; Yoshizawa, M.: The rejection of magnetic noise from the wire using ICA for magneto cardiogram, Magnetics, IEEE Transactions 41(10), 4152–4154 (2005)Google Scholar
  9. 10.
    Ciaramella, E.; Giorgi, L.; Dapos; Errico, A.; Cavaliere, F.; Gaimari, G.; Prati, G. “Technique for setting the power preemphasis in WDM optical systems”, Journal of Light wave Technology, 24(1), 342–356 (2006)CrossRefGoogle Scholar
  10. 11.
    Srinivasam R., Ming S.: Online fault diagnosis and state identification, Chemical engineering scienceGoogle Scholar
  11. 12.
    Sherlock B. G. and Kakad Y. P.: Transform domain technique for windowing the DCT and DST, Journal of the Franklin Institute 339(1), 111–120 (2002)MATHCrossRefGoogle Scholar
  12. 13.
    Duan C., He Zhengjia, and Jiang H.: A sliding window feature extraction method for rotating machine based the lifting scheme, Journal of Sound and Vibration Volume 229, Issues 4–5Google Scholar

Copyright information

© Indian Institute of Information Technology, India 2009

Authors and Affiliations

  • Vrijendra Singh
    • 1
  • Narendra Meena
    • 1
  1. 1.Indian Institute of Information TechnologyAllahabadIndia

Personalised recommendations