Feature Extraction

  • Nishchal K. VermaEmail author
  • Al Salour
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 256)


As detailed in Chap.  3, pre-processing of data improves the quality of data. Now, this chapter proceeds towards the next step of fault diagnosis framework where key characteristics of the data are found. For this purpose, data is analyzed in different domains and thus we obtain a new set of data which we call that good features are obtained. This chapter details how features can be extracted out from the pre-processed data. When the input data to an algorithm is too large to be processed and it is suspected to be redundant (much data but not much information), then the input data will be transformed into a reduced set of features (also named features vector). Transforming the input data into the set of features is called feature extraction. In order to extract useful information from the captured data, it is necessary to represent the data in a suitable form. Generally, for feature extraction purpose, three forms of signal representation as below are utilized.
  • Time domain

  • Frequency domain

  • Time–frequency/wavelet domain


  1. 1.
    Khorshidtalab, A., Salami, M.J.E., Hamedi, M.: Evaluating the effectiveness of time-domain features for motor imagery movements using SVM. In: IEEE International Conference on Computer and Communication Engineering, pp. 909–913 (2012)Google Scholar
  2. 2.
    He, Q., Kong, F., Yan, R.: Subspace-based gearbox condition monitoring by kernel principal component analysis. Int. J. Mech. Syst. Sig. Process. 21(4), 1755–1772 (2007)CrossRefGoogle Scholar
  3. 3.
    Verma, N.K., Gupta, V.K., Sharma, M., Sevakula, R.K.: Intelligent condition based monitoring of rotating machines using sparse auto-encoders. In: IEEE Conference on Prognostics and Health Management, pp. 1–7 (2013)Google Scholar
  4. 4.
    Daubechies, I.: Ten lectures on wavelets. In: SIAM (ed.) CBMS-NSF Conference Series in Applied Mathematics (1992)Google Scholar
  5. 5.
    Verma, N.K., Sevakula, R.K., Dixit, S., Salour, A.: Intelligent condition based monitoring using acoustic signals for air compressors. IEEE Trans. Rel. 65(1), 291–309 (2016)CrossRefGoogle Scholar
  6. 6.
    Lajos, T., Tóth, T.: On finding better wavelet basis for bearing fault detection. Acta Polytech. Hung. 10(3), 17–35 (2013)Google Scholar
  7. 7.
    Wang, S.B., Zhu, Z.K., Wang, A.Z.: Gearbox fault feature detection based on adaptive parameter identification with Morlet wavelet. In: Proceedings of IEEE International Conference on Wavelet Analysis and Pattern Recognition, pp. 409–414 (2010)Google Scholar
  8. 8.
    Ming, J.: Feature extraction based on Morlet wavelet and its application for mechanical fault diagnosis. J. Sound Vib. 234, 135–148 (2000)CrossRefGoogle Scholar
  9. 9.
    Stens, J.L.: Butterworth Low Pass Filter. Lecture Notes. Available at Accessed on June 2014
  10. 10.
    Verma, N.K., Singh, S., Gupta, J.K., Sevakula, R.K., Dixit, S., Salour, A.: Smartphone application for fault recognition. In: 6th International Conference on Sensing Technology, Kolkata, India, pp. 1–6 (2012)Google Scholar
  11. 11.
    Goumas, S.K., Zervakis, M.E., Stavrakakis, G.S.: Classification of washing machines vibration signals using discrete wavelet analysis for feature extraction. IEEE Trans. Instrum. Meas. 51(3), 497–508 (2002)CrossRefGoogle Scholar
  12. 12.
    Verma, N.K., Sarkar, S., Dixit, S., Sevakula, R.K., Salour, A.: Android app for intelligent CBM. In: 2013 IEEE International Symposium on Industrial Electronics, Taipei, Taiwan, pp. 1–6 (2013)Google Scholar
  13. 13.
    Liu, B., Lingand, S.-F., Meng, Q.F.: Machinery diagnostics based on wavelet packets. J. Vib. Control 3(1), 5–17 (1997)Google Scholar
  14. 14.
    Yang, D.M.: Induction motor bearing fault detection with non-stationary signal analysis. In: IEEE International Conference on Mechatronics, pp. 1–6 (2007)Google Scholar
  15. 15.
    Bruce, A., Donoho, D., Gao, H.Y.: Wavelet analysis for signal processing. IEEE Spectr. 33(10), 26–35 (1996)CrossRefGoogle Scholar
  16. 16.
    Maurits, M., Roose, D.: Wavelet-based image denoising using a Markov random field a priori model. IEEE Trans. Image Process. 6(4), 549–565 (1997)CrossRefGoogle Scholar
  17. 17.
    Sevakula, R.K., Verma, N.K.: Wavelet transforms for fault detection using SVM in power systems. In: IEEE International Conference on Power Electronics, Drives and Energy Systems, Bengaluru, India, pp. 1–6 (2012)Google Scholar
  18. 18.
    Verma, N.K., Gupta, J.K., Singh, S., Sevakula, R.K., Dixit, S., Salour, A.: Feature level analysis. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, IIT Kanpur, India, pp. 148–152 (2013)Google Scholar
  19. 19.
    Verma, N.K., Gupta, R., Sevakula, R.K., Salour, A.: Signal transforms for feature extraction from vibration signal for air compressor monitoring. In: IEEE Region 10 TENCON, Bangkok, Thailand, pp. 1–6 (2014)Google Scholar
  20. 20.
    Saraswat, G., Singh, V., Verma, N.K., Salour, A., Liu, J.: Prognosis of diesel engine (MBT) using feature extraction techniques: a comparative study. In: IEEE International Conference on Prognostics and Health Management, Washington, USA, pp. 11–13 (2018)Google Scholar
  21. 21.
    Verma, N.K., Sevakula, R.K., Goel, S.: Study of transforms for their comparison. In: International Conference on Industrial and Information Systems, Gwalior, India, pp. 1–6 (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Electrical Engineering and Inter-disciplinary Program in Cognitive ScienceIndian Institute of Technology KanpurKanpurIndia
  2. 2.Boeing Research and TechnologySaint LouisUSA

Personalised recommendations