On-line Time Domain Vibration and Current Signals Based Multi-fault Diagnosis of Centrifugal Pumps Using Support Vector Machines

  • Janani Shruti RapurEmail author
  • Rajiv Tiwari


It has been observed that centrifugal pumps (CPs) usually fail due to flow instabilities and other factors related to the hydraulic pump design. What is often ignored is the role of one fault in the pump system on the commencement/enhancement of another fault in it. Also, in a CP it is not only important to identify a fault, but it is also important to find the severity of it. In this research, causes of flow instabilities like, the blockage faults, impeller defects, pitted cover plate faults and dry runs are considered with varying severity. These faults are considered both independently and also in combinations with blockage faults. The CP vibration data and the motor line current data in time domain are used for the purpose of fault classification. The multi-fault diagnosis is attempted with the help of support vector machine (SVM) classifier. A fivefold cross-validation technique is used for the selection of optimum SVM hyper parameters. Wrapper model is used to select the best statistical feature(s). Novel features which give the best fault prediction performance of CP faults have been brought out in this work. The fault prediction from the experiments and the established approaches, aid the segregation of all the individual faults, fault combinations and their severities with promising execution, not only at the same training and testing speeds but also at the intermediate and overlying test speeds. The fault prediction of developed methodology has been inspected at various operating conditions of the CP and is found to be remarkably robust.


Centrifugal pump (CP) Individual and combination of faults Multi-fault diagnosis Cross validated-support vector machine (SVM) Time domain vibration and motor line current data 



The authors would like to acknowledge the LIBSVM tool, which is extensively used in the present work and freely available at [35].


  1. 1.
    Venkatachalam, R.: Mechanical Vibrations. PHI Learning, Delhi (2014)Google Scholar
  2. 2.
    Ugechi, C.I., Ogbonnaya, E.A., Lilly, M.T., Ogaji, S.O.T., Probert, S.D.: Condition-based diagnostic approach for predicting the maintenance requirements of machinery. Engineering 1, 177–187 (2009)CrossRefGoogle Scholar
  3. 3.
    Tabar, M.T.S., Hojjat Majidi, C., Poursharifi, Z.: Investigation of recirculation effects on the formation of vapor bubbles in centrifugal pump blades. World Acad. Sci. 49, 883–888 (2011)Google Scholar
  4. 4.
    Janani, S.R., Tiwari, R.: Experimental time-domain vibration based fault diagnosis of centrifugal pumps using SVM. ASCE-ASME J. Risk Uncert. Eng. Syst. Part B 3(4), 044501 (2016)Google Scholar
  5. 5.
    Alfayez, L., Mba, D., Dyson, G.: The application of acoustic emission for detecting incipient cavitation and the best efficiency point of a 60 kW centrifugal pump: case study. NDT E Int. 38, 354–358 (2005)CrossRefGoogle Scholar
  6. 6.
    Perovic, S., Unsworth, P. J., Higham, E. H.: Fuzzy logic system to detect pump faults from motor current spectra. In: Industry Applications Conference, 2001. Thirty-Sixth IAS Annual Meeting. Conference Record of the 2001 IEEE (2001), pp. 274–280Google Scholar
  7. 7.
    Harihara, P. P., Parlos, A. G.: Sensorless detection of impeller cracks in motor driven centrifugal pumps. In: ASME 2008 International Mechanical Engineering Congress and Exposition, Boston, MA (2008), pp. 17–23Google Scholar
  8. 8.
    Abdulkarem, W., Amuthakkannan, R., Al-Raheem, K. F.: Centrifugal pump impeller crack detection using vibration analysis. In: presented at the 2nd International Conference on Research in Science, Engineering and Technology (2014)Google Scholar
  9. 9.
    Bordoloi, D., Tiwari, R.: Identification of suction flow blockages and casing cavitations in centrifugal pumps by optimal support vector machine techniques. J. Br. Soc. Mech. Sci. Eng. 39, 1–12 (2017)CrossRefGoogle Scholar
  10. 10.
    Peck, J.P., Burrows, J.: On-line condition monitoring of rotating equipment using neural networks. ISA Trans. 33, 159–164 (1994)CrossRefGoogle Scholar
  11. 11.
    Cempel, C.: Vibroacoustical diagnostics of machinery: an outline. Mech. Syst. Signal Process. 2, 135–151 (1988)CrossRefGoogle Scholar
  12. 12.
    Sakthivel, N.R., Sugumaran, V., Nair, B.B.: Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump. Mech. Syst. Signal Process. 24, 1887–1906 (2010)CrossRefGoogle Scholar
  13. 13.
    Zouari, R., Sieg-Zieba, S., Sidahmed, M.: Fault detection system for centrifugal pumps using neural networks and neuro-fuzzy techniques. Presented at the Surveillance 5 CETIM Senlis, (2004)Google Scholar
  14. 14.
    Sakthivel, N., Sugumaran, V., Babudevasenapati, S.: Vibration based fault diagnosis of monoblock centrifugal pump using decision tree. Expert Syst. Appl. 37, 4040–4049 (2010)CrossRefGoogle Scholar
  15. 15.
    Vladimir, V.N., Vapnik, V.: The Nature of Statistical Learning Theory. Springer Science & Business Media, Berlin (1995)zbMATHGoogle Scholar
  16. 16.
    Widodo, A., Yang, B.-S.: Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 21, 2560–2574 (2007)CrossRefGoogle Scholar
  17. 17.
    Yang, Y., Yu, D., Cheng, J.: A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement 40, 943–950 (2007)CrossRefGoogle Scholar
  18. 18.
    Ganyun, L.V., Haozhong, C., Haibao, Z., Lixin, D.: Fault diagnosis of power transformer based on multi-layer SVM classifier. Electr. Power Syst. Res. 74, 1–7 (2005)CrossRefGoogle Scholar
  19. 19.
    Hu, Q., He, Z., Zhang, Z., Zi, Y.: Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble. Mech. Syst. Signal Process. 21, 688–705 (2007)CrossRefGoogle Scholar
  20. 20.
    Gangsar, P., Tiwari, R.: Multiclass fault taxonomy in rolling bearings at interpolated and extrapolated speeds based on time domain vibration data by SVM algorithms. J. Fail. Anal. Prev. 14, 826–837 (2014)CrossRefGoogle Scholar
  21. 21.
    Bordoloi, D.J., Tiwari, R.: Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data. Measurement 55, 1–14 (2014)CrossRefGoogle Scholar
  22. 22.
    Yuan, S.-F., Chu, F.-L.: Support vector machines-based fault diagnosis for turbo-pump rotor. Mech. Syst. Signal Process. 20, 939–952 (2006)CrossRefGoogle Scholar
  23. 23.
    Panda, A.K., Rapur, J.S., Tiwari, R.: Prediction of flow blockages and impending cavitation in centrifugal pumps using support vector machine (SVM) algorithms based on vibration measurements. Measurement 130, 44–56 (2018)CrossRefGoogle Scholar
  24. 24.
    Rapur J. S., Tiwari R.: A compliant algorithm to diagnose multiple centrifugal pump faults with corrupted vibration and current signatures in time-domain. p. V002T05A007 (2017)Google Scholar
  25. 25.
    Rapur, J.S., Tiwari, R.: Automation of multi-fault diagnosing of centrifugal pumps using multi-class support vector machine with vibration and motor current signals in frequency domain. J. Br. Soc. Mech. Sci. Eng. 40, 278 (2018)CrossRefGoogle Scholar
  26. 26.
    Luo, Y., Yuan, S., Yuan, J., Lu, J.: Research on characteristic of the vibration spectral entropy for centrifugal pump. Adv. Mech. Eng. 6, 1–9 (2014)CrossRefGoogle Scholar
  27. 27.
    Schoen, R.R., Habetler, T.G., Kamran, F., Bartfield, R.: Motor bearing damage detection using stator current monitoring. IEEE Trans. Ind. Appl. 31, 1274–1279 (1995)CrossRefGoogle Scholar
  28. 28.
    Harihara, P.P., Parlos, A.G.: “Sensorless detection of impeller cracks in motor driven centrifugal pumps. ASME Int. Mech. Eng. Congress Expos. 2008, 17–23 (2008)Google Scholar
  29. 29.
    Mba, D., Rao, R.B.: Development of acoustic emission technology for condition monitoring and diagnosis of rotating machines; bearings, pumps, gearboxes, engines and rotating structures. Shock Vibrat. Digest. 38, 3–16 (2006)CrossRefGoogle Scholar
  30. 30.
    Muralidharan, V., Sugumaran, V.: Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump. Measurement 46, 353–359 (2013)CrossRefGoogle Scholar
  31. 31.
    Yang, B.-S., Han, T., Yin, Z.-J.: Fault diagnosis system of induction motors using feature extraction, feature selection and classification algorithm. JSME Int J. Ser. C 49, 734–741 (2006)CrossRefGoogle Scholar
  32. 32.
    Chih-Wei, H., Chih-Jen, L.: A comparison of methods for multiclass support vector machines. IEEE Trans. Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  33. 33.
    Knerr, S., Personnaz, L., Dreyfus, G.: Single-layer learning revisited: a stepwise procedure for building and training a neural network. Neurocomputing. 68, 41–50 (1990)MathSciNetCrossRefGoogle Scholar
  34. 34.
    Kreßel, U.H.-G.: Pairwise classification and support vector machines. Adv Kernel Methods 27, 255–268 (1999)Google Scholar
  35. 35.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 1–27 (2011)CrossRefGoogle Scholar
  36. 36.
    Gangsar, P., Tiwari, R.: Taxonomy of induction-motor mechanical-fault based on time-domain vibration signals by multiclass SVM classifiers. Intell. Indust. Syst. 2, 269–281 (2016)CrossRefGoogle Scholar
  37. 37.
    Tiwari, R.: Rotor Systems: Analysis and Identification. CRC Press, Taylor and Francis Division, Boca Raton (2017)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringIndian Institute of Technology GuwahatiGuwahatiIndia

Personalised recommendations