Skip to main content
Log in

Identification of suction flow blockages and casing cavitations in centrifugal pumps by optimal support vector machine techniques

  • Technical Paper
  • Published:
Journal of the Brazilian Society of Mechanical Sciences and Engineering Aims and scope Submit manuscript

Abstract

Centrifugal pumps play vital role in many critical applications in industries and require continuous health monitoring to increase its availability. In centrifugal pumps, inlet pipe blockages and cavitation in the casing cause serious problems, such as the abnormal noise, high vibration, leakage, and decrease in the head capacity and the efficiency. Complexity in such fault is that one leads to other, and as such it falls under the multi-fault condition, which is hardly dealt in literature for pumps. Vibration-based monitoring of machinery faults using machine learning approaches has been one of latest trends. This paper presents the use of one of the machine learning tools, i.e., the support vector machine (SVM), for innovatively using in the diagnosis of blockage levels and the impeding cavitation at diverse pump speeds using statistical features extracted from vibration signature. SVM classifier parameters are optimally selected for better classifications. The prediction of classification is encouraging while taking decision for the pump condition.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Hellmann DH (2002) Early fault detection-an overview. World Pumps 428:54–57

    Google Scholar 

  2. Marçal RF, Negreiros M, Susin A, Kovaleski JL (2000) Detecting faults in rotating machines. Instrum Measurement Mag IEEE 3(4):24–26

    Article  Google Scholar 

  3. Schoen RR, Habetler TG, Kamran F, Bartfield RG (1995) Motor bearing damage detection using stator current monitoring. IEEE Trans Ind Appl 31(6):1274–1279

    Article  Google Scholar 

  4. Abdulkarem W, Amuthakkannan R, Al-Raheem KF (2014) Centrifugal Pump Impeller Crack Detection Using Vibration Analysis. 2nd International Conference on Research in Science, Engineering and Technology (ICRSET’2014), Dubai (UAE). pp 206–211

  5. Zouari R, Sieg-Zieba S, Sidahmed M (2004) Fault detection system for centrifugal pumps using neural networks and neuro-fuzzy techniques CETIM Senlis. Surveillance 5:11–13

    Google Scholar 

  6. Wang HQ, Chen P (2007) Fault diagnosis of centrifugal pump using symptom parameters in frequency domain. Agric Eng Int CIGR E J 07 005. Vol. IX

  7. Sakthivel NR, Sugumaran V, Senapati SV (2010) Vibration based fault diagnosis of monoblock centrifugal pump using decision tree. Expert Syst Appl 37(6):4040–4049

    Article  Google Scholar 

  8. Alfayez L, Mba D, Dyson G (2005) 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(5):354–358

    Article  Google Scholar 

  9. Farokhzad S (2013) Vibration Based Fault Detection of Centrifugal Pump by Fast Fourier Transform and Adaptive Neuro-Fuzzy Inference System. J Mech Eng Technol 1(3):82–87

    Article  Google Scholar 

  10. Albraik A, Althobiani F, Gu F, Ball A (2012) Diagnosis of centrifugal pump faults using vibration methods. J Phys Conf Ser 364(012139):1–12

    Google Scholar 

  11. Yang BS, Widodo A (2007) Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process 21(6):2560–2574

    Article  Google Scholar 

  12. Bordoloi DJ, Tiwari R (2013) Optimization of support vector machine based multi-fault classification with evolutionary algorithms from the time domain vibration data of gears. Proceedings of the Institution of Mechanical Engineers, Part C. J Mech Eng Sci 227(11):2428–2439. doi:10.1177/0954406213477777

    Article  Google Scholar 

  13. Bordoloi DJ, Tiwari R (2013) Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data. Measurement 55:1–14

    Article  Google Scholar 

  14. Vapnik V, Levin E, LeY Cun (1994) Measuring the VC-dimension of a learning machine. Neural Comput 6:851–876

    Article  Google Scholar 

  15. Burgess CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2:955–974

    Google Scholar 

  16. Gunn SR (1998) Support vector machines for classification and regression. Technical Report. University of Southampton, Southampton, pp 1–54

  17. Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. pp 1–16

  18. Cortes C, Vapnik V (1995) Support-vector network. Mach Learn 20:273–297

    MATH  Google Scholar 

  19. Boser BE, Guyon I, Vapnik V (1992) A training algorithm for optimal margin classifiers. Proceedings of the Fifth Annual Workshop on Computational Learning Theory. ACM Press. pp 144–152

  20. Scholkopf B, Smola A, Williamson RC, Bartlett PL (2000) New support vector algorithms. Neural Comput 12:1207–1245

    Article  Google Scholar 

  21. Knerr S, Personnaz L, Dreyfus G (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network. Neurocomputing: Algorithms, Architectures and Applications, NATO ASI, series. pp 41–50

  22. Kressel UHG (1998) Pairwise classification and support vector machines. In: Scholkopf B, Burges CJC, Smola AJ (eds) Advances in Kernel methods-support vector learning. MIT Press, Cambridge, pp 255–268

    Google Scholar 

  23. Hsu C-W, Lin C-J (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13(2):415–425

    Article  Google Scholar 

  24. Deb K (2003) Multi-objective optimization using evolutionary algorithms. Wiley, Chichester

    MATH  Google Scholar 

  25. Deb K (1995) Optimization for engineering design: algorithms and examples. Prentice-Hall of India Pvt Ltd, New Delhi

    Google Scholar 

  26. Houck CR, Joines JA, Kay MG (1996) A genetic algorithm for function optimization: a Matlab implementation. ACM Trans Math Softw 95:1–14

    Google Scholar 

  27. Karaboga D, Basturk B (2007) A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J Glob Optim 39(3):459–1171

    Article  MathSciNet  MATH  Google Scholar 

  28. Karaboga D, Basturk B (2008) On the performance of artificial bee colony (ABC) algorithm. Appl Soft Comput 8(1):687–697

    Article  Google Scholar 

Download references

Acknowledgements

The SVM software package LIBSVM (2011), Version 3.1, has been used for the present multi-class classification and could be downloaded freely from the web-address http://www.csie.ntu.edu.tw/~cjlin/libsvm. The single objective genetic algorithm is used for optimizing the SVM parameters and can be downloaded freely from the web-address http://www.ise.ncsu.edu/kay. The artificial bee colony algorithm ABCA software package version 2 (2009) is used for optimizing SVM parameters and could be downloaded freely from the web-address http://www.mf.erciyes.edu.tr/abc. Authors thank all of them.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Rajiv Tiwari.

Additional information

Technical Editor: Kátia Lucchesi Cavalca Dedini.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bordoloi, D.J., Tiwari, R. Identification of suction flow blockages and casing cavitations in centrifugal pumps by optimal support vector machine techniques. J Braz. Soc. Mech. Sci. Eng. 39, 2957–2968 (2017). https://doi.org/10.1007/s40430-017-0714-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40430-017-0714-z

Keywords

Navigation