Skip to main content
SpringerLink
Log in

Impeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networks

  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Nonstationary flow conditions can introduce complexities and nonlinear characteristics to pumping systems. This paper presents comparative studies of impeller fault detection techniques combined with artificial neural networks (ANNs) to propose the most appropriate diagnosis system. An experimental study, including seven impeller conditions, is performed to further explore the phenomena. Statistical parameters, frequency peaks, and wavelet packet energy present data feature sets, and a three-layer back-propagation ANN is used for fault recognition. The verification of the results proves that the detectability of the wavelet packet transform (WPT)-ANN model is considerably improved by using the energy of the decomposed vibration from WPT. This model can save computational time and provide superior diagnostic information. This study provides two key contributions. First, the feasibility and effectiveness of common monitoring techniques are compared. Second, the results demonstrate the accuracy of the proposed models for impellers operating under variable working conditions, which has not been previously addressed in the literature.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. R. Birajdar, R. Patil and K. Khanzode, Vibration and noise in centrifugal pump sources and diagnosis methods, 3rd International Conference on Integrity, Reliability and Failure, July (2009) 20–24.

    Google Scholar 

  2. L.-W. Lee and I.-H. Li, Design and implementation of a robust FNN-based adaptive sliding-mode controller for pneumatic actuator systems, J. Mech. Sci. Technol., 30 (1) (2016) 381–396.

    Article  Google Scholar 

  3. V. Muralidharan, V. Sugumaran and V. Indira, Fault diagnosis of monoblock centrifugal pump using SVM, Eng. Sci. Technol. an Int. J., 17 (3) (2014) 152–157.

    Article  Google Scholar 

  4. P. P. Harihara and A. G. Parlos, Sensorless detection of impeller cracks in motor driven centrifugal pumps, Design, Analysis, Control and Diagnosis of Fluid Power Systems, 5 (2008) 17–23.

    Google Scholar 

  5. R. Zouari and S. S. Menad, Fault detection system for centrifugal pumps using neural networks and neuro-fuzzy technique, CMSM 2005 (2005).

    Google Scholar 

  6. Y. F. Xing, Y. S. Wang, L. Shi, H. Guo and H. Chen, Sound quality recognition using optimal wavelet-packet transform and artificial neural network methods, Mech. Syst. Signal Process. (2015) 1–18.

    Google Scholar 

  7. J. Patel, V. Patel and A. Patel, Fault diagnostics of rolling bearing based on improve time and frequency domain features using artificial neural networks, Int. J. Sci. Res. Dev., 1 (4) (2013) 781–788.

    Google Scholar 

  8. B. Kamiel, G. Forbes, R. Entwistle, I. Mazhar and I. Howard, Impeller fault detection for a centrifugal pump using principal component analysis of time domain vibration features, Surveill. 7 Int. Conf. (2013) 1–12.

    Google Scholar 

  9. X. M. Zhao, Q. H. Hu, Y. G. Lei and M. J. Zuo, Vibrationbased fault diagnosis of slurry pump impellers using neighbourhood rough set models, Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., 224 (4) Apr. (2010) 995–1006.

    Google Scholar 

  10. A. K. Nandi, C. Liu and M. L. D. Wong, Intelligent vibration signal processing for condition monitoring, Proceedings of the International Conference Surveillance, 7 (2013) 1–15.

    Google Scholar 

  11. E. Chen, Z. Ma, G. Zhao, G. Li, A. Yang and G. Nan, Numerical investigation on vibration and noise induced by unsteady flow in an axial-flow pump, J. Mech. Sci. Technol., 30 (12) (2016) 5397–5404.

    Article  Google Scholar 

  12. S.-G. Park, H.-J. Sim, H.-J. Lee and J.-E. Oh, Application of non-stationary signal characteristics using wavelet packet transformation, J. Mech. Sci. Technol., 22 (11) (2008) 2122–2133.

    Article  Google Scholar 

  13. H. Yuan, J. Chen and G. Dong, An improved initialization method of D-KSVD algorithm for bearing fault diagnosis, J. Mech. Sci. Technol., 31 (11) (2017) 5161–5172.

    Article  Google Scholar 

  14. D. Wang and Q. Miao, Smoothness index-guided Bayesian inference for determining joint posterior probability distributions of anti-symmetric real Laplace wavelet parameters for identification of different bearing faults, J. Sound Vib., 345 (2015) 250–266.

    Article  Google Scholar 

  15. K. Shibata, A. Takahashi and T. Shirai, Fault diagnosis of rotating machinery through visualisation of sound signals, Mech. Syst. Signal Process., 14 (2) (2000) 229–241.

    Article  Google Scholar 

  16. R. Shao, W. Hu, Y. Wang and X. Qi, The fault feature extraction and classification of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform, Meas. J. Int. Meas. Confed., 54 (2014) 118–132.

    Article  Google Scholar 

  17. Y. Wang, G. Xu, L. Liang and K. Jiang, Detection of weak transient signals based on wavelet packet transform and manifold learning for rolling element bearing fault diagnosis, Mech. Syst. Signal Process., 54–55 (2015) 259–276.

    Article  Google Scholar 

  18. L. Toth, On finding better wavelet basis for bearing fault detection, Acta Polytech. Hungarica, 10 (3) (2013) 17–35.

    Google Scholar 

  19. E. Kim, Y. Lee and S. Lee, Heath monitoring of a glass transfer robot in the mass production line of liquid crystal display using abnormal operating sounds based on wavelet packet transform and artificial neural network, J. Sound Vib., 331 (2012) 3412–3427.

    Article  Google Scholar 

  20. M. Unal, M. Onat, M. Demetgul and H. Kucuk, Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network, Meas. J. Int. Meas. Confed., 58 (2014) 187–196.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Asset Integrity Management, Department of Mechanical and Aeronautical Engineering, University of Pretoria, Pretoria, 0002, South Africa

    A. Jami & P. S. Heyns

Authors
  1. A. Jami
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. S. Heyns
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. Jami.

Additional information

Recommended by Associate Editor Byeng Dong Youn

Amin Jami obtained his B.Eng. in 2013 in Iran, his B.Sc. (Hons) in 2015, and his M.Eng. in 2016 (cum laude) from the University of Pretoria in South Africa. He is currently a Ph.D. student in the Center for Asset Integrity Management of the University of Pretoria. His research interests include condition monitoring, vibration analysis, and machine and structural health diagnostics.

Stephan Heyns obtained his B.Sc. in Mechanical Engineering in 1978 (cum laude) and his Ph.D. in 1988 from the University of Pretoria in South Africa. In 1982, he joined the Department of Mechanical and Aeronautical Engineering at the University of Pretoria. He is currently a Director of the Center for Asset Integrity Management in the university. His research interests include machine and structural health diagnostics and prognostics, vibration analysis, vibration measurement techniques, and model updating.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jami, A., Heyns, P.S. Impeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networks. J Mech Sci Technol 32, 4079–4087 (2018). https://doi.org/10.1007/s12206-018-0807-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-018-0807-3

Keywords

Search

Navigation