Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump

Maamar Al Tobi; Geraint Bevan; Peter Wallace; David Harrison; Kenneth Eloghene Okedu

doi:10.1002/ese3.933

journal article Open Access Jul 02, 2021

Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump

Maamar Al Tobi

Geraint Bevan Peter Wallace David Harrison

Kenneth Eloghene Okedu

Energy Science & Engineering Vol. 10 No. 6 pp. 1826-1839 · Wiley

View at Publisher Save 10.1002/ese3.933

Abstract

AbstractThis paper explores artificial intelligent training schemes based on multilayer perceptron, considering back propagation and genetic algorithm (GA). The hybrid scheme is compared with the traditional support vector machine approach in the literature to analyze both fault and normal scenarios of a centrifugal pump. A comparative analysis of the performance of the variables was carried out using both schemes. The study used features extracted for three decomposition levels based on wavelet packet transform. In order to investigate the effectiveness of the extracted features, two mother wavelets were investigated. The salient part of this work is the optimization of the hidden layers numbers using GA. Furthermore, this optimization process was extended to the multilayer perceptron neurons. The evaluation of the model system performance used for the study shows better response of the extracted features, and hidden layers variables including the selected neurons. Moreover, the applied training algorithm used in the work was able to enhance the classifications obtained considering the hybrid artificial intelligent scheme been proposed. This work has achieved a number of contributions like GA‐based selection of hidden layers and neuron, applied in neural network of centrifugal pump condition classification. Furthermore, a hybrid training method combining GA and back propagation (BP) algorithms has been applied for condition classification of a centrifugal pump. The obtained results have shown the good ability of the proposed methods and algorithms.

Topics

No keywords indexed for this article. Browse by subject →

References

55

[1]

Al‐Tubi MAS "Rolling element bearing faults detection, a time domain analysis" Caledonian J Eng (2010)

[2]

Al‐Tubi MAS (2012)

[3]

Mehala N (2008)

[4]

10.1016/s0888-3270(03)00075-x

[5]

10.13189/ujme.2015.030203

[6]

Elsken T "Neural architecture search: a survey" J Mach Learn Res (2019)

[7]

vanSteinB WangH ThomasB.Neural network design: learning from neural architecture search. Preprint;2020. 10.1109/ssci47803.2020.9308394

[8]

10.18005/jmet0103001

[9]

10.1016/j.jestch.2014.02.005

[10]

Al TM "Faults diagnosis of a centrifugal pump using multilayer perceptron genetic algorithm back propagation and support vector machine with discrete wavelet transform‐based feature extraction" Comput Intellig (2020)

[11]

10.1186/s13640‐018‐0396‐1

[12]

Yanjun L (2009)

[13]

10.1016/s0888-3270(03)00020-7

[14]

10.1109/icsse.2011.5961870

[15]

Al‐Raheem KF "Rolling bearing fault diagnostics using artificial neural networks based on laplace wavelet analysis" Int J Eng Sci Technol (2010)

[16]

Altobi MAS (2017)

[17]

Altobi MAS (2017)

[18]

10.1016/j.jestch.2019.01.005

[19]

10.1186/s10033‐019‐0388‐9

[20]

Deng W "An enhanced MSIQDE algorithm with novel multiple strategies for global optimization problems" IEEE Trans Syst Man Cybernet: Syst (2020)

[21]

10.1155/2021/6660115

[22]

Charniak E (2000)

[23]

A logical calculus of the ideas immanent in nervous activity

Warren S. McCulloch, Walter Pitts

The Bulletin of Mathematical Biophysics 10.1007/bf02478259

[24]

Fuzzy sets

L.A. Zadeh

Information and Control 10.1016/s0019-9958(65)90241-x

[25]

10.1109/icmech.2011.5971192

[26]

Farokhzad S "Fault classification of centrifugal water pump based on decision tree and regression model" J Sci Today's World (2013)

[27]

Farokhzad S "Artificial neural network based classification of faults in centrifugal water pump" J Vibroeng (2012)

[28]

10.1109/icqr2mse.2011.5976651

[29]

10.1080/08839514.2012.721694

[30]

10.1007/s00521-008-0192-4

[31]

Wang HQ "Fault diagnosis of centrifugal pump using symptom parameters in frequency domain" Agric Eng Int: CIGR Ejournal (2007)

[32]

Muralidharan V "Artifical neural network based classification for monoblock centrifugal pump using wavelet analysis" Int J Mech Eng (2010)

[33]

10.1243/0954408971529665

[34]

Zouari R (2004)

[35]

10.1109/icmech.2011.5971192

[36]

10.1007/s00170-013-4797-0

[37]

10.1016/j.asoc.2015.02.015

[38]

10.1109/icsem.2010.93

[39]

Sui W‐T (2009)

[40]

10.1109/icicci.2010.64

[41]

10.1007/s00500-005-0481-0

[42]

Learning representations by back-propagating errors

David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams

Nature 10.1038/323533a0

[43]

Support-Vector Networks

Corinna Cortes, Vladimir Vapnik

Machine Learning 10.1023/a:1022627411411

[44]

Holland JH (1975)

[45]

Rooij AJFV (1996)

[46]

10.1016/j.eswa.2008.05.052

[47]

Saberi M (2011)

[48]

10.1016/s0169-7439(97)00029-4

[49]

Coifman RR (1992)

[50]

10.1016/j.asoc.2011.12.009

Showing 50 of 55 references

Metrics

17

Citations

55

References

Details

Published: Jul 02, 2021
Vol/Issue: 10(6)
Pages: 1826-1839
License: View

Authors

M

Maamar Al Tobi

Mechanical & Industrial Engineering College of Engineering National University of Science and Technology Muscat Oman

G

Geraint Bevan

School of Engineering and Built Environment Glasgow Caledonian University Glasgow UK

P

Peter Wallace

School of Engineering and Built Environment Glasgow Caledonian University Glasgow UK

D

David Harrison

School of Engineering and Built Environment Glasgow Caledonian University Glasgow UK

K

Kenneth Eloghene Okedu

Electrical and Computer Engineering College of Engineering National University of Science and Technology Muscat Oman; Electrical and Electronic Engineering Nisantasi University Istanbul Turkey

Cite This Article

Maamar Al Tobi, Geraint Bevan, Peter Wallace, et al. (2021). Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump. Energy Science & Engineering, 10(6), 1826-1839. https://doi.org/10.1002/ese3.933

Using MLP‐GABP and SVM with wavelet packet transform‐based feature extraction for fault diagnosis of a centrifugal pump

You May Also Like