Research Papers

Performance Comparison Between Fast Fourier Transform-Based Segmentation, Feature Selection, and Fault Identification Algorithm and Neural Network for the Condition Monitoring of Centrifugal Equipment

[+] Author and Article Information
Samer Gowid

Faculty of Engineering,
School of Electronic, Electrical and
Systems Engineering,
Loughborough University,
Leicestershire LE11 3TU, UK;
Department of Mechanical and
Industrial Engineering,
College of Engineering,
Qatar University,
Doha 2713, Qatar
e-mail: samer@qu.edu.qa

Roger Dixon

Faculty of Engineering,
School of Electronic, Electrical and
Systems Engineering,
Loughborough University,
Leicestershire LE11 3TU, UK

Saud Ghani

Department of Mechanical
and Industrial Engineering,
College of Engineering,
Qatar University,
Doha 2713, Qatar

1Corresponding author.

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received January 4, 2016; final manuscript received December 6, 2016; published online April 13, 2017. Assoc. Editor: M. Porfiri.

J. Dyn. Sys., Meas., Control 139(6), 061013 (Apr 13, 2017) (9 pages) Paper No: DS-16-1007; doi: 10.1115/1.4035458 History: Received January 04, 2016; Revised December 06, 2016

This paper compares and evaluates the performance of two major feature selection and fault identification methods utilized for the condition monitoring (CM) of centrifugal equipment, namely fast Fourier transform (FFT)-based segmentation, feature selection, and fault identification (FS2FI) algorithm and neural network (NN). Multilayer perceptron (MLP) is the most commonly used NN model for fault pattern recognition. Feature selection and trending play an important role in pattern recognition and hence affect the performance of CM systems. The technical and developmental challenges of both methods were investigated experimentally on a Paxton industrial centrifugal air blower system with a rotational speed of 15,650 RPMs. Five different machine conditions were experimentally emulated in the laboratory. A low training-to-testing ratio of 50% was utilized to evaluate the performance of both methods. In order to maximize fault identification accuracy and minimize computing time and cost, a near-optimal NN configuration was identified. The results showed that both techniques operated with a fault identification accuracy of 100%. However, the FS2FI algorithm showed a number of advantages over NN. These advantages include the ease of implementation and a reduction of cost and time in development and computing, as it processed the data from the first trial in less than 6.2% of the time taken by the NN.

Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.


Dulange, S. , Pundir, A. , and Ganapathy, L. , 2014, “ Impact of Maintenance on Profitability: A Case Study of Power Loom Textile,” Int. J. Bus. Manage., 2(7), pp. 36–39.
Prajapati, A. , Bechtel, J. , and Ganesan, S. , 2012, “ Condition Based Maintenance: A Survey,” J. Qual. Maint. Eng., 18(4), pp. 384–400. [CrossRef]
Gowid, S. , Dixon, R. , and Ghani, S. , 2014, “ Optimization of Reliability and Maintenance of Liquefaction System on FLNG Terminals Using Markov Modelling,” Int. J. Qual. Reliab. Manage., 31(3), pp. 293–310. [CrossRef]
Roddis, A. , 2006, “ Improve Plant Equipment Reliability by 20%,” AESSEAL, South Yorkshire, UK.
Helwig, N. , Klein, S. , and Schütze, A. , 2016, “ Identification and Quantification of Hydraulic System Faults Based on Multivariate Statistics Using Spectral Vibration Features,” Proc. Eng., 72–73, pp. 134–159.
Wang, T. , Liang, M. , Li, J. , Cheng, W. , and Li, C. , 2016, “ Bearing Fault Diagnosis Under Unknown Variable Speed Via Gear Noise Cancellation and Rotational Order Sideband Identification,” Mech. Syst. Signal Process., 62–63, pp. 30–53.
Liu, Y. , Guo, L. , Wang, Q. , An, G. , Guo, M. , and Lian, H. , 2010, “ Application to Induction Motor Faults Diagnosis of the Amplitude Recovery Method Combined With FFT,” Mech. Syst. Signal Process., 28(8), pp. 2961–2971. [CrossRef]
Booth, C. , and McDonald, J. , 1998, “ The Use of Artificial Neural Networks for Condition Monitoring of Electrical Power Transformers,” Neurocomputing, 23(1–3), pp. 97–109. [CrossRef]
Pham, D. , and Oztemel, E. , 1998, “ Condition Monitoring and Fault Diagnosis,” Intelligent Quality Systems, Springer, London, pp. 167–191.
Stergiou, C. , and Siganos, D. , 2011, “ Neural Networks,” Surprice 96 J., 4(11).
Gowid, S. , Dixon, R. , and Ghani, S. , 2015, “ FFT-Based Robust Automated Segmentation and Features Selection Algorithm for Condition Based Monitoring Systems,” J. Appl. Acoust., 88, pp. 66–74. [CrossRef]
Cho, Y. , and Kang, S. , 2011, “ Sensory Evaluation Using Artificial Intelligence,” Emerging Technologies for Food Quality and Food Safety Evaluation, CRC Press, Boca Raton, FL.
MathWorks, 2015, “  Multilayer Neural Network Architecture,” Matlab Help, MathWorks Company, Natick, MA.
Belciug, S. , and Gorunescu, F. , 2014, “ Error-Correction Learning for Artificial Neural Networks Using the Bayesian Paradigm. Application to Automated Medical Diagnosis,” J. Biomed. Inf., 52, pp. 329–337. [CrossRef]
Møller, M. , 1993, “ A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning,” Neural Networks, 6(4), pp. 525–533. [CrossRef]
Fernández-Redondo, M. , and Hernández-Espinosa, C. , 2001, “ Weight Initialization Methods for Multilayer Feedforward,” ESANN'2001 Proceedings—European Symposium on Artificial Neural Networks, Bruges, Belgium, Apr. 25–27, pp. 119–124.
Ming, A. , Qin, Z. , Zhang, W. , and Chu, F. , 2013, “ Spectrum Auto-Correlation Analysis and Its Application to Fault Diagnosis of Rolling Element Bearings,” Mech. Syst. Signal Process., 41(1–2), pp. 141–154. [CrossRef]
El-Thalji, I. , and Jantunen, E. , 2015, “ Fault Analysis of the Wear Fault Development in Rolling Bearings,” Eng. Failure Anal., 57, pp. 470–482. [CrossRef]
Gowid, S. , Dixon, R. , and Ghani, S. , 2016, “ Characterisation of Major Fault Detection Features and Techniques for the Condition-Based Monitoring of High-Speed Centrifugal Blowers,” Int. J. Acoust. Vib., 21(2), pp. 184–191.
Meh, D. , Denislic, M. , Lehtokangas, M. , and Saarinen, J. , 1998, “ Weight Initialization With Reference Patterns,” Neurocomputing, 20(131), pp. 265–278.
Wang, Z. , and Bovik, A. , 2009, “ Data Mining Concept and Techniques, Mean Squared Error: Love It or Leave It?,” IEEE Signal Process. Mag., 98, pp. 98–112. [CrossRef]
Akhmet, M. , and Yılmaz, E. , 2013, Neural Networks With Discontinuous/Impact Activations, Springer, New York.
Kinney, C. , Callafon, R. , Dunens, E. , Bargerhuff, R. , and Bash, C. , 2007, “ Optimal Periodic Disturbance Reduction for Active Noise Cancelation,” J. Sound Vib., 305(1–2), pp. 22–33. [CrossRef]
Gowid, S. , Dixon, R. , and Ghani, S. , 2015, “ Profitability, Reliability and Condition Based Monitoring of LNG Floating Platforms: A Review,” J. Nat. Gas Sci. Eng., 27(Pt. 3), pp. 1495–1511. [CrossRef]
Dahl, G. , McAvinney, A. , and Newhall, T. , 2008, “ Parallelizing Neural Networks Training for Cluster Systems,” PDCN'08 Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks.


Grahic Jump Location
Fig. 2

CCP and MLP feedforward architecture of NNs

Grahic Jump Location
Fig. 4

(a) The experimental setup and (b) schema of the experimental setup

Grahic Jump Location
Fig. 3

Positions of AE sensors

Grahic Jump Location
Fig. 5

Notches in the outer races of (a) bearing (A) and (b) bearing (B)

Grahic Jump Location
Fig. 6

Acoustic emission FFT amplitude spectra of the healthy and faulty machine conditions

Grahic Jump Location
Fig. 7

Illustrative flowchart of the FS2FI algorithm

Grahic Jump Location
Fig. 8

Performance comparison results between the FFT-based and the NN-based machine fault identification methods




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In