0
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.

FIGURES IN THIS ARTICLE
<>
Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 2

CCP and MLP feedforward architecture of NNs

Grahic Jump Location
Fig. 3

Positions of AE sensors

Grahic Jump Location
Fig. 4

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

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

Tables

Errata

Discussions

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