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.

References

References
1.
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
.
2.
Prajapati
,
A.
,
Bechtel
,
J.
, and
Ganesan
,
S.
,
2012
, “
Condition Based Maintenance: A Survey
,”
J. Qual. Maint. Eng.
,
18
(
4
), pp.
384
400
.
3.
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
.
4.
Roddis
,
A.
,
2006
, “
Improve Plant Equipment Reliability by 20%
,” AESSEAL, South Yorkshire, UK.
5.
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
.
6.
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
.
7.
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
.
8.
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
.
9.
Pham
,
D.
, and
Oztemel
,
E.
,
1998
, “
Condition Monitoring and Fault Diagnosis
,”
Intelligent Quality Systems
,
Springer
,
London
, pp.
167
191
.
10.
Stergiou
,
C.
, and
Siganos
,
D.
,
2011
, “
Neural Networks
,”
Surprice 96 J.
,
4
(
11
).
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
.
12.
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
.
13.
MathWorks
,
2015
, “
Multilayer Neural Network Architecture
,” Matlab Help,
MathWorks Company
, Natick, MA.
14.
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
.
15.
Møller
,
M.
,
1993
, “
A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning
,”
Neural Networks
,
6
(
4
), pp.
525
533
.
16.
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
.
17.
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
.
18.
El-Thalji
,
I.
, and
Jantunen
,
E.
,
2015
, “
Fault Analysis of the Wear Fault Development in Rolling Bearings
,”
Eng. Failure Anal.
,
57
, pp.
470
482
.
19.
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
.
20.
Meh
,
D.
,
Denislic
,
M.
,
Lehtokangas
,
M.
, and
Saarinen
,
J.
,
1998
, “
Weight Initialization With Reference Patterns
,”
Neurocomputing
,
20
(
131
), pp.
265
278
.
21.
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
.
22.
Akhmet
,
M.
, and
Yılmaz
,
E.
,
2013
,
Neural Networks With Discontinuous/Impact Activations
,
Springer
,
New York
.
23.
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
.
24.
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
.
25.
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
.
You do not currently have access to this content.