The conventional approach to neural network-based aircraft engine fault diagnostics has been mainly via multilayer feed-forward systems with sigmoidal hidden neurons trained by back propagation as well as radial basis function networks. In this paper, we explore two novel approaches to the fault-classification problem using (i) Fourier neural networks, which synthesizes the approximation capability of multidimensional Fourier transforms and gradient-descent learning, and (ii) a class of generalized single hidden layer networks (GSLN), which self-structures via Gram-Schmidt orthonormalization. Using a simulation program for the F404 engine, we generate steady-state engine parameters corresponding to a set of combined two-module deficiencies and require various neural networks to classify the multiple faults. We show that, compared to the conventional network architecture, the Fourier neural network exhibits stronger noise robustness and the GSLNs converge at a much superior speed.

1.
DePold
,
H. R.
, and
Gass
,
F. D.
, 1999, “
The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics
,”
ASME J. Eng. Gas Turbines Power
0742-4795,
121
, pp.
607
612
.
2.
Lu
,
P. J.
,
Hsu
,
T. C.
,
Zhang
,
M. C.
, and
Zhang
,
J.
, 2000, “
An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks
,” ASME Paper No. 2000-GT-0029.
3.
Camporeale
,
S.
,
Dambrosio
,
L.
,
Milella
,
A.
,
Mastrovito
,
M.
, and
Fortunato
,
B.
, 2003, “
Fault Diagnosis of Combined Cycle Gas Turbine Components Using Feedforward Neural Networks
,” ASME Paper No. GT-2003-38742.
4.
Kong
,
C.
,
Ki
,
J.
,
Kang
,
M.
, and
Kho
,
S.
, 2004, “
Intelligent Performance Diagnostics of a Gas Turbine Engine Using Friendly Interface Neural Networks
,”
Aircraft Eng. Aerospace Tech.
,
76
, pp.
391
397
.
5.
Peng
,
P.
, and
Yang
,
M. T.
, 2000, “
Neural Networks Based Diagnostics for Mistuned Bladed Disk
,” ASME Paper No. 2000-GT-0035.
6.
Sampath
,
S.
,
Gulati
,
A.
, and
Singh
,
R.
, 2002, “
Fault Diagnostics Using Genetic Algorithm for Advanced Cycle Gas Turbine
,” ASME Paper No. GT-2002-30021.
7.
Sampath
,
S.
,
Ogaji
,
S. O. T.
,
Li
,
Y. G.
, and
Singh
,
R.
, 2003, “
Fault Diagnosis of a Two Spool Turbo-Fan Engine Using Transient Data: A Genetic Algorithm Approach
,” ASME Paper No. GT2003-38300.
8.
DePold
,
H.
,
Chen
,
D.
,
Ganguli
,
R.
, and
Volponi
,
A. J.
, 2000, “
The Use of Kalman Filter and Neural Network Methologies in Gas Turbine Performance Diagnostics: AComparative Study
,” ASME Paper No. 2000-GT-547.
9.
Hassan
,
T. A. F.
,
El-Shafei
,
A.
, and
Zeyada
,
Y.
, 2003, “
Comparison of Neural Network Architectures for Machinery Fault Diagnosis
,” ASME Paper No. GT2003-38450.
10.
General Electric, 1996, “
F404-GE-100D Cycledeck Program L0046E
,” GE Aircraft Engine Advance Engineering Program Dept, Lynn, MA.
11.
Tan
,
H. S.
, 2004, “
Glances at Artificial Intelligence Methods in Aircraft Engine Diagnostics
,” Republic of Singapore Air Force, Air Logistics Dept., Propulsion Branch Internal Publication.
12.
RSL Electronics Ltd., 2001,
User Manual for Ground Station System for F404-GE-100D Engine Health Monitoring System
.
13.
Kurzke
,
J.
, 2003, “
Model Based Gas Turbine Parameter Correction
,” ASME Paper No. GT2003-38234.
14.
Haykin
,
S.
, 1999, “
Neural Networks: a Comprehensive Foundation
,”
Prentice-Hall
, Englewood Cliffs, NJ.
15.
Cybenko
,
G.
, 1989, “
Approximation By Superposition of a Sigmoidal Function
,”
Math. Control, Signals, Syst.
0932-4194,
2
, pp.
303
314
.
16.
Wang
,
Z.
,
Tham
,
M. T.
, and
Morris
,
A. J.
, 1992, “
Multilayer Neural Networks: Approximated Canonical Decomposition of Non-Linearity
,”
Int. J. Control
0020-7179,
56
, pp.
655
672
.
17.
Silvescu
,
A.
, 1999, “
Fourier Neural Networks
,”
Proceedings of the International Joint Conference On Neural Networks
,
IEEE
, Washington, DC, pp. 488–491.
18.
Kantorovich
,
L. V.
, and
Akilov
,
G. P.
, 1964,
Functional Analysis
,
Oxford Pergamon Press
, New York.
19.
Walker
,
J.
, 1988,
Fourier Analysis
,
Oxford University Press
, New York.
20.
Zhang
,
Q.
, and
Benveniste
,
A.
, 1992, “
Wavelet Networks
,”
IEEE Trans. Neural Netw.
1045-9227,
3
, pp.
889
898
.
21.
Pittner
,
S.
,
Kamarthi
,
S. V.
, and
Gao
,
G.
, 1998, “
Wavelet Networks for Sensor Signal Classification in Flank Wear Assessment
,”
J. Intell. Manuf.
0956-5515,
9
, pp.
315
322
.
22.
Strumillo
,
P.
, and
Kaminski
,
W.
, 1997, “
Kernal Orthonormalization in Radial Basis Function Neural Networks
,”
IEEE Trans. Neural Netw.
1045-9227,
8
, pp.
1177
1183
.
23.
Zhang
,
J.
, and
Morris
,
A. J.
, 1998, “
A Sequential Learning Approach for Single Hidden Layer Neural Networks
,”
Neural Networks
0893-6080,
11
, pp.
65
80
.
24.
Strumillo
,
P.
, and
Kaminski
,
W.
, 2001,
Neural Networks with Orthogonalised Transfer Functions
,
ESANN, Belgium.
25.
Duch
,
W.
, and
Jankowski
,
N.
, 1999, “
Survey of Neural Transfer Functions
,”
Neural Comput. Surv.
,
2
, pp.
163
212
.
26.
Hagan
,
M. T.
,
Demuth
,
H. B.
, and
Beale
,
M. H.
, 1996,
Neural Network Design
,
PWS Publishing
, Boston.
27.
Cover
,
T. M.
, 1965, “
Geometrical and Statistical Properties of Systems of Linear Inequalities With Applications in Pattern Recognition
,”
IEEE Trans. Electron. Comput.
0367-7508,
EC-14
, pp.
326
334
.
28.
General Electric Aircraft Engine, 1991,
Technical Manual Intermediate Maintenance Turbofan Engine F404-GE-100D Model
,
SEI-701.
29.
Koplon
,
R.
, and
Sontag
,
E. D.
, 1997, “
Using Fourier Neural Recurrent Networks to Fit Sequential Input/Output Data
,”
Neurocomputing
0925-2312,
15
, pp.
225
248
.
This content is only available via PDF.
You do not currently have access to this content.