In this paper, we investigate four key issues associated with data-driven approaches for fault classification using the Pratt and Whitney commercial dual-spool turbofan engine data as a test case. The four issues considered here include the following. (1) Can we characterize, a priori, the difficulty of fault classification via self-organizing maps? (2) Do data reduction techniques improve fault classification performance and enable the implementation of data-driven classification techniques in memory-constrained digital electronic control units (DECUs)? (3) When does adaptive boosting, an incremental fusion method that successively combines moderately inaccurate classifiers into accurate ones, help improve classification performance? (4) How to synthesize classifier fusion architectures to improve the overall diagnostic accuracy? The classifiers studied in this paper are the support vector machine, probabilistic neural network, k-nearest neighbor, principal component analysis, Gaussian mixture models, and a physics-based single fault isolator. As these algorithms operate on large volumes of data and are generally computationally expensive, we reduce the data set using the multiway partial least squares method. This has the added benefits of improved diagnostic accuracy and smaller memory requirements. The performance of the moderately inaccurate classifiers is improved using adaptive boosting. These results are compared to the results of the classifiers alone, as well as different fusion architectures. We show that fusion reduces the variability in diagnostic accuracy, and is most useful when combining moderately inaccurate classifiers.

1.
Butler
,
S. W.
,
Pattipati
,
K. R.
,
Volponi
,
A.
,
Hull
,
J.
,
Rajamani
,
R.
, and
Siegel
,
J.
, 2006, “
An Assessment Methodology for Data Driven and Model-Based Techniques for Engine Health Monitoring
,” ASME Paper No. GT 2006-91096.
2.
Fodor
,
I. K.
, “
A Survey of Data Reduction Techniques
,” available online at: http://www.llnl.gov/casc/sapphire/pubs148494.pdfhttp://www.llnl.gov/casc/sapphire/pubs148494.pdf
3.
Basserville
,
M.
, and
Nikiforov
,
I.
, 1993,
Detection of Abrupt Changes: Theory and Application
,
Information and System Science Series
,
Prentice-Hall
,
Englewood Cliffs, NJ
.
4.
Bishop
,
C. M.
, 2006,
Pattern Recognition and Machine Learning
,
Springer
,
New York
.
5.
Duda
,
R. O.
,
Hart
,
P. E.
, and
Stork
,
D. G.
2001,
Pattern Classification
,
2nd ed.
,
Wiley
,
New York
.
6.
Choi
,
K.
,
Luo
,
J.
,
Pattipati
,
K. R.
,
Qiao
,
L.
, and
Chigusa
,
S.
, 2006, “
Data Reduction Techniques for Intelligent Fault Diagnosis
,” 2006,
Proceedings of the IEEE Autotestcon
,
Anaheim, CA
, Sept.
7.
Jackson
,
J. E.
, 1991,
A User’s Guide to Principal Components
,
Wiley
,
New York
.
8.
Shah
,
J.
, 2004, “
Sequential k-Nearest Neighbor Pattern Recognition for Usable Speech Classification—A Revised Report
,” Speech Processing Lab, Temple University.
9.
Nomikos
,
P.
, 1996, “
Detection and Diagnosis of Abnormal Batch Operations Based on Multi-Way Principal Component Analysis
,”
ISA Trans.
0019-0578,
35
(
3
), pp.
259
266
.
10.
Volponi
,
A.
,
Depold
,
H.
,
Ganguli
,
R.
, and
Daguang
,
C.
, 2000, “
The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics: A Comparative Study
,”
ASME Paper No. 2000-GT-547
.
11.
Haykin
,
S.
, 1999,
Neural Networks: A Comprehensive Foundation
,
2nd ed.
,
Prentice-Hall
,
Englewood Cliffs, NJ
.
12.
Kohonen
,
T.
,
Erkki
,
O.
,
Simula
,
O.
,
Visa
,
A.
, and
Kangas
,
J.
, 1996, “
Engineering Applications of the Self-Organizing Map
,”
Proc. IEEE
0018-9219,
84
(
10
), pp.
1358
1384
.
13.
Hand
,
D. J.
, 1981,
Discrimination and Classification
,
Wiley
,
New York
.
14.
Mardia
,
K. V.
,
Kent
,
J. T.
, and
Bibby
,
J. M.
, 1995,
Multivariate Analysis
,
Probability and Mathematical Statistics
,
Academic
,
New York
.
15.
Ripley
,
B. D.
, 1996,
Pattern Recognition and Neural Networks
,
Cambridge University Press
,
Cambridge
.
16.
Friedman
,
J.
,
Hastie
,
T.
, and
Tibshirani
,
R.
, 2001,
Elements of Statistical Learning: Prediction, Inference and Data Mining
,
Springer
,
New York
.
17.
Wold
,
S.
,
Kettaneh
,
N.
,
Friden
,
H.
, and
Holmberg
,
A.
, 1998, “
Modeling and Diagnostics of Batch Processes and Analogous Kinetic Experiments
,”
Chemom. Intell. Lab. Syst.
0169-7439,
44
(
1–2
), pp.
331
340
.
18.
Wold
,
S.
,
Geladi
,
K.
,
Esbensen
,
K.
, 1987, “
Principle Component Analysis
,”
Chemom. Intell. Lab. Syst.
0169-7439,
2
(
1–3
), pp.
37
52
.
19.
Choi
,
K.
,
Azam
,
M.
,
Namburu
,
M.
,
Luo
,
J.
,
Pattipati
,
K. R.
, and
Patterson-Hine
,
A.
, 2006, “
Fault Diagnostics in HVAC Chillers Using Data-Driven Techniques
,”
IEEE Instrum. Meas. Mag.
1094-6969,
8
(
3
), pp.
24
32
.
20.
Rasmus
,
R.
, 1996, “
Multiway Calibration. Multilinear PLS
,”
Geol. J.
0072-1050,
10
(
1
), pp.
47
61
.
21.
Eibel
,
G.
, and
Pfeiffer
,
K.-P.
, 2005, “
Multi-Class Boosting for Weak Classifiers
,”
J. Mach. Learn. Res.
1532-4435,
6
, pp.
189
210
.
22.
Tang
,
Z. B.
,
Pattipati
,
K. R.
, and
Kleinman
,
D. L.
, 1991, “
Optimization of Detection Networks: Part I—Tandem Structures
,”
IEEE Trans. Syst. Man Cybern.
0018-9472,
21
(
5
), pp.
1045
1059
.
23.
Tang
,
Z. B.
,
Pattipati
,
K. R.
, and
Kleinman
,
D. L.
, 1992, “
A Distributed M-ary Hypothesis Testing Problem With Correlated Observations
,”
IEEE Trans. Autom. Control
0018-9286,
37
(
7
), pp.
1042
1046
.
24.
Pete
,
A.
,
Pattipati
,
K. R.
, and
Kleinman
,
D. L.
, 1994, “
Optimization of Detection Networks With Generalized Event Structures
,”
IEEE Trans. Autom. Control
0018-9286,
39
(
8
), pp.
1702
1707
.
25.
Kuncheva
,
L. I.
, 2004,
Combining Pattern Classifiers
,
Wiley
,
New York
.
26.
Chou
,
C. K.
, and
Liu
,
C. N.
, 1968, “
Approximating Discrete Probability Distributions With Dependence Trees
,”
IEEE Trans. Inf. Theory
0018-9448,
14
(
3
), pp.
463
467
.
27.
Berman
,
K. A.
, and
Paul
,
J. L.
, 1997,
Fundamentals of Sequential and Parallel Algorithms
,
PWS
,
Boston
.
28.
Aylpaydin
,
E.
, 2004,
Introduction to Machine Learning
,
MIT Press
,
Cambridge
.
29.
Choi
,
K.
,
Singh
,
S.
,
Kodali
,
A.
,
Pattipati
,
K.
,
Shepard
,
J.
,
Namburu
,
S.
,
Chigusa
,
S.
,
Prokhorov
,
D.
, and
Qiao
,
L.
, 2007, “
Novel Classifier Fusion Approaches for Fault Diagnosis in Automotive Systems
,”
IEEE Autotestcon
,
Baltimore, MD
.
You do not currently have access to this content.