Abstract

Removing noise from health signals is critical in gas path diagnostics of aircraft engines. An efficient noise filtering/denoising method should remove noise without using future data points, preserve important changes, and promote accurate diagnostics without time delay. Machine learning (ML)-based methods are promising for high fidelity, accuracy, and computational efficiency under the motivation of Intelligent Engines. However, previous ML-based denoising methods are rarely applied in actual engineering practice because they cannot accommodate time series and cannot effectively capture important changes or are limited by the time delay problem. This paper proposes a convolutional neural network denoising auto-encoder (CNN-DAE) method to build a denoising auto-encoder structure. In this structure, a convolutional operation is used to accommodate time series, and causal convolution is introduced to solve the problem of using future data points. The proposed denoising method is evaluated against NASA's propulsion diagnostic method evaluation strategy (prodimes) software. It has been proved that the proposed method can accommodate time series, remove noise for improved denoising accuracy, and preserve the important changes for enhanced diagnostic information. NASA's blind test case results show that kappa coefficient of a common diagnostic method using the processed data is 0.731 and is at least 0.046 higher than the other diagnostic methods in the open literature. Processing health signals using the proposed method would significantly promote accurate diagnostics without time delay. The proposed method could support intelligent condition monitoring systems by exploiting historical information for improved denoising and diagnostic performance.

References

1.
Lipowsky
,
H.
,
Staudacher
,
S.
,
Bauer
,
M.
, and
Schmidt
,
K. J.
,
2010
, “
Application of Bayesian Forecasting to Change Detection and Prognosis of Gas Turbine Performance
,”
ASME J. Eng. Gas Turbines Power
,
132
(
3
), p.
031602
.10.1115/1.3159367
2.
Sogut
,
M. Z.
,
Yalcin
,
E.
, and
Karakoc
,
T. H.
,
2017
, “
Assessment of Degradation Effects for an Aircraft Engine Considering Exergy Analysis
,”
Energy
,
140
, pp.
1417
1426
.10.1016/j.energy.2017.03.093
3.
Volponi
,
A. J.
, and
Tang
,
L.
,
2016
, “
Improved Engine Health Monitoring Using Full Flight Data and Companion Engine Information
,”
SAE Int. J. Aerosp.
,
9
(
1
), pp.
91
102
.10.4271/2016-01-2024
4.
Simon
,
D. L.
,
2010
, “
Propulsion Diagnostic Method Evaluation Strategy (ProDiMES) User's Guide
,” NASA, Cleveland, OH, Report No.
NASA/TM-2010-215840
. https://ntrs.nasa.gov/citations/20100005639
5.
Ganguli
,
R.
,
2012
,
Gas Turbine Diagnostics: Signal Processing and Fault Isolation
,
CRC Press
,
London, UK
.
6.
Chen
,
Y. Z.
,
Zhao
,
X. D.
,
Xiang
,
H. C.
, and
Tsoutsanis
,
E.
,
2021
, “
A Sequential Model-Based Approach for Gas Turbine Performance Diagnostics
,”
Energy
,
220
(
11
), p.
119657
.10.1016/j.energy.2020.119657
7.
Kim
,
S.
,
2021
, “
A New Performance Adaptation Method for Aero Gas Turbine Engines Based on Large Amounts of Measured Data
,”
Energy
,
221
(
11
), p.
119863
.10.1016/j.energy.2021.119863
8.
Simon
,
D. L.
,
Borguet
,
S.
,
Léonard
,
O.
, and
Zhang
,
X.
,
2014
, “
Aircraft Engine Gas Path Diagnostic Methods: Public Benchmarking Results
,”
ASME J. Eng. Gas Turbines Power
,
136
(
4
), p.
041201
.10.1115/1.4025482
9.
Koskoletos
,
A. O.
,
Aretakis
,
N.
,
Alexiou
,
A.
,
Romesis
,
C.
, and
Mathioudakis
,
K.
,
2018
, “
Evaluation of Aircraft Engine Gas Path Diagnostic Methods Through ProDiMES
,”
ASME J. Eng. Gas Turbines Power
,
140
(
12
), p.
121016
.10.1115/1.4040909
10.
Uday
,
P.
, and
Ganguli
,
R.
,
2010
, “
Jet Engine Health Signal Denoising Using Optimally Weighted Recursive Median Filters
,”
ASME J. Eng. Gas Turbines Power
,
132
(
4
), p.
041601
.10.1115/1.3200907
11.
Ganguli
,
R.
,
2002
, “
Noise and Outlier Removal From Jet Engine Health Signals Using Weighted FIR Median Hybrid Filters
,”
Mech. Syst. Signal Process.
,
16
(
6
), pp.
967
978
.10.1006/mssp.2002.1477
12.
Ganguli
,
R.
,
2003
, “
Jet Engine Gas-Path Measurement Filtering Using Center Weighted Idempotent Median Filters
,”
J. Propul. Power
,
19
(
5
), pp.
930
937
.10.2514/2.6186
13.
Raikar
,
C.
, and
Ganguli
,
R.
,
2017
, “
Denoising Signals Used in Gas Turbine Diagnostics With Ant Colony Optimized Weighted Recursive Median Filters
,”
INAE Lett.
,
2
(
3
), pp.
133
143
.10.1007/s41403-017-0023-y
14.
Borguet
,
S.
,
Leonard
,
O.
, and
Dewallef
,
P.
,
2016
, “
Regression-Based Modeling of a Fleet of Gas Turbine Engines for Performance Trending
,”
ASME J. Eng. Gas Turbines Power
,
138
(
2
), p.
021201
.10.1115/1.4031253
15.
Bengio
,
Y.
,
2009
, Learning Deep Architectures for AI, Foundations and Trends in Machine Learning, Montreal, QC, Canada.
16.
Ackley
,
D. H.
,
Hinton
,
G. E.
, and
Sejnowski
,
T. J.
,
1985
, “
A Learning Algorithm for Boltzmann Machines
,”
Cognit. Sci.
,
9
(
1
), pp.
147
169
.10.1207/s15516709cog0901_7
17.
Vincent
,
P.
,
Larochelle
,
H.
,
Bengio
,
Y.
, and
Manzagol
,
P. A.
,
2008
, “
Extracting and Composing Robust Features With Denoising Autoencoders
,”
Proceedings of the 25th International Conference on Machine Learning
,
Helsinki, Finland
, June 5–9, pp.
1096
1103
.https://www.cs.toronto.edu/~larocheh/publications/icml-2008-denoising-autoencoders.pdf
18.
Kramer
,
M. A.
,
1992
, “
Autoassociative Neural Networks
,”
Comput. Chem. Eng.
,
16
(
4
), pp.
313
328
.10.1016/0098-1354(92)80051-A
19.
Guo
,
T. H.
,
Saus
,
J.
,
Lin
,
C. F.
, and
Ge
,
J. H.
,
1996
, “
Sensor Validation for Turbofan Engines Using an Autoassociative Neural Network
,”
AIAA
Paper No. 96-3926. 10.2514/6.96-3926
20.
Lu
,
P. J.
,
Zhang
,
M. C.
,
Hsu
,
T. C.
, and
Zhang
,
J.
,
2001
, “
An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks
,”
ASME J. Eng. Gas Turbines Power
,
123
(
2
), pp.
340
346
.10.1115/1.1362667
21.
Zedda
,
M.
, and
Singh
,
R.
,
1998
, “
Fault Diagnosis of a Turbofan Engine Using Neural Networks: A Quantitative Approach
,”
AIAA
Paper No.
98
3602
.10.2514/6.1998-3602
22.
Ogaji
,
S. O. T.
,
Singh
,
R.
, and
Probert
,
S. D.
,
2002
, “
Multiple-Sensor Fault-Diagnoses for a 2-Shaft Stationary Gas-Turbine
,”
Appl. Energy
,
71
(
4
), pp.
321
339
.10.1016/S0306-2619(02)00015-6
23.
Li
,
D.
,
Zhou
,
J.
, and
Liu
,
Y.
,
2021
, “
Recurrent-Neural-Network-Based Unscented Kalman Filter for Estimating and Compensating the Random Drift of MEMS Gyroscopes in Real Time
,”
Mech. Syst. Signal Process.
,
147
, pp.
1
20
.10.1016/j.ymssp.2020.107057
24.
Li
,
H.
,
Yang
,
Z.
, and
Yan
,
W.
,
2022
, “
An Improved AIC Onset-Time Picking Method Based on Regression Convolutional Neural Network
,”
Mech. Syst. Signal Process.
,
171
, pp.
1
20
.10.1016/j.ymssp.2022.108867
25.
Bai
,
S.
,
Kolter
,
J. Z.
, and
Koltun
,
V.
,
2018
, “
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
,” e-print
arXiv:1803.01271
. 10.48550/arXiv.1803.01271
26.
Barzegar
,
V.
,
Laflamme
,
S.
,
Hu
,
C.
, and
Dodson
,
J.
,
2021
, “
Ensemble of Recurrent Neural Networks With Long Short-Term Memory Cells for High-Rate Structural Health Monitoring
,”
Mech. Syst. Signal Process.
,
164
, pp.
1
15
.10.1016/j.ymssp.2021.108201
27.
Chen
,
Z.
,
Xia
,
T.
,
Li
,
Y.
, and
Pan
,
E.
,
2021
, “
A Hybrid Prognostic Method Based on Gated Recurrent Unit Network and an Adaptive Wiener Process Model Considering Measurement Errors
,”
Mech. Syst. Signal Process.
,
158
, pp.
1
21
.10.1016/j.ymssp.2021.107785
28.
Zhao
,
J.
, and
Li
,
Y.
,
2020
, “
Abrupt Fault Detection and Isolation for Gas Turbine Components Based on a 1D Convolutional Neural Network Using Time Series Data
,”
AIAA
Paper No. 2020-3675. 10.2514/6.2020-3675
29.
Kiranyaz
,
S.
,
Avci
,
O.
,
Abdeljaber
,
O.
,
Ince
,
T.
,
Gabbouj
,
M.
, and
Inman
,
D. J.
,
2021
, “
1D Convolutional Neural Networks and Applications: A Survey
,”
Mech. Syst. Signal Process.
,
151
, pp.
1
21
.10.1016/j.ymssp.2020.107398
30.
Goodfellow
,
I.
,
Bengio
,
Y.
, and
Courville
,
A.
,
2016
,
Deep Learning
,
MIT Press
, Cambridge, MA.
31.
Oord
,
A. V. D.
,
Dieleman
,
S.
,
Zen
,
H.
,
Simonyan
,
K.
,
Vinyals
,
O.
,
Graves
,
A.
,
Kalchbrenner
,
N.
,
Senior
,
A.
, and
Kavukcuoglu
,
K.
,
2016
, “
WaveNet: A Generative Model for Raw Audio
,” e-print
arXiv:1609.03499
. 10.48550/arXiv.1609.03499
32.
Feurer
,
M.
, and
Hutter
,
F.
,
2019
, “
Hyperparameter Optimization
,”
Automated Machine Learning—Methods, Systems, Challenges
,
Springer
, Berlin, pp.
233
317
.
33.
Loboda
,
I.
,
Pérez-Ruiz
,
J. L.
, and
Yepifanov
,
S.
,
2018
, “
A Benchmarking Analysis of a Data-Driven Gas Turbine Diagnostic Approach
,”
ASME
Paper No. GT2018-76887. 10.1115/GT2018-76887
34.
Calderano
,
P. H. S.
,
Ribeiro
,
M. G. C.
,
Amaral
,
R. P. F.
,
Vellasco
,
M. M. B. R.
,
Tanscheit
,
R.
, and
de Aguiar
,
E. P.
,
2019
, “
An Enhanced Aircraft Engine Gas Path Diagnostic Method Based on Upper and Lower Singleton Type-2 Fuzzy Logic System
,”
J. Braz. Soc. Mech. Sci. Eng.
,
41
(
2
), pp.
1
14
.10.1007/s40430-019-1567-4
35.
Pérez-Ruiz
,
J. L.
,
Tang
,
Y.
, and
Loboda
,
I.
,
2021
, “
Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach
,”
Aerospace
,
8
(
8
), p.
232
.10.3390/aerospace8080232
You do not currently have access to this content.