Abstract

Prediction of successful ignition is a challenging task that requires knowledge of the local thermochemical state in highly turbulent flow conditions. For typical industrial gas turbine (GTs) conditions operated on active service, these pieces of information are not directly available despite the high impact of ignition on technological and economic performance. The success of ignition mainly depends on the experiences made with the specific GT during long-term operation. Hence, there is a need for reliable prediction models for successful ignition that take the current conditions of the engine into account. We demonstrate the performance of supervised machine learning (ML) models to predict both successful and failed ignitions of GTs based on “real world” fleet data from the SGTx-8000H frame. This study compares the classification ability of seven widely used algorithms, for which we initially select 22 engineering-relevant parameters based on sensor data. We employ correlation and elimination techniques to reduce the parameter space drastically so that with only two input parameters we achieve a high (87%) prediction accuracy. Finally, we highlight the generalizability of the best performing ML model by application to unseen data of a different GT and report, for another case, on a recommissioned GT that is assisted by the ML model and consistently ignites the engine over an extended period of time.

References

1.
Gülen
,
S.
, and
Curtis
,
M.
,
2022
, “
Gas Turbine's Role in Energy Transition
,”
ASME
Paper No. GT2022-81802.10.1115/GT2022-81802
2.
Losi
,
E.
,
Venturini
,
M.
,
Manservigi
,
L.
,
Ceschini
,
G. F.
,
Bechini
,
G.
,
Cota
,
G.
, and
Riguzzi
,
F.
,
2022
, “
Prediction of Gas Turbine Trip: A Novel Methodology Based on Random Forest Models
,”
ASME J. Eng. Gas Turbines Power
,
144
(
3
), p.
14
.10.1115/1.4053194
3.
Cordier
,
M.
,
Vandel
,
A.
,
Renou
,
B.
,
Cabot
, G.
,
Boukhalfa
, M. A.
,
Esclapez
, L.
,
Barré
, D.
,
Riber
, E.
,
Cuenot
, B.
, et al.,
2013
, “
Experimental and Numerical Analysis of an Ignition Sequence in a Multiple-Injectors Burner
,”
ASME
Paper No. GT2013-94681.10.1115/GT2013-94681
4.
Gadde
,
S. B.
,
Teehan
,
D. G.
,
Singh
,
J. P.
,
Hildebrandt
,
G.
,
Kozachuk
,
D. W.
, and
Kollar
,
J. L.
,
2009
, “
Fuel Control for Starting a Gas Turbine Engine
,” U.S. Patent No.
74,810,617,481,061
.https://patents.google.com/patent/US7481061B2/en
5.
Yadav
,
V.
,
Casel
,
M.
, and
Ghani
,
A.
,
2023
, “
Physics-Informed Recurrent Neural Networks for Linear and Nonlinear Flame Dynamics
,”
Proc. Combust. Inst.
, 39(2), p.
1597
.10.1016/j.proci.2022.08.036
6.
Sengupta
,
U.
,
Rasmussen
,
C.
, and
Juniper
,
M.
,
2020
, “
Bayesian Machine Learning for the Prognosis of Combustion Instabilities From Noise
,”
ASME J. Eng. Gas Turbines Power
, 143(7), p.
071001
.10.1115/1.4049762
7.
McCartney
,
M.
,
Indlekofer
,
T.
, and
Polifke
,
W.
,
2020
, “
Online Detection of Combustion Instabilities Using Supervised Machine Learning
,”
ASME
Paper No. GT2020-14834.10.1115/GT2020-14834
8.
Kuznetsova
,
M.
, and
Ghani
,
A.
,
2024
, “
From Abstraction to Design: Interpretable Tree-Based Machine Learning for Stable Thermoacoustic System Layout
,”
Proc. Combust. Inst.
, 40(1), p.
105349
.10.1016/j.proci.2024.105349
9.
Pileggi
,
P.
,
Lazovik
,
E.
,
Snijders
,
R. e A.
, and
Graff
,
J.
,
2021
, “
A Lesson on Operationalizing Machine Learning for Predictive Maintenance of Gas Turbines
,”
ASME
Paper No. GT2021-59249.10.1115/GT2021-59249
10.
Kumar
,
R.
,
Peters
,
B.
,
Emerson
,
B.
,
Paynabar
,
K. e A.
, and
Lieuwen
,
T.
,
2020
, “
Data Driven Fault Detection of Premixer Centerbody Degradation in a Swirl Combustor
,”
ASME
Paper No. GT2020-14222.10.1115/GT2020-14222
11.
Li
,
S.
,
Qian
,
W.
,
Liu
,
H.
,
Zhu
,
M.
, and
Markides
,
C. N.
,
2020
, “
Prediction of the Autoignition of a Fuel Jet in a Confined Turbulent Hot Coflow Using Machine Learning Methods
,”
ASME
Paper No. GT2020-15020.10.1115/GT2020-15020
12.
Liu
,
J.
,
Ulishney
,
C.
, and
Dumitrescu
,
C. E.
,
2021
, “
Random Forest Machine Learning Model for Predicting Combustion Feedback Information of a Natural Gas Spark Ignition Engine
,” ASME
J. Energy Resour. Technol.
,
143
(
1
), p.
012301
.10.1115/1.4047761
13.
Breiman
,
L.
,
2001
, “
Random Forests Machine Learning
,”
45
(
1
), pp.
5
32
.
14.
Chen
,
C.
, and
Breiman
,
L.
,
2004
,
Using Random Forest to Learn Imbalanced Data
,
University of California
,
Berkeley, Berkeley, CA
.
15.
Friedman
,
J. H.
,
2002
, “
Stochastic Gradient Boosting
,”
Comput. Stat. Data Anal.
,
38
(
4
), pp.
367
378
.10.1016/S0167-9473(01)00065-2
16.
Hastie
,
T.
,
Rosset
,
S.
,
Zhu
,
J.
, and
Zou
,
H.
,
2009
, “
Multi-Class AdaBoost
,”
Stat. Its Interface
,
2
(
3
), pp.
349
360
.10.4310/SII.2009.v2.n3.a8
17.
Nayebi
,
H.
,
2020
, “
Advanced Statistics for Testing Assumed Causal Relationships: Multiple Regression Analysis Path Analysis Logistic Regression Analysis
,” Springer, 65(1), p.
79
.10.1007/978-3-030-54754-7
18.
Burkov
,
A.
,
2019
,
The Hundred-Page Machine Learning Book, MITP
,
Verlags GmbH & Co. KG, Warsow
,
Poland
.
19.
Zhou
,
D.
,
Zhang
,
H.
, and
Weng
,
S.
,
2015
, “
A New Gas Path Fault Diagnostic Method of Gas Turbine Based on Support Vector Machine
,”
ASME J. Eng. Gas Turbines Power
,
137
(
10
), p.
102605
.10.1115/1.4030277
20.
Rasmussen
,
C. E.
, and
Williams
,
C. K. I.
,
2006
,
Gaussian Processes for Machine Learning
,
Massachusetts Institute of Technology
,
Cambridge, MA
.
21.
Janus
,
B.
,
Bigalk
,
J.
,
Helmers
,
L.
,
Witzel
,
B. e A.
, and
Sunshine
,
R.
,
2014
, “
Successfully Validated Combustion System Upgrade for the SGT5/6-8000H Gas Turbines: Technical Features and Test Results
,”
ASME
Paper No. GT2014-27015.10.1115/GT2014-27015
22.
Gruschka
,
U.
,
Janus
,
B.
,
Meisl
,
J.
,
Huth
,
M.
, and
Wasif
,
S.
,
2008
, “
ULN System for the New SGT5-8000H Gas Turbine: Design and High Pressure Rig Test Results
,”
ASME
Paper No. GT2008-51208.10.1115/GT2008-51208
23.
Singh
,
D.
, and
Singh
,
B.
,
2020
, “
Investigating the Impact of Data Normalization on Classification Performance
,”
Appl. Soft Comput.
,
97
, p.
105524
.10.1016/j.asoc.2019.105524
24.
Losi
,
E.
,
Venturini
,
M.
, and
Manservigi
,
L.
,
2019
, “
Gas Turbine Health State prognostics by Means of Bayesian Hierarchical Models
,”
ASME J. Eng. Gas Turbines Power
,
141
(
11
), p.
111018
.10.1115/1.4044689
25.
Fernández
,
A.
,
García
,
S.
,
Galar
,
M.
,
Prati
,
R.
,
Krawczyk
,
B.
, and
Herrera
,
F.
,
2018
,
Learning From Imbalanced Data Sets
,
Springer Nature
,
Cham
.
26.
Chawla
,
N.
,
Bowyer
,
K. W.
,
Hall
,
L. O.
, and
Kegelmeyer
,
W. P.
,
2002
, “
SMOTE: Synthetic Minority Oversampling Technique
,”
J. Artif. Intell. Res.
,
16
, pp.
321
357
.10.1613/jair.953
27.
Storn
,
R.
, and
Price
,
K. V.
,
1997
, “
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization Over Continuous Spaces
,”
J. Global Optim.
,
11
(
4
), pp.
341
359
.10.1023/A:1008202821328
28.
Julier
,
S. J.
,
Uhlmann
,
J. K.
, and
Durrant-Whyte
,
H. F.
,
1995
, “
A New Approach for Filtering Nonlinear Systems
,”
Proceedings of 1995 American Control Conference-ACC'95
, Vol.,
3
, Seattle, WA, June 21–23, pp.
1628
1632
.10.1109/ACC.1995.529783
29.
Kuhn
,
M.
, and
Johnson
,
K.
,
2013
,
Applied Predictive Modeling
,
Springer
,
New York
.
30.
Raschka
,
S.
,
Liu
,
H. Y.
, and
Mirjalili
,
V.
,
2022
,
Machine Learning With PyTorch and Scikit-Learn
,
Packt Publishing
,
Birmingham, UK
.
31.
Bolón-Canedo
,
V.
, and
Alonso-Betanzos
,
A.
,
2018
,
Recent Advances in Ensembles for Feature Selection
,
Springer
,
Birmingham, UK
.
32.
Guyon
,
I.
,
Weston
,
J.
,
Barnhill
,
S.
, and
Vapnik
,
V.
,
2002
,
Gene Selection for Cancer Classification Using Support Vector Machines
,
Springer
,
New York
.
33.
Pedregosa
,
F.
,
Varoquaux
,
G.
,
Gramfort
,
A.
,
Michel
,
V.
,
Thirion
,
B.
,
Grisel
,
O.
,
Blondel
,
M.
,
Prettenhofer
,
P.
,
Weiss
,
R.
, et al.,
2011
, “
Scikit-Learn: Machine Learning in Python
,”
J. Mach. Learn. Res.
,
12
, pp.
2825
2830
.https://jmlr.org/papers/v12/pedregosa11a.html
34.
Caruana
,
R.
,
Karampatziakis
,
N.
, and
Yessenalina
,
A.
,
2008
, “
An Empirical Evaluation of Supervised Learning in High Dimensions
,”
Proceedings of the 25th International Conference on Machine Learning
,
Helsinki, Finland
, July 5–9, pp.
96
103
.10.1145/1390156.1390169
35.
Claussen
,
H.
,
Ulerich
,
N. H.
,
Momin
,
Z.
, and
Rosca
,
J.
,
2016
, “
Dynamic Pressure Method of Detecting Flame on/Off in Gas Turbine Combusion Cans for Engine Protection
,” U.S. Patent No.
70,313,203
.https://patents.google.com/patent/US20160313203A1/en
36.
Karim
,
F.
,
Majumdar
,
S.
,
Darabi
,
H.
, and
Chen
,
S.
,
2018
, “
LSTM Fully Convolutional Networks for Time Series Classification
,”
IEEE Access
,
6
, pp.
1662
1669
.10.1109/ACCESS.2017.2779939
37.
Chen
,
J.
,
Tang
,
X.
,
Lu
,
J.
, and
Zhang
,
H.
,
2022
, “
A Compressor Off-Line Washing Schedule Optimization Method With a LSTM Deep Learning Model Predicting the Fouling Trend
,”
ASME J. Eng. Gas Turbines Power
,
144
(
8
), p.
081005
.10.1115/1.4054748
38.
Cremanns
,
K.
, and
Roos
,
D.
,
2017
, “
Deep Gaussian Covariance Network
,”
Comp. Sci.
, 4, pp. 1–14.10.48550/arXiv.1710.06202
You do not currently have access to this content.