Abstract

Flame flashback (FB) is a major concern in hydrogen-fired gas turbines. In order to determine the flashback propensity of a hydrogen burner, several burner design tests at different operating points and fuel blends are performed under engine-relevant conditions at the test facility of Siemens Energy. A camera monitors the flame in the combustion chamber and the occurrence of flame flashback events in the image recordings becomes clearly visible. This anomalous behavior clearly deviates from normal hydrogen operation. We develop a data-driven approach to detect flame flashback events based on the camera images at 100% hydrogen operation, where all images feature identical characteristics since the pure hydrogen flame is not visible for the camera. Simultaneously, the highest susceptibility to flashback is attained in this regime. We use both facts and the good suitability of image data to train a convolutional auto-encoder (CAE) model to detect anomalies. Here, anomalies correspond to flashback events. Flashback is captured by the CAE using the reconstruction error associated with a dynamic threshold as a measure of anomaly. This newly developed dynamic threshold overcomes the difficulties in the generalization capability of the CAE. Regardless of the test campaign, burner design, and camera settings, it reliably identifies flashback events. Along with the CAE, the compressed representation, namely, the latent space of the CAE, detects the position of flame flashback events. Our methodology is able to detect flame flashback using only flame images and provides a reliable tool even when unseen data are used.

References

1.
IEA - International Energy Agency
,
2021
, “
Global Hydrogen Review 2021
,” IEA Publications, Paris, France, accessed Oct. 2023, https://www.iea.org/reports/global-hydrogen-review-2021
2.
Witzel
,
B.
,
Moëll
,
D.
,
Parsania
,
N.
,
Yilmaz
,
E.
, and
Koenig
,
M.
,
2022
, “
Development of a Fuel Flexible H2-Natural Gas Turbine Combustion Technology Platform
,”
ASME
Paper No. GT2022-82881.10.1115/GT2022-82881
3.
Clavin
,
P.
,
1985
, “
Dynamic Behavior of Premixed Flame Fronts in Laminar and Turbulent Flows
,”
Prog. Energy Combust. Sci.
,
11
(
1
), pp.
1
59
.10.1016/0360-1285(85)90012-7
4.
Eichler
,
C.
,
Baumgartner
,
G.
, and
Sattelmayer
,
T.
,
2012
, “
Experimental Investigation of Turbulent Boundary Layer Flashback Limits for Premixed Hydrogen-Air Flames Confined in Ducts
,”
ASME J. Eng. Gas Turbine Power
,
134
(
1
), p.
011502
.10.1115/1.4004149
5.
Reichel
,
T. G.
,
Terhaar
,
S.
, and
Paschereit
,
O.
,
2015
, “
Increasing Flashback Resistance in Lean Premixed Swirl-Stabilized Hydrogen Combustion by Axial Air Injection
,”
ASME J. Eng. Gas Turbine Power
,
137
(
7
), p.
071503
.10.1115/1.4029119
6.
Baumgartner
,
G.
,
Boeck
,
L. R.
, and
Sattelmayer
,
T.
,
2016
, “
Experimental Investigation of the Transition Mechanism From Stable Flame to Flashback in a Generic Premixed Combustion System With High-Speed Micro-Particle Image Velocimetry and Micro-PLIF Combined With Chemiluminescence Imaging
,”
ASME J. Eng. Gas Turbine Power
,
138
(
2
), p.
021501
.10.1115/1.4031227
7.
Ebi
,
D.
, and
Jansohn
,
P.
,
2021
, “
Boundary Layer Flashback Limits of Hydrogen-Methane-Air Flames in a Generic Swirl Burner at Gas Turbine-Relevant Conditions
,”
ASME J. Eng. Gas Turbine Power
,
143
(
8
), p.
081011
.10.1115/1.4049777
8.
Gruber
,
A.
,
Chen
,
J. H.
,
Valiev
,
D.
, and
Law
,
C. K.
,
2012
, “
Direct Numerical Simulation of Premixed Flame Boundary Layer Flashback in Turbulent Channel Flow
,”
J. Fluid Mech.
,
709
, pp.
516
542
.10.1017/jfm.2012.345
9.
Endres
,
A.
, and
Sattelmayer
,
T.
,
2019
, “
Numerical Investigation of Pressure Influence on the Confined Turbulent Boundary Layer Flashback Process
,”
Fluids
,
4
(
3
), p.
146
.10.3390/fluids4030146
10.
Bailey
,
J. R.
, and
Richardson
,
E. S.
,
2021
, “
DNS Analysis of Boundary Layer Flashback in Turbulent Flow With Wall-Normal Pressure Gradient
,”
Proc. Combust. Inst.
,
38
(
2
), pp.
2791
2799
.10.1016/j.proci.2020.06.004
11.
Xia
,
H.
,
Han
,
W.
,
Wei
,
X.
,
Zhang
,
M.
,
Wang
,
J.
,
Huang
,
Z.
, and
Hasse
,
C.
,
2023
, “
Numerical Investigation of Boundary Layer Flashback of CH 4/H 2/Air Swirl Flames Under Different Thermal Boundary Conditions in a Bluff–Body Swirl Burner
,”
Proc. Combust. Inst.
,
39
(
4
), pp.
4541
4551
.10.1016/j.proci.2022.07.040
12.
Lin
,
Y.-C.
,
Daniele
,
S.
,
Jansohn
,
P.
, and
Boulouchos
,
K.
,
2013
, “
Turbulent Flame Speed as an Indicator for Flashback Propensity of Hydrogen-Rich Fuel Gases
,”
ASME J. Eng. Gas Turbine Power
,
135
(
11
), p.
111503
.10.1115/1.4025068
13.
Hoferichter
,
V.
,
Hirsch
,
C.
, and
Sattelmayer
,
T.
,
2017
, “
Prediction of Confined Flame Flashback Limits Using Boundary Layer Separation Theory
,”
ASME J. Eng. Gas Turbine Power
,
139
(
2
), p.
021505
.10.1115/1.4034237
14.
Björnsson
,
Ó. H.
,
Klein
,
S. A.
, and
Tober
,
J.
,
2021
, “
Boundary Layer Flashback Model for Hydrogen Flames in Confined Geometries Including the Effect of Adverse Pressure Gradient
,”
ASME J. Eng. Gas Turbine Power
,
143
(
6
), p.
061003
.10.1115/1.4048566
15.
Novoselov
,
A. G.
,
Ebi
,
D.
, and
Noiray
,
N.
,
2022
, “
Accurate Prediction of Confined Turbulent Boundary Layer Flashback Through a Critically Strained Flame Model
,”
ASME J. Eng. Gas Turbine Power
,
144
(
10
), p.
101013
.10.1115/1.4055413
16.
Vance
,
F. H.
,
de Goey
,
L.
, and
van Oijen
,
J. A.
,
2022
, “
Development of a Flashback Correlation for Burner-Stabilized Hydrogen-Air Premixed Flames
,”
Combust. Flame
,
243
, p.
112045
.10.1016/j.combustflame.2022.112045
17.
Lieuwen
,
T.
,
McDonell
,
V.
,
Santavicca
,
D.
, and
Sattelmayer
,
T.
,
2008
, “
Burner Development and Operability Issues Associated With Steady Flowing Syngas Fired Combustors
,”
Combust. Sci. Technol.
,
180
(
6
), pp.
1169
1192
.10.1080/00102200801963375
18.
Kalantari
,
A.
, and
McDonell
,
V.
,
2017
, “
Boundary Layer Flashback of Non-Swirling Premixed Flames: Mechanisms, Fundamental Research, and Recent Advances
,”
Prog. Energy Combust. Sci.
,
61
, pp.
249
292
.10.1016/j.pecs.2017.03.001
19.
Iannitelli
,
M.
,
Allegorico
,
C.
,
Garau
,
F.
, and
Capanni
,
M.
,
2018
, “
A Hybrid Model for on-Line Detection of Gas Turbine Lean Blowout Events
,”
Phm Society European Conference
, Utrecht, The Netherlands, July 3–6, Vol.
4
(
1
), pp.
1
8
.https://papers.phmsociety.org/index.php/phme/article/download/405/phmec_18_405
20.
Lapeyre
,
C. J.
,
Misdariis
,
A.
,
Cazard
,
N.
,
Veynante
,
D.
, and
Poinsot
,
T.
,
2019
, “
Training Convolutional Neural Networks to Estimate Turbulent Sub-Grid Scale Reaction Rates
,”
Combust. Flame
,
203
, pp.
255
264
.10.1016/j.combustflame.2019.02.019
21.
Bode
,
M.
,
Gauding
,
M.
,
Lian
,
Z.
,
Denker
,
D.
,
Davidovic
,
M.
,
Kleinheinz
,
K.
,
Jitsev
,
J.
, and
Pitsch
,
H.
,
2021
, “
Using Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks for Subfilter Modeling in Turbulent Reactive Flows
,”
Proc. Combust. Inst.
,
38
(
2
), pp.
2617
2625
.10.1016/j.proci.2020.06.022
22.
Bury
,
T. M.
,
Sujith
,
R. I.
,
Pavithran
,
I.
,
Scheffer
,
M.
,
Lenton
,
T. M.
,
Anand
,
M.
, and
Bauch
,
C. T.
,
2021
, “
Deep Learning for Early Warning Signals of Tipping Points
,”
Proc. Natl. Acad. Sci. U. S. A.
,
118
(
39
), p.
e2106140118
.10.1073/pnas.2106140118
23.
Hasti
,
V. R.
,
Navarkar
,
A.
, and
Gore
,
J. P.
,
2021
, “
A Data-Driven Approach Using Machine Learning for Early Detection of the Lean Blowout
,”
Energy AI
,
5
, p.
100099
.10.1016/j.egyai.2021.100099
24.
Gangopadhyay
,
T.
,
Ramanan
,
V.
,
Akintayo
,
A.
,
Boor
,
P. K.
,
Sarkar
,
S.
,
Chakravarthy
,
S. R.
, and
Sarkar
,
S.
,
2021
, “
3D Convolutional Selective Autoencoder for Instability Detection in Combustion Systems
,”
Energy AI
,
4
, p.
100067
.10.1016/j.egyai.2021.100067
25.
Bahashwan
,
A. A.
,
Ibrahim
,
R. B.
,
Omar
,
M. B.
, and
Faqih
,
M.
,
2022
, “
The Lean Blowout Prediction Techniques in Lean Premixed Gas Turbine: An Overview
,”
Energies
,
15
(
22
), p.
8343
.10.3390/en15228343
26.
Ihme
,
M.
,
Chung
,
W. T.
, and
Mishra
,
A. A.
,
2022
, “
Combustion Machine Learning: Principles, Progress and Prospects
,”
Prog. Energy Combust. Sci.
,
91
, p.
101010
.10.1016/j.pecs.2022.101010
27.
Yadav
,
V.
,
Casel
,
M.
, and
Ghani
,
A.
,
2023
, “
Physics-Informed Recurrent Neural Networks for Linear and Nonlinear Flame Dynamics
,”
Proc. Combust. Inst.
,
39
(
2
), pp.
1597
1606
.10.1016/j.proci.2022.08.036
28.
Ruff
,
L.
,
Kauffmann
,
J. R.
,
Vandermeulen
,
R. A.
,
Montavon
,
G.
,
Samek
,
W.
,
Kloft
,
M.
,
Dietterich
,
T. G.
, and
Muller
,
K.-R.
,
2021
, “
A Unifying Review of Deep and Shallow Anomaly Detection
,”
Proc. IEEE
,
109
(
5
), pp.
756
795
.10.1109/JPROC.2021.3052449
29.
Principi
,
E.
,
Vesperini
,
F.
,
Squartini
,
S.
, and
Piazza
,
F.
, “
Acoustic Novelty Detection With Adversarial Autoencoders
,” 2017 International Joint Conference on Neural Networks (
IJCNN
), Anchorage, AK, May 14–19, pp.
3324
3330
.10.1109/IJCNN.2017.7966273
30.
Gal
,
Y.
, and
Ghahramani
,
Z.
,
2015
, “
Bayesian Convolutional Neural Networks With Bernoulli Approximate Variational Inference
,”
arXiv:1506.02158
.10.48550/arXiv.1506.02158
31.
Chen
,
J.
,
Sathe
,
S.
,
Aggarwal
,
C.
, and
Turaga
,
D.
,
2017
, “
Outlier Detection With Autoencoder Ensembles
,”
Proceedings of the 2017 SIAM International Conference on Data Mining
, Houston, TX, Apr. 27–29, pp.
90
98
.10.1137/1.9781611974973.11
32.
Pang
,
G.
,
Shen
,
C.
,
Cao
,
L.
, and
den van Hengel
,
A.
,
2022
, “
Deep Learning for Anomaly Detection
,”
ACM Comput. Surv.
,
54
(
2
), pp.
1
38
.10.1145/3439950
33.
Baur
,
C.
,
Wiestler
,
B.
,
Albarqouni
,
S.
, and
Navab
,
N.
,
2019
, “
Deep Autoencoding Models Unsupervised Anomaly Segmentation Brain MR Images
,”
BrainLesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
, BrainLes 2018, Granada, Spaindate, Sept. 16, Vol.
11383
(
9
), pp.
161
169
.10.1007/978-3-030-11723-8_16
34.
Wang
,
P.
,
Fan
,
E.
, and
Wang
,
P.
,
2021
, “
Comparative Analysis of Image Classification Algorithms Based on Traditional Machine Learning and Deep Learning
,”
Pattern Recognit. Lett.
,
141
, pp.
61
67
.10.1016/j.patrec.2020.07.042
35.
Barbedo
,
J. G. A.
,
2018
, “
Impact of Dataset Size and Variety on the Effectiveness of Deep Learning and Transfer Learning for Plant Disease Classification
,”
Comput. Electron. Agric.
,
153
, pp.
46
53
.10.1016/j.compag.2018.08.013
36.
Korotcov
,
A.
,
Tkachenko
,
V.
,
Russo
,
D. P.
, and
Ekins
,
S.
,
2017
, “
Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets
,”
Mol. Pharm.
,
14
(
12
), pp.
4462
4475
.10.1021/acs.molpharmaceut.7b00578
37.
Wang
,
Z.
,
Bovik
,
A. C.
,
Sheikh
,
H. R.
, and
Simoncelli
,
E. P.
,
2004
, “
Image Quality Assessment: From Error Visibility to Structural Similarity
,”
IEEE Trans. Image Process.
,
13
(
4
), pp.
600
612
.10.1109/TIP.2003.819861
38.
Brunton
,
S. L.
, and
Kutz
,
J. N.
,
2022
,
Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
,
Cambridge University Press
, Cambridge, UK.
39.
Sari
,
S.
,
Roslan
,
H.
, and
Shimamura
,
T.
,
2012
, “
Noise Estimation by Utilizing Mean Deviation of Smooth Region in Noisy Image
,”
Fourth International Conference on Computational Intelligence, Modelling and Simulation
, Kuantan, Malaysia, Sept. 25–27, pp.
232
236
.10.1109/CIMSim.2012.89
40.
Gilchrist
,
W.
,
2000
,
Statistical Modelling With Quantile Functions
,
Chapman and Hall/CRC
, Boca Raton, FL.
You do not currently have access to this content.