Abstract

Modern low-emission combustion systems with improved fuel-air mixing are more prone to combustion instabilities and, therefore, use advanced control methods to balance minimum NOx emissions and the presence of thermoacoustic combustion instabilities. The exact operating conditions at which the system encounters an instability are uncertain because of sources of stochasticity, such as turbulent combustion, and the influence of hidden variables, such as unmeasured wall temperatures or differences in machine geometry within manufacturing tolerances. Practical systems tend to be more elaborate than laboratory systems and tend to have less instrumentation, meaning that they suffer more from uncertainty induced by hidden variables. In many commercial systems, the only direct measurement of the combustor comes from a dynamic pressure sensor. In this study, we train a Bayesain Neural Network to predict the probability of onset of thermoacoustic instability at various times in the future, using only dynamic pressure measurements and the current operating condition. We show that on a practical system, the error in the onset time predicted by the Bayesain Neural Networks is 45% lower than the error when using the operating condition alone and more informative than the warning provided by commonly used precursor detection methods. This is demonstrated on two systems: (i) a premixed hydrogen/methane annular combustor, where the hidden variables are wall temperatures that depend on the rate of change of operating condition, and (ii) full-scale prototype combustion system, where the hidden variables arise from differences between the systems.

References

1.
Smith
,
K.
, and
Blust
,
J.
,
2005
, “
Combustion Instabilities in Industrial Gas Turbines: Solar Turbines' Experience
,”
Prog. Astronaut. Aeronaut.
,
210
(
1
), pp.
29
41
.10.2514/5.9781600866807.0029.0041
2.
Foust
,
M.
,
Thomsen
,
D.
,
Stickles
,
R.
,
Cooper
,
C.
, and
Dodds
,
W.
,
2012
, “
Development of the GE Aviation Low Emissions TAPS Combustor for Next Generation Aircraft Engines
,”
AIAA Paper No. 2012-0936
.10.2514/6.2012-936
3.
Juniper
,
M. P.
, and
Sujith
,
R.
,
2018
, “
Sensitivity and Nonlinearity of Thermoacoustic Oscillations
,”
Annu. Rev. Fluid Mech.
,
50
(
1
), pp.
661
689
.10.1146/annurev-fluid-122316-045125
4.
Dakos
,
V.
,
Carpenter
,
S. R.
,
Brock
,
W. A.
,
Ellison
,
A. M.
,
Guttal
,
V.
,
Ives
,
A. R.
,
Kéfi
,
S.
,
Livina
,
V.
,
Seekell
,
D. A.
,
van Nes
,
E. H.
, and
Scheffer
,
M.
,
2012
, “
Methods for Detecting Early Warnings of Critical Transitions in Time Series Illustrated Using Simulated Ecological Data
,”
PLoS One
,
7
(
7
), p.
e41010
.10.1371/journal.pone.0041010
5.
Gotoda
,
H.
,
Miyano
,
T.
, and
Shepherd
,
I. G.
,
2010
, “
Dynamic Properties of Unstable Motion of Swirling Premixed Flames Generated by a Change in Gravitational Orientation
,”
Phys. Rev. E
,
81
(
2
), p.
026211
.10.1103/PhysRevE.81.026211
6.
Gotoda
,
H.
,
Ikawa
,
T.
,
Maki
,
K.
, and
Miyano
,
T.
,
2012
, “
Short-Term Prediction of Dynamical Behavior of Flame Front Instability Induced by Radiative Heat Loss
,”
Chaos: Interdiscip. J. Nonlinear Sci.
,
22
(
3
), p.
033106
.10.1063/1.4731267
7.
Sarkar
,
S.
,
Chakravarthy
,
S. R.
,
Ramanan
,
V.
, and
Ray
,
A.
,
2016
, “
Dynamic Data-Driven Prediction of Instability in a Swirl-Stabilized Combustor
,”
Int. J. Spray Combust. Dyn.
,
8
(
4
), pp.
235
253
.10.1177/1756827716642091
8.
Murugesan
,
M.
, and
Sujith
,
R. I.
,
2016
, “
Detecting the Onset of an Impending Thermoacoustic Instability Using Complex Networks
,”
J. Propul. Power
,
32
(
3
), pp.
707
712
.10.2514/1.B35914
9.
Scheffer
,
M.
,
Bascompte
,
J.
,
Brock
,
W. A.
,
Brovkin
,
V.
,
Carpenter
,
S. R.
,
Dakos
,
V.
,
Held
,
H.
,
Van Nes
,
E. H.
,
Rietkerk
,
M.
, and
Sugihara
,
G.
,
2009
, “
Early-Warning Signals for Critical Transitions
,”
Nature
,
461
(
7260
), pp.
53
59
.10.1038/nature08227
10.
Nair
,
V.
, and
Sujith
,
R.
,
2014
, “
Multifractality in Combustion Noise: Predicting an Impending Combustion Instability
,”
J. Fluid Mech.
,
747
(
1
), pp.
635
655
.10.1017/jfm.2014.171
11.
Gotoda
,
H.
,
Nikimoto
,
H.
,
Miyano
,
T.
, and
Tachibana
,
S.
,
2011
, “
Dynamic Properties of Combustion Instability in a Lean Premixed Gas-Turbine Combustor
,”
Chaos Interdiscip. J. Nonlinear Sci.
,
21
(
1
), p.
013124
.10.1063/1.3563577
12.
Jha
,
D. K.
,
Virani
,
N.
, and
Ray
,
A.
,
2018
, “
Markov Modeling of Time Series Via Spectral Analysis for Detection of Combustion Instabilities
,”
Handbook of Dynamic Data Driven Applications Systems
,
Springer International Publishing
, Cham, Switzerland, pp.
123
138
.10.1007/978-3-319-95504-9_6
13.
Mondal
,
S.
,
Ghalyan
,
N. F.
,
Ray
,
A.
, and
Mukhopadhyay
,
A.
,
2019
, “
Early Detection of Thermoacoustic Instabilities Using Hidden Markov Models
,”
Combust. Sci. Technol.
,
191
(
8
), pp.
1309
1336
.10.1080/00102202.2018.1523900
14.
Hachijo
,
T.
,
Masuda
,
S.
,
Kurosaka
,
T.
, and
Gotoda
,
H.
,
2019
, “
Early Detection of Thermoacoustic Combustion Oscillations Using a Methodology Combining Statistical Complexity and Machine Learning
,”
Chaos Interdiscip. J. Nonlinear Sci.
,
29
(
10
), p.
103123
.10.1063/1.5120815
15.
McCartney
,
M.
,
Indlekofer
,
T.
, and
Polifke
,
W.
,
2020
, “
Online Prediction of Combustion Instabilities Using Machine Learning
,”
ASME Paper No. GT2020-14834
.10.1115/GT2020-14834
16.
Indlekofer
,
T.
,
Faure-Beaulieu
,
A.
,
Noiray
,
N.
, and
Dawson
,
J.
,
2021
, “
The Effect of Dynamic Operating Conditions on the Thermoacoustic Response of Hydrogen Rich Flames in an Annular Combustor
,”
Combust. Flame
,
223
(
1
), pp.
284
294
.10.1016/j.combustflame.2020.10.013
17.
Pearce
,
T.
,
Leibfried
,
F.
, and
Brintrup
,
A.
,
2020
, “
Uncertainty in Neural Networks: Approximately Bayesian Ensembling
,”
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics
,
S.
Chiappa
and
R.
Calandra
, eds., Vol.
108
of Proceedings of Machine Learning Research, PMLR, Palermo, Sicily, June 3, pp.
234
244
.http://proceedings.mlr.press/v108/pearce20a/pearce20a.pdf
18.
Goodfellow
,
I.
,
Bengio
,
Y.
, and
Courville
,
A.
,
2016
,
Deep Learning
,
MIT Press
, Cambridge, MA, Chaps.
8
11
.
19.
Welch
,
P.
,
1967
, “
The Use of Fast Fourier Transform for the Estimation of Power Spectra: A Method Based on Time Averaging Over Short, Modified Periodograms
,”
IEEE Trans. Audio Electroacoustics
,
15
(
2
), pp.
70
73
.10.1109/TAU.1967.1161901
20.
Sengupta
,
U.
,
Rasmussen
,
C.
, and
Juniper
,
M.
,
2021
, “
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
21.
Leibig
,
C.
,
Allken
,
V.
,
Ayhan
,
M. S.
,
Berens
,
P.
, and
Wahl
,
S.
,
2017
, “
Leveraging Uncertainty Information From Deep Neural Networks for Disease Detection
,”
Sci. Rep.
,
7
(
1
), Article No. 17816.10.1038/s41598-017-17876-z
22.
Deisenroth
,
M. P.
, and
Rasmussen
,
C. E.
,
2011
, “
Pilco: A Model-Based and Data-Efficient Approach to Policy Search
,”
Proceedings of the 28th International Conference on International Conference on Machine Learning, ICML'11
, Bellevue, WA, Omnipress, June 28–July 2, pp.
465
472
.https://mlg.eng.cam.ac.uk/pub/pdf/DeiRas11.pdf
You do not currently have access to this content.