Combustion mode analysis is essential to a rocket-based combined cycle (RBCC) combustor because it may experience multiple combustion modes during the operation. In this study, a method based on an autoencoder and a K-means algorithm was proposed for combustion mode analysis. Flame chemiluminescence images and schlieren images of three combustion modes observed in an RBCC combustor were used to evaluate this method. Two autoencoders that followed the same encoder–decoder architecture were developed separately to generate the latent space representations of flame chemiluminescence images and schlieren images. In the latent space, the centroids and boundaries of different combustion modes were determined using the K-means algorithm. Each autoencoder was trained using 750 images and tested using another 3000 images. The method achieved an accuracy up to 99% on both flame chemiluminescence images and schlieren images. The images generated by the decoder suggested that the autoencoder captured the important features (e.g., primary reaction zone and shock wave) of the reacting flow field. The autoencoder developed for flame chemiluminescence images also successfully detected the combustion mode transition during an ignition process, which suggested that it had the potential to monitor the combustion mode in a real time manner. However, the autoencoder failed on monitoring combustion mode transition when it came to the schlieren images because the optical access of the training data was not exactly the same. Therefore, it is essential to ensure that the optical accesses of different combustion modes are exactly the same when schlieren images are employed for combustion mode analysis.

1.
R.
Daines
and
C.
Segal
, “
Combined rocket and airbreathing propulsion systems for space-launch applications
,”
J. Propul. Power
14
,
605
(
1998
).
2.
L.
Yang
,
B.
An
,
J.
Liang
,
X.
Li
, and
Z.
Wang
, “
Dual-pulse laser ignition of ethylene-air mixtures in a supersonic combustor
,”
Opt. Express
26
,
7911
(
2018
).
3.
G.
Li
,
M.
Sun
,
J.
Yu
,
C.
Liang
,
Y.
Liu
,
G.
Zhao
, and
Y.
Huang
, “
Effect of injection Mach number on penetration in a supersonic crossflow
,”
AIAA J.
58
,
1216
(
2020
).
4.
S.
Saxena
,
M. S. P.
Kahandawala
, and
S. S.
Sidhu
, “
A shock tube study of ignition delay in the combustion of ethylene
,”
Combust. Flame
158
,
1019
(
2011
).
5.
T.
Wang
,
Z.
Wang
,
Z.
Cai
,
M.
Sun
,
H.
Wang
,
Y.
Sun
,
Y.
Yang
,
P.
Li
, and
Y.
Huang
, “
Combustion characteristics in scramjet combustor operating at different inflow stagnation pressures
,”
AIAA J.
60
,
4544
(
2022
).
6.
F. W.
Barnes
and
C.
Segal
, “
Cavity-based flameholding for chemically-reacting supersonic flows
,”
Prog. Aerosp. Sci.
76
,
24
(
2015
).
7.
J.
Lee
,
N.
Yokev
, and
D.
Michaels
, “
Combustion instability due to combustion mode transition in a cavity-stabilized scramjet
,”
J. Propul. Power
38
,
945
(
2022
).
8.
L.
Elkowitz
,
A.
Wanchek
,
R.
Rockwell
,
C. P.
Goyne
,
C. E.
Dedic
, “
Q.
Le
,
J.
Walters-Williams
, and
D.
Hunt
,
Dual-mode scramjet control using optical emission sensors
,” AIAA Paper 2023–0120,
2023
.
9.
T.
Ombrello
,
D. L.
Blunck
, and
M.
Resor
, “
Quantified infrared imaging of ignition and combustion in a supersonic flow
,”
Exp. Fluids
57
,
140
(
2016
).
10.
J.
Kiefer
,
Z.
Li
,
J.
Zetterberg
,
X.
Bai
, and
M.
Aldén
, “
Investigation of local flame structures and statistics in partially premixed turbulent jet flames using simultaneous single-shot CH and OH planar laser-induced fluorescence imaging
,”
Combust. Flame
154
,
802
(
2008
).
11.
D. J.
Micka
and
J. F.
Driscoll
, “
Combustion characteristics of a dual-mode scramjet combustor with cavity flameholder
,”
Proc. Combust. Inst.
32
,
2397
(
2009
).
12.
H.
Wang
,
Z.
Wang
,
M.
Sun
, and
H.
Wu
, “
Combustion modes of hydrogen jet combustion in a cavity-based supersonic combustor
,”
Int. J. Hydrogen Energ.
38
,
12078
(
2013
).
13.
B.
An
,
L.
Yang
,
Z.
Wang
,
X.
Li
,
M.
Sun
,
J.
Zhu
, and
W.
Yan
, “
Characteristics of laser ignition and spark discharge ignition in a cavity-based supersonic combustor
,”
Combust. Flame
212
,
177
(
2020
).
14.
B.
An
,
Z.
Wang
, and
M.
Sun
, “
Flame stabilization enhancement by microjet-based virtual shock wave generators in a supersonic combustor
,”
Phys. Fluids
33
,
016104
(
2021
).
15.
B.
An
,
Z.
Wang
, and
M.
Sun
, “
Ignition dynamics and combustion mode transitions in a rocket-based combined cycle combustor operating in the ramjet/scramjet mode
,”
Aerosp. Sci. Technol.
118
,
106951
(
2021
).
16.
T.
Wang
,
Z.
Cai
,
B.
An
,
J.
Wang
,
M.
Sun
,
C.
Liang
, and
Z.
Wang
, “
Behaviors of the reacting flowfield during the spontaneous formation of ramjet mode under a supersonic inflow
,”
Phys. Fluids
35
,
024105
(
2023
).
17.
B.
An
,
M.
Sun
,
Z.
Wang
, and
J.
Chen
, “
Cavity flameholding subjected to an expansion fan in a rocket-based combined cycle combustor
,”
Aerosp. Sci. Technol.
106
,
106180
(
2020
).
18.
B.
Xiao
,
J.
Xing
,
Y.
Tian
, and
X.
Wang
, “
Experimental and numerical investigations of combustion mode transition in a direct-connect scramjet combustor
,”
Aerosp. Sci. Technol.
46
,
331
(
2015
).
19.
X.
Deng
,
M.
Guo
,
Y.
Tian
,
L.
Li
,
J.
Le
,
H.
Zhang
, and
F.
Zhong
, “
Reconstructing the self-luminous image of a flame in a supersonic combustor based on residual network reconstruction algorithm
,”
Phys. Fluids
35
,
025129
(
2023
).
20.
E.
Chen
,
M.
Guo
,
Y.
Tian
,
Y.
Zhang
,
H.
Chen
,
J.
Le
,
F.
Zhong
, and
H.
Zhang
, “
Flame development prediction of supersonic combustion flow based on lightweight cascaded convolutional neural network
,”
Phys. Fluids
35
,
025134
(
2023
).
21.
X.
Deng
,
M.
Guo
,
H.
Chen
,
Y.
Tian
,
J.
Le
, and
H.
Zhang
, “
Dual-path flow field reconstruction for a scramjet combustor based on deep learning
,”
Phys. Fluids
34
,
095118
(
2022
).
22.
H.
Li
and
J.
Tan
, “
Cluster-based Markov model to understand the transition dynamics of a supersonic mixing layer
,”
Phys. Fluids
32
,
056104
(
2020
).
23.
C.
Fujio
,
K.
Akiyama
, and
H.
Ogawa
, “
Fast and reliable prediction of scramjet flowfields via Gaussian process latent variable model and deep learning
,”
Phys. Fluids
35
,
046120
(
2023
).
24.
B.
Liu
,
J.
Tang
,
H.
Huang
, and
X.
Lu
, “
Deep learning methods for super-resolution reconstruction of turbulent flows
,”
Phys. Fluids
32
,
025105
(
2020
).
You do not currently have access to this content.