Abstract

Transfer learning (TL) is a machine learning (ML) tool where the knowledge, acquired from a source domain, is “transferred” to perform a task in a target domain that has (to some extent) a similar setting. The underlying concept does not require the ML method to analyze a new problem from the beginning, and thereby both the learning time and the amount of required target-domain data are reduced for training. An example is the occurrence of thermoacoustic instability (TAI) in combustors, which may cause pressure oscillations, possibly leading to flame extinction as well as undesirable vibrations in the mechanical structures. In this situation, it is difficult to collect useful data from industrial combustion systems, due to the transient nature of TAI phenomena. A feasible solution is the usage of prototypes or emulators, like a Rijke tube, to produce largely similar phenomena. This paper proposes symbolic time-series analysis (STSA)-based TL, where the key idea is to develop a capability of discrimination between stable and unstable operations of a combustor, based on the time-series of pressure oscillations from a data source that contains sufficient information, even if it is not the target regime, and then transfer the learnt models to the target regime. The proposed STSA-based pattern classifier is trained on a previously validated numerical model of a Rijke-tube apparatus. The knowledge of this trained classifier is transferred to classify similar operational regimes in: (i) an experimental Rijke-tube apparatus and (ii) an experimental combustion system apparatus. Results of the proposed TL have been validated by comparison with those of two shallow neural networks (NNs)-based TL and another NN having an additional long short-term memory (LSTM) layer, which serve as benchmarks, in terms of classification accuracy and computational complexity.

References

1.
Pan
,
S. J.
, and
Yang
,
Q.
,
2010
, “
A Survey on Transfer Learning
,”
IEEE Trans. Knowl. Data Eng.
,
22
(
10
), pp.
1345
1359
.10.1109/TKDE.2009.191
2.
Zhuang
,
F.
,
Qi
,
Z.
,
Duan
,
K.
,
Xi
,
D.
,
Zhu
,
Y.
,
Zhu
,
H.
,
Xiong
,
H.
, and
He
,
Q.
,
2020
, “
A Comprehensive Survey on Transfer Learning
,”
Proc. IEEE
, 109(1), pp.
43
76
.10.1109/JPROC.2020.3004555
3.
Raghu
,
M.
,
Zhang
,
C.
,
Kleinberg
,
J.
, and
Bengio
,
S.
,
2019
, “
Transfusion: Understanding Transfer Learning for Medical Imaging
,”
Advances in Neural Information Processing Systems
, Vancouver, Canada, Dec. 8–14, pp.
3347
3357
.
4.
Cai
,
C.
,
Wang
,
S.
,
Xu
,
Y.
,
Zhang
,
W.
,
Tang
,
K.
,
Ouyang
,
Q.
,
Lai
,
L.
, and
Pei
,
J.
,
2020
, “
Transfer Learning for Drug Discovery
,”
J. Med. Chem.
,
63
(
16
), pp.
8683
8694
.10.1021/acs.jmedchem.9b02147
5.
Ruder
,
S.
,
Peters
,
M. E.
,
Swayamdipta
,
S.
, and
Wolf
,
T.
,
2019
, “
Transfer Learning in Natural Language Processing
,”
Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics
: Tutorials, Minneapolis, MN, June 2–7, pp.
15
18
.
6.
Banerjee
,
B.
, and
Stone
,
P.
,
2007
, “
General Game Learning Using Knowledge Transfer
,”
IJCAI
, Hyderabad, India, Jan. 6–12, pp.
672
677
.
7.
Fan
,
Y.
,
Nowaczyk
,
S.
, and
Rögnvaldsson
,
T.
,
2020
, “
Transfer Learning for Remaining Useful Life Prediction Based on Consensus Self-Organizing Models
,”
Reliab. Eng. Syst. Saf.
,
203
, p.
107098
.10.1016/j.ress.2020.107098
8.
Murphy
,
K.
,
2012
,
Machine Learning: A Probabilistic Perspective
,
The MIT Press
,
Cambridge, MA
.
9.
Matveev
,
K. I.
, and
Culick
,
F.
,
2003
, “
A Model for Combustion Instability Involving Vortex Shedding
,”
Combust. Sci. Technol.
,
175
(
6
), pp.
1059
1083
.10.1080/00102200302349
10.
Culick
,
F.
,
1988
, “
Combustion Instabilities in Liquid-Fuelled Propulsion Systems
,” Caltech, Neuilly Sur Seine, France, Report No. AGARD-CP-450.
11.
Rayleigh
,
J. W. S.
,
1845
,
The Theory of Sound
,
Dover Publications
,
New York
.
12.
Rijke
,
P. L.
,
1859
, “
Notiz Über Eine Neue Art, Die in Einer an Beiden Enden Offenen Röhre Enthaltene Luft in Schwingungen zu Versetzen
,”
Ann. Phys.
,
183
(
6
), pp.
339
343
.10.1002/andp.18591830616
13.
Sarkar
,
S.
,
Lore
,
K. G.
,
Sarkar
,
S.
,
Ramanan
,
V.
,
Chakravarthy
,
S. R.
,
Phoha
,
S.
, and
Ray
,
A.
,
2015
, “
Early Detection of Combustion Instability From Hi-Speed Flame Images Via Deep Learning and Symbolic Time Series Analysis
,”
Annual Conference of the Prognostics and Health Management Society
, Coronado, CA, Oct. 18–22, pp.
353
362
.
14.
Bhattacharya
,
C.
,
De
,
S.
,
Mukhopadhyay
,
A.
,
Sen
,
S.
, and
Ray
,
A.
,
2020
, “
Detection and Classification of Lean Blow-Out and Thermoacoustic Instability in Turbulent Combustors
,”
Appl. Therm. Eng.
,
180
, p.
115808
.10.1016/j.applthermaleng.2020.115808
15.
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
16.
Mondal
,
S.
,
Bhattacharya
,
C.
,
Chattopadhyay
,
P.
,
Mukhopadhyay
,
A.
, and
Ray
,
A.
,
2017
, “
Prediction of Thermoacoustic Instabilities in a Premixed Combustor Based on FFT-Based Dynamic Characterization
,”
AIAA
Paper No. 2017-4892.10.2514/6.2017-4892
17.
Kobayashi
,
T.
,
Murayama
,
S.
,
Hachijo
,
T.
, and
Gotoda
,
H.
,
2019
, “
Early Detection of Thermoacoustic Combustion Instability Using a Methodology Combining Complex Networks and Machine Learning
,”
Phys. Rev. Appl.
,
11
(
6
), p.
064034
.10.1103/PhysRevApplied.11.064034
18.
Sen
,
U.
,
Gangopadhyay
,
T.
,
Bhattacharya
,
C.
,
Mukhopadhyay
,
A.
, and
Sen
,
S.
,
2018
, “
Dynamic Characterization of a Ducted Inverse Diffusion Flame Using Recurrence Analysis
,”
Combust. Sci. Technol.
,
190
(
1
), pp.
32
56
.10.1080/00102202.2017.1374952
19.
Kasthuri
,
P.
,
Pavithran
,
I.
,
Pawar
,
S. A.
,
Sujith
,
R.
,
Gejji
,
R.
, and
Anderson
,
W.
,
2019
, “
Dynamical Systems Approach to Study Thermoacoustic Transitions in a Liquid Rocket Combustor
,”
Chaos: Interdiscip. J. Nonlinear Sci.
,
29
(
10
), p.
103115
.10.1063/1.5120429
20.
Silva
,
C. F.
,
Magri
,
L.
,
Runte
,
T.
, and
Polifke
,
W.
,
2017
, “
Uncertainty Quantification of Growth Rates of Thermoacoustic Instability by an Adjoint Helmholtz Solver
,”
ASME J. Eng. Gas Turbines Power
,
139
(
1
), p.
011901
.10.1115/1.4034203
21.
Magri
,
L.
,
2019
, “
Adjoint Methods as Design Tools in Thermoacoustics
,”
ASME Appl. Mech. Rev.
,
71
(
2
), p.
020801
.10.1115/1.4042821
22.
Dupont
,
P.
,
Denis
,
F.
, and
Esposito
,
Y.
,
2005
, “
Links Between Probabilistic Automata and Hidden Markov Models: Probability Distributions, Learning Models and Induction Algorithms
,”
Pattern Recognit.
,
38
(
9
), pp.
1349
1371
.10.1016/j.patcog.2004.03.020
23.
Ray
,
A.
,
2004
, “
Symbolic Dynamic Analysis of Complex Systems for Anomaly Detection
,”
Signal Process.
,
84
(
7
), pp.
1115
1130
.10.1016/j.sigpro.2004.03.011
24.
Mukherjee
,
K.
, and
Ray
,
A.
,
2014
, “
State Splitting and Merging in Probabilistic Finite State Automata for Signal Representation and Analysis
,”
Signal Process.
,
104
, pp.
105
119
.10.1016/j.sigpro.2014.03.045
25.
Daw
,
C. S.
,
Finney
,
C. E. A.
, and
Tracy
,
E. R.
,
2003
, “
A Review of Symbolic Analysis of Experimental Data
,”
Rev. Sci. Instrum.
,
74
(
2
), pp.
915
930
.10.1063/1.1531823
26.
Bhattacharya
,
C.
, and
Ray
,
A.
,
2020
, “
Online Discovery and Classification of Operational Regimes From an Ensemble of Time Series Data
,”
ASME J. Dyn. Syst., Meas., Control
,
142
(
11
), p.
114501
.10.1115/1.4047449
27.
Bhattacharya
,
C.
,
O'Connor
,
J.
, and
Ray
,
A.
,
2020
, “
Data-Driven Detection and Early Prediction of Thermoacoustic Instability in a Multi-Nozzle Combustor
,”
Combust. Sci. Technol.
, In press, pp.
1
32
. 10.1080/00102202.2020.1820495
28.
Berman
,
A.
, and
Plemmons
,
R.
,
1994
,
Nonnegative Matrices in the Mathematical Sciences
,
SIAM
,
Philadelphia, PA
.
29.
Bhattacharya
,
C.
,
Mondal
,
S.
,
Ray
,
A.
, and
Mukhopadhyay
,
A.
,
2020
, “
Reduced-Order Modelling of Thermoacoustic Instabilities in a Two-Heater Rijke Tube
,”
Combust. Theory Modell.
,
24
(
3
), pp.
530
548
.10.1080/13647830.2020.1714080
30.
Kim
,
K. T.
, and
Santavicca
,
D. A.
,
2013
, “
Interference Mechanisms of Acoustic/Convective Disturbances in a Swirl-Stabilized Lean-Premixed Combustor
,”
Combust. Flame
,
160
(
8
), pp.
1441
1457
.10.1016/j.combustflame.2013.02.022
31.
Culick
,
F.
,
1976
, “
Nonlinear Behavior of Acoustic Waves in Combustion Chambers—I
,”
Acta Astronaut.
,
3
(
9–10
), pp.
715
734
.10.1016/0094-5765(76)90107-7
32.
Heckl
,
M. A.
,
1988
, “
Active Control of the Noise From a Rijke Tube
,”
J. Sound Vib.
,
124
(
1
), pp.
117
133
.10.1016/S0022-460X(88)81408-1
33.
Matveev
,
K. I.
,
2003
, “
Thermoacoustic Instabilities in the Rijke Tube: Experiments and Modeling
,” Ph.D. thesis,
California Institute of Technology
, Pasadena, CA.
34.
Heckl
,
M. A.
,
1990
, “
Non-Linear Acoustic Effects in the Rijke Tube
,”
Acustica
,
72
, pp.
63
71
.
35.
Rajagopalan
,
V.
, and
Ray
,
A.
,
2006
, “
Symbolic Time Series Analysis Via Wavelet-Based Partitioning
,”
Signal Process.
,
86
(
11
), pp.
3309
3320
.10.1016/j.sigpro.2006.01.014
36.
Ghalyan
,
N. F.
, and
Ray
,
A.
,
2020
, “
Symbolic Time Series Analysis for Anomaly Detection in Measure-Invariant Ergodic Systems
,”
ASME J. Dyn. Syst., Meas., Control
,
142
(
6
), p.
061003
.10.1115/1.4046156
37.
Ghalyan
,
N. F.
, and
Ray
,
A.
,
2021
, “
Measure Invariance of Ergodic Symbolic Systems for Low-Delay Detection of Anomalous Events
,”
Mech. Syst. Signal Process.
,
159
, p.
107746
.10.1016/j.ymssp.2021.107746
38.
Bhattacharya
,
C.
,
Dharmadhikari
,
S.
,
Basak
,
A.
, and
Ray
,
A.
,
2021
, “
Early Detection of Fatigue Crack Damage in Ductile Materials: A Projection-Based Probabilistic Finite State Automata Approach
,”
ASME Lett. Dyn. Syst. Control
,
1
(
4
), p.
041003
.10.1115/1.4050183
39.
Karim
,
F.
,
Majumdar
,
S.
, and
Darabi
,
H.
,
2019
, “
Insights Into LSTM Fully Convolutional Networks for Time Series Classification
,”
IEEE Access
,
7
, pp.
67718
67725
.10.1109/ACCESS.2019.2916828
40.
Cao
,
J.
,
Li
,
Z.
, and
Li
,
J.
,
2019
, “
Financial Time Series Forecasting Model Based on CEEMDAN and LSTM
,”
Phys. A: Stat. Mech. Appl.
,
519
, pp.
127
139
.10.1016/j.physa.2018.11.061
You do not currently have access to this content.