All Issue

2023 Vol.28, Issue 3 Preview Page

Research Article

Detection of Combustion Instability of Gas Turbine Combustor using Convolutional Autoencoder Model

합성곱 오토인코더 기법을 이용한 가스터빈 연소기의 연소불안정 상태 감지 연구

Junwoo Jung1
,
Daesik Kim1
,
Jaemin Beak1†
정 준우1
,
김 대식1
,
백 재민1†
1Department of Mechanical Engineering, Gangneung-Wonju National University, Korea
1강릉원주대학교 기계공학과
*Corresponding Author
30 September 2023. pp. 11-19
PDF XML Citation
Abstract

This paper presents a method for detecting the system instability in gas turbine combustor. The proposed approach is designed as the convolutional autoencoder technique so that it offers strong attractivity even if it has a very little data. Additionally, given that it is a solution to enhance the learning effect in this system, it also provides convenience of use to practicing engineers. From these benefits, the detection rate of the system instability in the proposed method is improved while in operation, which is compared with that in both a root-mean-square and a zero-crossing approaches as well-known statistic methods.

Keywords
Anomaly detection
Combustion instability
Convolutional autoencoder
Dynamic pressure
Zero crossing rate
References
1
J. Beita, M. Talibi, S. Sadasivuni, R. Balachandran, Thermoacoustic instability considerations for high hydrogen combustion in lean premixed gas turbine combustor, Hydrogen, 2 (2021), 33-57. 10.3390/hydrogen2010003
2
D. Kim, Review on the Development Trend of Hydrogen Gas Turbine Combustion Technology, J. Korean Soc. Combust. 24(4) (2019), 1-10. 10.15231/jksc.2019.24.4.001
3
B. Noble, L. Angello, B. Emerson, T. Lieuwen, Advanced gas turbine combustor health monitoring using combustion dynamics data, high pressure condition, 59th ISA POWID/EPRI Symposium (2016).
4
J. Oh, Y. Yoon, Combustion Instability in Gas Turbine Engines, J. Korean Soc. Propulsion Engineers, 12(4) (2008), 63-77.
5
S. Joo, J. Choi, M. Lee, N. Kim, Prognosis of combustion instability in a gas turbine combustor using spectral centroid & spread, Energy, 224 (2021), 120180. 10.1016/j.energy.2021.120180
6
W. Song, D. Cha, Temporal kurtosis of dynamic pressure signal as a quantitative measure of combustion instability, Appl. Therm. Eng. 104 (2016), 577-586. 10.1016/j.applthermaleng.2016.05.094
7
W. Song, D. Cha, Combustion Instability Assessment Using Temporal Kurtosis of Dynamic Pressure Data, The 48th KOSCO Symposium, (2014), 39-41.
8
S. Choi, J. Baek, D. Kim, Early Diagnosis of Combustion Instability Using Statistical Methods, J. Korean Soc. Combust. 27(3) (2022), 1-7. 10.15231/jksc.2022.27.3.001
9
S. Joo, J. Choi, N. Kim, M. Lee, Zero-crossing rate method as an efficient tool for combustion instability diagnosis, Exp. Therm Fluid Sci. 123 (2021), 110340. 10.1016/j.expthermflusci.2020.110340
10
B. Jun, D. Jang, M. Lee, Combustion instability diagnosis using machine learning methodology of high-speed flame images for the safe operation of a gas turbine combustor, Trans. Korean Soc. Mech. Eng. B 45 (2021), 447-458. 10.3795/KSME-B.2021.45.8.447
11
T. Gangopadhyay, V. Ramanan, A. Akintayo, P.K. Boor, S. Sarkar, S.R. Chakravarthy, S. Sarkar, 3D convolutional selective autoencoder for instability detection in combustion systems, Energy and AI 4 (2021), 100067. 10.1016/j.egyai.2021.100067
12
G. Dong, G. Liao, H. Liu, G. Kuang, A review of the autoencoder and its variants: A comparative perspective from target recognition in synthetic-aperture radar images, IEEE GEOSCI REMOTE M 6 (2018), 44-68. 10.1109/MGRS.2018.2853555
13
C. Fan, F. Xiao, Y. Zhao, J. Wang, Analytical investigation of autoencoder based methoeds for unsupervised anomaly detetion in building energy data, Applied Energy 211 (2018), 1123-1135. 10.1016/j.apenergy.2017.12.005
14
G. Lee, M. Jung, M. Song, J. Choo, Unsupervised anomaly detection of the gas turbine operation via convolutional auto-encoder, 2020 IEEE International Conference on Prognostics and Health Management (2020), 19950224. 10.1109/ICPHM49022.2020.9187054
15
F. Fleurt, François Fleuret's deep-learning courses 14x050, the University of Geneva, Switzerland, Available at https://fleuret.org/francois/
16
C. Lee, S. Lee, P. Kim, Fault detection and diagnosis of chain transmission system using convolutional auto-encoder, Trans. the KSNVE 31 (2021), 563-573. 10.5050/KSNVE.2021.31.5.563
17
J. An, S. Cho, Variational autoencoder based anomaly detection using reconstruction probability, SNU Data Mining Center (2015).
18
Tensorflow 2.9.1, Available at https://www.tensorflow.org.
19
S. Joo, S. Kwak, S. Kim, J. Lee, Y. Yoon, High-frequency transition characteristics of synthetic natural gas combustion in gas turbine, Aeronaut. J. 123 (2019), 138-156. 10.1017/aer.2018.150
Information
  • Publisher :The Korean Society of Combustion
  • Publisher(Ko) :한국연소학회
  • Journal Title :Journal of the Korean Society of Combustion
  • Journal Title(Ko) :한국연소학회지
  • Volume : 28
  • No :3
  • Pages :11-19
  • Received Date : 2023-03-28
  • Revised Date : 2023-04-14
  • Accepted Date : 2023-08-14
  • DOI :https://doi.org/10.15231/jksc.2023.28.3.011
Journal Informaiton Journal of the Korean Society of Combustion Journal of the Korean Society of Combustion
Online submission
  • ESCI_jkosco
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close