3D convolutional selective autoencoder for instability detection in combustion systems

highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable regime using spatiotemporal data (snippets of flame videos).•Demonstration of excellent generalization capability for different operating con...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Energy and AI Ročník 4; s. 100067
Hlavní autori: Gangopadhyay, Tryambak, Ramanan, Vikram, Akintayo, Adedotun, K Boor, Paige, Sarkar, Soumalya, Chakravarthy, Satyanarayanan R, Sarkar, Soumik
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.06.2021
Elsevier
Predmet:
ISSN:2666-5468, 2666-5468
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable regime using spatiotemporal data (snippets of flame videos).•Demonstration of excellent generalization capability for different operating conditions.•Verification of the identified precursors of transitions using physics-based understanding. [Display omitted] While analytical solutions of critical (phase) transitions in dynamical systems are abundant for simple nonlinear systems, such analysis remains intractable for real-life dynamical systems. A key example is thermoacoustic instability in combustion, where prediction or early detection of the onset of instability is a hard technical challenge, which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries. The instabilities arising in combustion chambers of engines are mathematically too complex to model. To address this issue in a data-driven manner instead, we propose a novel deep learning architecture called 3D convolutional selective autoencoder (3D-CSAE) to detect the evolution of self-excited oscillations using spatiotemporal data, i.e., hi-speed videos taken from a swirl-stabilized combustor (laboratory surrogate of gas turbine engine combustor). 3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability from the training videos (i.e., two spatial dimensions for the image frames and the third dimension for time). We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions. We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video. The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability. The machine learning-driven results are verified with physics-based off-line measures. Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.
AbstractList highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable regime using spatiotemporal data (snippets of flame videos).•Demonstration of excellent generalization capability for different operating conditions.•Verification of the identified precursors of transitions using physics-based understanding. [Display omitted] While analytical solutions of critical (phase) transitions in dynamical systems are abundant for simple nonlinear systems, such analysis remains intractable for real-life dynamical systems. A key example is thermoacoustic instability in combustion, where prediction or early detection of the onset of instability is a hard technical challenge, which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries. The instabilities arising in combustion chambers of engines are mathematically too complex to model. To address this issue in a data-driven manner instead, we propose a novel deep learning architecture called 3D convolutional selective autoencoder (3D-CSAE) to detect the evolution of self-excited oscillations using spatiotemporal data, i.e., hi-speed videos taken from a swirl-stabilized combustor (laboratory surrogate of gas turbine engine combustor). 3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability from the training videos (i.e., two spatial dimensions for the image frames and the third dimension for time). We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions. We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video. The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability. The machine learning-driven results are verified with physics-based off-line measures. Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.
While analytical solutions of critical (phase) transitions in dynamical systems are abundant for simple nonlinear systems, such analysis remains intractable for real-life dynamical systems. A key example is thermoacoustic instability in combustion, where prediction or early detection of the onset of instability is a hard technical challenge, which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries. The instabilities arising in combustion chambers of engines are mathematically too complex to model. To address this issue in a data-driven manner instead, we propose a novel deep learning architecture called 3D convolutional selective autoencoder (3D-CSAE) to detect the evolution of self-excited oscillations using spatiotemporal data, i.e., hi-speed videos taken from a swirl-stabilized combustor (laboratory surrogate of gas turbine engine combustor). 3D-CSAE consists of filters to learn, in a hierarchical fashion, the complex visual and dynamic features related to combustion instability from the training videos (i.e., two spatial dimensions for the image frames and the third dimension for time). We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions. We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video. The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability. The machine learning-driven results are verified with physics-based off-line measures. Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.
ArticleNumber 100067
Author Gangopadhyay, Tryambak
Ramanan, Vikram
Akintayo, Adedotun
K Boor, Paige
Sarkar, Soumalya
Chakravarthy, Satyanarayanan R
Sarkar, Soumik
Author_xml – sequence: 1
  givenname: Tryambak
  surname: Gangopadhyay
  fullname: Gangopadhyay, Tryambak
  organization: Department of Mechanical Engineering, Iowa State University, Ames, IA, USA
– sequence: 2
  givenname: Vikram
  surname: Ramanan
  fullname: Ramanan, Vikram
  organization: Indian Institute of Technology Madras, Chennai, India
– sequence: 3
  givenname: Adedotun
  surname: Akintayo
  fullname: Akintayo, Adedotun
  organization: Intel Corporation, Folsom, CA, USA
– sequence: 4
  givenname: Paige
  surname: K Boor
  fullname: K Boor, Paige
  organization: Department of Mechanical Engineering, Iowa State University, Ames, IA, USA
– sequence: 5
  givenname: Soumalya
  surname: Sarkar
  fullname: Sarkar, Soumalya
  organization: Raytheon Technologies, East Hartford, CT, USA
– sequence: 6
  givenname: Satyanarayanan R
  surname: Chakravarthy
  fullname: Chakravarthy, Satyanarayanan R
  organization: Indian Institute of Technology Madras, Chennai, India
– sequence: 7
  givenname: Soumik
  surname: Sarkar
  fullname: Sarkar, Soumik
  email: soumiks@iastate.edu
  organization: Department of Mechanical Engineering, Iowa State University, Ames, IA, USA
BookMark eNqFkE1rGzEQhkVJIKnjX5DL_gG7knZXsg45lPQjhkAuaa9idjQyMutVkGSD_31lu5SSQ3sazcs8L-j5yK6mOBFj94IvBRfq03ZJmyOEpeRS1IRzpT-wW6mUWvSdWl399b5h85y39UT2Qhitb9nP9kuDcTrEcV9CnGBsMo2EJRyogX2JNGF0lBofUxOmXGAIYyjHxlE5XcWpprVgN-zzecvHXGiX79i1hzHT_PecsR_fvr4-Pi2eX76vHz8_L7ATXVngoAZBknfoELQmTWiGFr1zyNUKV62ToCQYlAK89lySMtRrpaCTHltsZ2x96XURtvYthR2ko40Q7DmIaWMhlYAjWaG09NIAiV53pvWGd46LwXSkBWnX16720oUp5pzI_-kT3J5M2609m7Yn0_ZiulLmHYWhwMlFSRDG_7APF5aqokOgZDOGapxcSNVu_UP4J_8LaF2eww
CitedBy_id crossref_primary_10_1016_j_ast_2023_108354
crossref_primary_10_1016_j_energy_2023_129782
crossref_primary_10_1016_j_ast_2025_109994
crossref_primary_10_1016_j_proci_2025_105796
crossref_primary_10_1115_1_4069002
crossref_primary_10_2514_1_B38780
crossref_primary_10_2514_1_B39287
crossref_primary_10_3390_en14248468
crossref_primary_10_1016_j_apenergy_2024_123224
crossref_primary_10_3390_s23031236
crossref_primary_10_3390_s25154613
crossref_primary_10_1016_j_engappai_2022_105591
crossref_primary_10_1016_j_joei_2024_101733
crossref_primary_10_1016_j_ast_2025_110243
crossref_primary_10_1016_j_fuel_2024_133393
crossref_primary_10_1177_17568277221139974
crossref_primary_10_3389_feart_2022_1029160
crossref_primary_10_1016_j_combustflame_2023_113182
Cites_doi 10.1016/j.apenergy.2019.114159
10.1017/S0022112008003613
10.1016/j.egyai.2020.100033
10.1016/j.combustflame.2016.06.018
10.1103/PhysRevE.97.022223
10.1115/1.2981178
10.1080/00102202.2012.752734
10.1016/j.proci.2006.07.138
10.1016/j.proci.2010.06.059
10.1017/jfm.2019.822
10.1016/j.proci.2014.07.002
10.1016/j.fuel.2019.116709
10.1063/1.864048
10.1016/j.combustflame.2018.10.027
10.1016/j.combustflame.2019.07.015
10.1063/1.3563577
10.1080/00102202.2013.876420
10.1214/aoms/1177729694
10.1080/00102202.2017.1374952
10.31224/osf.io/ysgp4
10.1615/JFlowVisImageProc.2018025857
10.2514/2.6192
10.1006/jsvi.1995.0100
10.1016/j.patcog.2016.06.008
10.1017/jfm.2016.803
10.1016/j.proci.2008.05.037
10.1146/annurev.fl.25.010193.002543
10.1007/s12650-018-0523-1
10.1177/1756827716642091
10.1017/S0022112010001217
10.1126/science.aaw4741
10.1017/jfm.2014.171
10.2514/2.6182
10.15231/jksc.2015.20.1.024
10.1080/13647830.2019.1602286
10.1016/j.combustflame.2011.02.012
10.1063/1.5113494
10.1017/jfm.2016.615
10.1016/j.combustflame.2015.06.020
10.1103/PhysRevApplied.11.064034
10.1260/147547209786234984
ContentType Journal Article
Copyright 2021 The Author(s)
Copyright_xml – notice: 2021 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.egyai.2021.100067
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2666-5468
ExternalDocumentID oai_doaj_org_article_1672f29ae157493f904d01b94e71e7d5
10_1016_j_egyai_2021_100067
S2666546821000215
GroupedDBID 6I.
AAEDW
AAFTH
AAXUO
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
EBS
FDB
GROUPED_DOAJ
M41
M~E
NCXOZ
OK1
ROL
0R~
AALRI
AAYWO
AAYXX
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AIGII
AITUG
AKBMS
AKYEP
APXCP
CITATION
ID FETCH-LOGICAL-c414t-cb6b1e204cdca77e7ec9b3cfddc068c83d2a62a9c21af7f02e69e5766a42fc3c3
IEDL.DBID DOA
ISICitedReferencesCount 26
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001058070400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2666-5468
IngestDate Fri Oct 03 12:51:00 EDT 2025
Thu Nov 20 00:37:27 EST 2025
Tue Nov 18 22:34:23 EST 2025
Tue Jul 25 21:02:16 EDT 2023
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords 3D deep learning
Instability precursors
Combustion instability
Hi-speed video analytics
Gas turbine engines
Physics-based validation
Convolutional autoencoder
Early detection
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c414t-cb6b1e204cdca77e7ec9b3cfddc068c83d2a62a9c21af7f02e69e5766a42fc3c3
OpenAccessLink https://doaj.org/article/1672f29ae157493f904d01b94e71e7d5
ParticipantIDs doaj_primary_oai_doaj_org_article_1672f29ae157493f904d01b94e71e7d5
crossref_primary_10_1016_j_egyai_2021_100067
crossref_citationtrail_10_1016_j_egyai_2021_100067
elsevier_sciencedirect_doi_10_1016_j_egyai_2021_100067
PublicationCentury 2000
PublicationDate June 2021
2021-06-00
2021-06-01
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: June 2021
PublicationDecade 2020
PublicationTitle Energy and AI
PublicationYear 2021
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Murata, Fukami, Fukagata (bib0038) 2020; 882
Dowling, Stow (bib0004) 2003; 19
Ioffe S., Szegedy C.. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv
Taamallah, LaBry, Shanbhogue, Ghoniem (bib0057) 2015; 35
Lieuwen (bib0003) 2012
Barwey S., Raman V., Steinberg A.. Extracting information overlap in simultaneous oh-plif and piv fields with neural networks. arXiv preprint arXiv
Raissi, Yazdani, Karniadakis (bib0041) 2020; 367
Candel, Durox, Ducruix, Birbaud, Noiray, Schuller (bib0002) 2009; 8
Glorot, Bordes, Bengio (bib0052) 2011
Ducruix, Schuller, Durox, Candel (bib0001) 2003; 19
Ling, Kurzawski, Templeton (bib0036) 2016; 807
Murayama, Kinugawa, Tokuda, Gotoda (bib0010) 2018; 97
Berkooz, Holmes, Lumley (bib0019) 1993; 25
Kutz (bib0042) 2017; 814
Han, Hossain, Wang, Li, Xu (bib0048) 2020; 259
Bishop (bib0021) 2006
Pu, Gan, Henao, Yuan, Li, Stevens (bib0051) 2016
Ćosić, Moeck, Paschereit (bib0029) 2014; 186
Kobayashi, Murayama, Hachijo, Gotoda (bib0034) 2019; 11
de Frahan, Yellapantula, King, Day, Grout (bib0037) 2019; 208
Gotoda, Nikimoto, Miyano, Tachibana (bib0009) 2011; 21
.
Palies, Schuller, Durox, Candel (bib0025) 2011; 33
Kim, Santavicca (bib0024) 2013; 185
Gangopadhyay, Tan, Locurto, Michael, Sarkar (bib0055) 2019
Dowling (bib0005) 1995; 180
Sarkar, Lore, Sarkar, Ramanan, Chakravarthy, Phoha (bib0015) 2015
Gangopadhyay T.. Deep learning for monitoring cyber-physical systems2019.
Kullback, Leibler (bib0049) 1951; 22
Kingma D.P., Ba J.. Adam: A method for stochastic optimization. arXiv preprint arXiv
Gangopadhyay, Locurto, Boor, Michael, Sarkar (bib0044) 2018
Sengupta U., Rasmussen C., Juniper M.. Bayesian machine learning for the prognosis of combustion instabilities from noise2020.
Han, Li, Morgans (bib0030) 2015; 162
Turns (bib0056) 1996; 287
Stow, Dowling (bib0007) 2009; 131
Deng, Wang, Liu, Wang, Li, Liu (bib0039) 2019; 22
LoCurto A., Gangopadhyay T., Boor P., Sarkar S., Michael J.B.. Mode decomposition and convolutional neural network analysis of thermoacoustic instabilities in a rijke tube2018.
Gangopadhyay, Locurto, Michael, Sarkar (bib0046) 2020
Sarkar, Chakravarthy, Ramanan, Ray (bib0059) 2016; 8
Zhou, Tao (bib0060) 2020; 263
Schmid (bib0022) 2010; 656
Pawar, Rahman, Vaddireddy, San, Rasheed, Vedula (bib0040) 2019; 31
Noiray, Durox, Schuller, Candel (bib0006) 2008; 615
Sarkar, Lore, Sarkar (bib0016) 2015
Akintayo, Lore, Sarkar, Sarkar (bib0047) 2016; 7
Ghosal, Ramanan, Sarkar, Chakravarthy, Sarkar (bib0023) 2016
Barwey, Hassanaly, Raman, Steinberg (bib0031) 2019
Sen, Gangopadhyay, Bhattacharya, Misra, Karmakar, Sengupta (bib0013) 2016
Bellows, Bobba, Forte, Seitzman, Lieuwen (bib0026) 2007; 31
Cui, Wang, Liu, Zheng, Wang, Yue (bib0033) 2020; 2
Thumuluru, Lieuwen (bib0027) 2009; 32
Nair, Sujith (bib0011) 2014; 747
Hussain (bib0008) 1983; 26
Barwey, Hassanaly, An, Raman, Steinberg (bib0014) 2019; 23
Ramanan, Chakravarthy (bib0018) 2019; 26
Fukami, Fukagata, Taira (bib0043) 2020
Lore, Akintayo, Sarkar (bib0050) 2017; 61
Palies, Durox, Schuller, Candel (bib0028) 2011; 158
Sen, Gangopadhyay, Bhattacharya, Mukhopadhyay, Sen (bib0012) 2018; 190
Zheng, Fang, Liu, Geng, Yang, Feng (bib0017) 2019; 199
Sampath, Chakravarthy (bib0058) 2016; 172
Ahn, Song, Cha (bib0061) 2015; 20
10.1016/j.egyai.2021.100067_bib0035
Bishop (10.1016/j.egyai.2021.100067_bib0021) 2006
Sampath (10.1016/j.egyai.2021.100067_bib0058) 2016; 172
Gotoda (10.1016/j.egyai.2021.100067_bib0009) 2011; 21
Barwey (10.1016/j.egyai.2021.100067_bib0014) 2019; 23
Nair (10.1016/j.egyai.2021.100067_bib0011) 2014; 747
Akintayo (10.1016/j.egyai.2021.100067_bib0047) 2016; 7
Lore (10.1016/j.egyai.2021.100067_bib0050) 2017; 61
10.1016/j.egyai.2021.100067_bib0045
Pawar (10.1016/j.egyai.2021.100067_bib0040) 2019; 31
Berkooz (10.1016/j.egyai.2021.100067_bib0019) 1993; 25
Noiray (10.1016/j.egyai.2021.100067_bib0006) 2008; 615
Murayama (10.1016/j.egyai.2021.100067_bib0010) 2018; 97
de Frahan (10.1016/j.egyai.2021.100067_bib0037) 2019; 208
Palies (10.1016/j.egyai.2021.100067_bib0025) 2011; 33
Sarkar (10.1016/j.egyai.2021.100067_bib0059) 2016; 8
Dowling (10.1016/j.egyai.2021.100067_bib0005) 1995; 180
Bellows (10.1016/j.egyai.2021.100067_bib0026) 2007; 31
Fukami (10.1016/j.egyai.2021.100067_bib0043) 2020
Sarkar (10.1016/j.egyai.2021.100067_bib0016) 2015
Glorot (10.1016/j.egyai.2021.100067_bib0052) 2011
Zheng (10.1016/j.egyai.2021.100067_bib0017) 2019; 199
Lieuwen (10.1016/j.egyai.2021.100067_bib0003) 2012
10.1016/j.egyai.2021.100067_bib0053
Han (10.1016/j.egyai.2021.100067_bib0048) 2020; 259
10.1016/j.egyai.2021.100067_bib0054
Stow (10.1016/j.egyai.2021.100067_bib0007) 2009; 131
Murata (10.1016/j.egyai.2021.100067_bib0038) 2020; 882
Kullback (10.1016/j.egyai.2021.100067_bib0049) 1951; 22
Zhou (10.1016/j.egyai.2021.100067_bib0060) 2020; 263
Schmid (10.1016/j.egyai.2021.100067_bib0022) 2010; 656
Barwey (10.1016/j.egyai.2021.100067_bib0031) 2019
Hussain (10.1016/j.egyai.2021.100067_bib0008) 1983; 26
Palies (10.1016/j.egyai.2021.100067_bib0028) 2011; 158
Sen (10.1016/j.egyai.2021.100067_bib0012) 2018; 190
Ahn (10.1016/j.egyai.2021.100067_bib0061) 2015; 20
Turns (10.1016/j.egyai.2021.100067_bib0056) 1996; 287
Pu (10.1016/j.egyai.2021.100067_bib0051) 2016
Ducruix (10.1016/j.egyai.2021.100067_bib0001) 2003; 19
10.1016/j.egyai.2021.100067_bib0020
Ćosić (10.1016/j.egyai.2021.100067_bib0029) 2014; 186
Taamallah (10.1016/j.egyai.2021.100067_bib0057) 2015; 35
Sarkar (10.1016/j.egyai.2021.100067_bib0015) 2015
Ramanan (10.1016/j.egyai.2021.100067_bib0018) 2019; 26
Deng (10.1016/j.egyai.2021.100067_bib0039) 2019; 22
Candel (10.1016/j.egyai.2021.100067_bib0002) 2009; 8
Thumuluru (10.1016/j.egyai.2021.100067_bib0027) 2009; 32
Kobayashi (10.1016/j.egyai.2021.100067_bib0034) 2019; 11
Gangopadhyay (10.1016/j.egyai.2021.100067_bib0055) 2019
Han (10.1016/j.egyai.2021.100067_bib0030) 2015; 162
Cui (10.1016/j.egyai.2021.100067_bib0033) 2020; 2
Ghosal (10.1016/j.egyai.2021.100067_bib0023) 2016
Kutz (10.1016/j.egyai.2021.100067_bib0042) 2017; 814
Ling (10.1016/j.egyai.2021.100067_bib0036) 2016; 807
Raissi (10.1016/j.egyai.2021.100067_bib0041) 2020; 367
Sen (10.1016/j.egyai.2021.100067_sbref0013) 2016
Gangopadhyay (10.1016/j.egyai.2021.100067_sbref0044) 2018
Gangopadhyay (10.1016/j.egyai.2021.100067_bib0046) 2020
Dowling (10.1016/j.egyai.2021.100067_bib0004) 2003; 19
Kim (10.1016/j.egyai.2021.100067_bib0024) 2013; 185
10.1016/j.egyai.2021.100067_bib0032
References_xml – volume: 180
  start-page: 557
  year: 1995
  end-page: 581
  ident: bib0005
  article-title: The calculation of thermoacoustic oscillations
  publication-title: J Sound Vib
– volume: 287
  year: 1996
  ident: bib0056
  article-title: Introduction to combustion
– year: 2012
  ident: bib0003
  article-title: Unsteady combustor physics
– volume: 263
  start-page: 116709
  year: 2020
  ident: bib0060
  article-title: Effects of annular n2/o2 and co2/o2 jets on combustion instabilities and nox emissions in lean-premixed methane flames
  publication-title: Fuel
– volume: 8
  start-page: 1
  year: 2009
  end-page: 56
  ident: bib0002
  article-title: Flame dynamics and combustion noise: progress and challenges
  publication-title: Int J Aeroacoust
– volume: 199
  start-page: 213
  year: 2019
  end-page: 229
  ident: bib0017
  article-title: Study on the flame development patterns and flame speeds from homogeneous charge to stratified charge by fueling n-heptane in an optical engine
  publication-title: Combust Flame
– year: 2015
  ident: bib0016
  article-title: Early detection of combustion instability by neural-symbolic analysis on hi-speed video.
  publication-title: CoCo@ NIPS
– volume: 162
  start-page: 3632
  year: 2015
  end-page: 3647
  ident: bib0030
  article-title: Prediction of combustion instability limit cycle oscillations by combining flame describing function simulations with a thermoacoustic network model
  publication-title: Combust Flame
– volume: 22
  start-page: 65
  year: 2019
  end-page: 78
  ident: bib0039
  article-title: A cnn-based vortex identification method
  publication-title: J Visual
– volume: 23
  start-page: 994
  year: 2019
  end-page: 1020
  ident: bib0014
  article-title: Experimental data-based reduced-order model for analysis and prediction of flame transition in gas turbine combustors
  publication-title: Combust Theory Model
– volume: 31
  start-page: 3181
  year: 2007
  end-page: 3188
  ident: bib0026
  article-title: Flame transfer function saturation mechanisms in a swirl-stabilized combustor
  publication-title: Proceedings of the combustion institute
– reference: Barwey S., Raman V., Steinberg A.. Extracting information overlap in simultaneous oh-plif and piv fields with neural networks. arXiv preprint arXiv:
– volume: 807
  start-page: 155-166
  year: 2016
  ident: bib0036
  article-title: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
  publication-title: J Fluid Mech
– volume: 21
  start-page: 013124
  year: 2011
  ident: bib0009
  article-title: Dynamic properties of combustion instability in a lean premixed gas-turbine combustor
  publication-title: Chaos: An Interdiscip J Nonlinear Sci
– volume: 97
  start-page: 022223
  year: 2018
  ident: bib0010
  article-title: Characterization and detection of thermoacoustic combustion oscillations based on statistical complexity and complex-network theory
  publication-title: Phys Rev E
– start-page: 315
  year: 2011
  end-page: 323
  ident: bib0052
  article-title: Deep sparse rectifier neural networks
  publication-title: Proceedings of the fourteenth international conference on artificial intelligence and statistics
– volume: 747
  start-page: 635
  year: 2014
  end-page: 655
  ident: bib0011
  article-title: Multifractality in combustion noise: predicting an impending combustion instability
  publication-title: J Fluid Mech
– volume: 259
  start-page: 114159
  year: 2020
  ident: bib0048
  article-title: Combustion stability monitoring through flame imaging and stacked sparse autoencoder based deep neural network
  publication-title: Applied Energy
– volume: 19
  start-page: 722
  year: 2003
  end-page: 734
  ident: bib0001
  article-title: Combustion dynamics and instabilities: Elementary coupling and driving mechanisms
  publication-title: J Propuls Power
– volume: 131
  year: 2009
  ident: bib0007
  article-title: A time-domain network model for nonlinear thermoacoustic oscillations
  publication-title: J Eng Gas Turbines Power
– volume: 35
  start-page: 3273
  year: 2015
  end-page: 3282
  ident: bib0057
  article-title: Thermo-acoustic instabilities in lean premixed swirl-stabilized combustion and their link to acoustically coupled and decoupled flame macrostructures
  publication-title: Proc Combust Inst
– volume: 19
  start-page: 751
  year: 2003
  end-page: 764
  ident: bib0004
  article-title: Acoustic analysis of gas turbine combustors
  publication-title: J Propuls Power
– reference: Gangopadhyay T.. Deep learning for monitoring cyber-physical systems2019.
– volume: 185
  start-page: 999
  year: 2013
  end-page: 1015
  ident: bib0024
  article-title: Generalization of turbulent swirl flame transfer functions in gas turbine combustors
  publication-title: Combust Sci Technol
– year: 2016
  ident: bib0013
  article-title: Investigation of ducted inverse nonpremixed flame using dynamic systems approach
  publication-title: ASME Turbo Expo 2016: Turbomachinery Technical Conference and Exposition
– volume: 208
  start-page: 436
  year: 2019
  end-page: 450
  ident: bib0037
  article-title: Deep learning for presumed probability density function models
  publication-title: Combust Flame
– reference: Kingma D.P., Ba J.. Adam: A method for stochastic optimization. arXiv preprint arXiv:
– reference: LoCurto A., Gangopadhyay T., Boor P., Sarkar S., Michael J.B.. Mode decomposition and convolutional neural network analysis of thermoacoustic instabilities in a rijke tube2018.
– volume: 367
  start-page: 1026
  year: 2020
  end-page: 1030
  ident: bib0041
  article-title: Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
  publication-title: Science
– volume: 172
  start-page: 309
  year: 2016
  end-page: 325
  ident: bib0058
  article-title: Investigation of intermittent oscillations in a premixed dump combustor using time-resolved particle image velocimetry
  publication-title: Combust Flame
– volume: 814
  start-page: 1
  year: 2017
  end-page: 4
  ident: bib0042
  article-title: Deep learning in fluid dynamics
  publication-title: J Fluid Mech
– reference: Sengupta U., Rasmussen C., Juniper M.. Bayesian machine learning for the prognosis of combustion instabilities from noise2020.
– start-page: 2352
  year: 2016
  end-page: 2360
  ident: bib0051
  article-title: Variational autoencoder for deep learning of images, labels and captions
  publication-title: Proceedings of the advances in neural information processing systems
– volume: 26
  year: 2019
  ident: bib0018
  article-title: Investigation of rotational symmetry in vortex-driven acoustic oscillations in a laboratory-scale swirl combustor
  publication-title: J Flow Visual Image Process
– volume: 8
  start-page: 235
  year: 2016
  end-page: 253
  ident: bib0059
  article-title: Dynamic data-driven prediction of instability in a swirl-stabilized combustor
  publication-title: Int J Spray Combust Dyn
– volume: 190
  start-page: 32
  year: 2018
  end-page: 56
  ident: bib0012
  article-title: Dynamic characterization of a ducted inverse diffusion flame using recurrence analysis
  publication-title: Combust Sci Technol
– volume: 186
  start-page: 713
  year: 2014
  end-page: 736
  ident: bib0029
  article-title: Nonlinear instability analysis for partially premixed swirl flames
  publication-title: Combust Sci Technol
– year: 2016
  ident: bib0023
  article-title: Detection and analysis of combustion instability from hi-speed flame images using dynamic mode decomposition
  publication-title: ASME 2016 dynamic systems and control conference
– year: 2006
  ident: bib0021
  article-title: Pattern recognition and machine learning
– start-page: 1
  year: 2019
  end-page: 24
  ident: bib0031
  article-title: Using machine learning to construct velocity fields from oh-plif images
  publication-title: Combust Sci Technol
– volume: 11
  start-page: 064034
  year: 2019
  ident: bib0034
  article-title: Early detection of thermoacoustic combustion instability using a methodology combining complex networks and machine learning
  publication-title: Phys Rev Appl
– volume: 33
  start-page: 2967
  year: 2011
  end-page: 2974
  ident: bib0025
  article-title: Modeling of premixed swirling flames transfer functions
  publication-title: Proc Combust Inst
– volume: 158
  start-page: 1980
  year: 2011
  end-page: 1991
  ident: bib0028
  article-title: Nonlinear combustion instability analysis based on the flame describing function applied to turbulent premixed swirling flames
  publication-title: Combust Flame
– volume: 61
  start-page: 650
  year: 2017
  end-page: 662
  ident: bib0050
  article-title: Llnet: A deep autoencoder approach to natural low-light image enhancement
  publication-title: Pattern Recognit
– start-page: 1
  year: 2020
  end-page: 23
  ident: bib0043
  article-title: Assessment of supervised machine learning methods for fluid flows
  publication-title: Theor Comput Fluid Dyn
– volume: 615
  start-page: 139
  year: 2008
  end-page: 167
  ident: bib0006
  article-title: A unified framework for nonlinear combustion instability analysis based on the flame describing function
  publication-title: J Fluid Mech
– reference: Ioffe S., Szegedy C.. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:
– volume: 26
  start-page: 2816
  year: 1983
  end-page: 2850
  ident: bib0008
  article-title: Coherent structuresreality and myth
  publication-title: Phys Fluids
– volume: 882
  year: 2020
  ident: bib0038
  article-title: Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
  publication-title: J Fluid Mech
– year: 2015
  ident: bib0015
  article-title: Early detection of combustion instability from hi-speed flame images via deep learning and symbolic time series analysis
  publication-title: Proceedings of the annual conference of the prognostics and health management
– volume: 20
  start-page: 24
  year: 2015
  end-page: 31
  ident: bib0061
  article-title: Effect of a preprocessing method on the inversion of oh* chemiluminescence images acquired for visualizing sng swirl-stabilized flame structure
  publication-title: J Korean Soc Combust
– volume: 2
  start-page: 100033
  year: 2020
  ident: bib0033
  article-title: Development of the ignition delay prediction model of n-butane/hydrogen mixtures based on artificial neural network
  publication-title: Energy and AI
– reference: .
– year: 2018
  ident: bib0044
  article-title: Characterizing combustion instability using deep convolutional neural network
  publication-title: Proceedings of the ASME 2018 dynamic systems and control conference
– volume: 22
  start-page: 79
  year: 1951
  end-page: 86
  ident: bib0049
  article-title: On information and sufficiency
  publication-title: Ann Math Stat
– volume: 31
  start-page: 085101
  year: 2019
  ident: bib0040
  article-title: A deep learning enabler for nonintrusive reduced order modeling of fluid flows
  publication-title: Phys Fluids
– volume: 25
  start-page: 539
  year: 1993
  end-page: 575
  ident: bib0019
  article-title: The proper orthogonal decomposition in the analysis of turbulent flows
  publication-title: Annu Rev Fluid Mech
– volume: 32
  start-page: 2893
  year: 2009
  end-page: 2900
  ident: bib0027
  article-title: Characterization of acoustically forced swirl flame dynamics
  publication-title: Proc Combust Inst
– volume: 656
  start-page: 5
  year: 2010
  end-page: 28
  ident: bib0022
  article-title: Dynamic mode decomposition of numerical and experimental data
  publication-title: J Fluid Mech
– volume: 7
  start-page: 1
  year: 2016
  end-page: 14
  ident: bib0047
  article-title: Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder
  publication-title: Int J Prognost Health Manag
– year: 2019
  ident: bib0055
  article-title: An explainable framework using deep attention models for sequential data in combustion systems
  publication-title: Proceedings of the NeurIPS 2019 workshop on machine learning and the physical sciences
– start-page: 283
  year: 2020
  end-page: 300
  ident: bib0046
  article-title: Deep learning algorithms for detecting combustion instabilities
  publication-title: Proceedings of the dynamics and control of energy systems
– volume: 259
  start-page: 114159
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0048
  article-title: Combustion stability monitoring through flame imaging and stacked sparse autoencoder based deep neural network
  publication-title: Applied Energy
  doi: 10.1016/j.apenergy.2019.114159
– year: 2015
  ident: 10.1016/j.egyai.2021.100067_bib0015
  article-title: Early detection of combustion instability from hi-speed flame images via deep learning and symbolic time series analysis
– volume: 615
  start-page: 139
  year: 2008
  ident: 10.1016/j.egyai.2021.100067_bib0006
  article-title: A unified framework for nonlinear combustion instability analysis based on the flame describing function
  publication-title: J Fluid Mech
  doi: 10.1017/S0022112008003613
– volume: 2
  start-page: 100033
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0033
  article-title: Development of the ignition delay prediction model of n-butane/hydrogen mixtures based on artificial neural network
  publication-title: Energy and AI
  doi: 10.1016/j.egyai.2020.100033
– volume: 172
  start-page: 309
  year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0058
  article-title: Investigation of intermittent oscillations in a premixed dump combustor using time-resolved particle image velocimetry
  publication-title: Combust Flame
  doi: 10.1016/j.combustflame.2016.06.018
– volume: 97
  start-page: 022223
  issue: 2
  year: 2018
  ident: 10.1016/j.egyai.2021.100067_bib0010
  article-title: Characterization and detection of thermoacoustic combustion oscillations based on statistical complexity and complex-network theory
  publication-title: Phys Rev E
  doi: 10.1103/PhysRevE.97.022223
– volume: 131
  issue: 3
  year: 2009
  ident: 10.1016/j.egyai.2021.100067_bib0007
  article-title: A time-domain network model for nonlinear thermoacoustic oscillations
  publication-title: J Eng Gas Turbines Power
  doi: 10.1115/1.2981178
– volume: 185
  start-page: 999
  issue: 7
  year: 2013
  ident: 10.1016/j.egyai.2021.100067_bib0024
  article-title: Generalization of turbulent swirl flame transfer functions in gas turbine combustors
  publication-title: Combust Sci Technol
  doi: 10.1080/00102202.2012.752734
– volume: 31
  start-page: 3181
  issue: 2
  year: 2007
  ident: 10.1016/j.egyai.2021.100067_bib0026
  article-title: Flame transfer function saturation mechanisms in a swirl-stabilized combustor
  publication-title: Proceedings of the combustion institute
  doi: 10.1016/j.proci.2006.07.138
– ident: 10.1016/j.egyai.2021.100067_bib0053
– ident: 10.1016/j.egyai.2021.100067_bib0020
– volume: 33
  start-page: 2967
  issue: 2
  year: 2011
  ident: 10.1016/j.egyai.2021.100067_bib0025
  article-title: Modeling of premixed swirling flames transfer functions
  publication-title: Proc Combust Inst
  doi: 10.1016/j.proci.2010.06.059
– year: 2016
  ident: 10.1016/j.egyai.2021.100067_sbref0013
  article-title: Investigation of ducted inverse nonpremixed flame using dynamic systems approach
– volume: 882
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0038
  article-title: Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
  publication-title: J Fluid Mech
  doi: 10.1017/jfm.2019.822
– volume: 35
  start-page: 3273
  issue: 3
  year: 2015
  ident: 10.1016/j.egyai.2021.100067_bib0057
  article-title: Thermo-acoustic instabilities in lean premixed swirl-stabilized combustion and their link to acoustically coupled and decoupled flame macrostructures
  publication-title: Proc Combust Inst
  doi: 10.1016/j.proci.2014.07.002
– year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0023
  article-title: Detection and analysis of combustion instability from hi-speed flame images using dynamic mode decomposition
– volume: 263
  start-page: 116709
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0060
  article-title: Effects of annular n2/o2 and co2/o2 jets on combustion instabilities and nox emissions in lean-premixed methane flames
  publication-title: Fuel
  doi: 10.1016/j.fuel.2019.116709
– volume: 26
  start-page: 2816
  issue: 10
  year: 1983
  ident: 10.1016/j.egyai.2021.100067_bib0008
  article-title: Coherent structuresreality and myth
  publication-title: Phys Fluids
  doi: 10.1063/1.864048
– volume: 287
  year: 1996
  ident: 10.1016/j.egyai.2021.100067_bib0056
– volume: 199
  start-page: 213
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0017
  article-title: Study on the flame development patterns and flame speeds from homogeneous charge to stratified charge by fueling n-heptane in an optical engine
  publication-title: Combust Flame
  doi: 10.1016/j.combustflame.2018.10.027
– volume: 208
  start-page: 436
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0037
  article-title: Deep learning for presumed probability density function models
  publication-title: Combust Flame
  doi: 10.1016/j.combustflame.2019.07.015
– year: 2018
  ident: 10.1016/j.egyai.2021.100067_sbref0044
  article-title: Characterizing combustion instability using deep convolutional neural network
– start-page: 2352
  year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0051
  article-title: Variational autoencoder for deep learning of images, labels and captions
– ident: 10.1016/j.egyai.2021.100067_bib0054
– volume: 21
  start-page: 013124
  issue: 1
  year: 2011
  ident: 10.1016/j.egyai.2021.100067_bib0009
  article-title: Dynamic properties of combustion instability in a lean premixed gas-turbine combustor
  publication-title: Chaos: An Interdiscip J Nonlinear Sci
  doi: 10.1063/1.3563577
– volume: 186
  start-page: 713
  issue: 6
  year: 2014
  ident: 10.1016/j.egyai.2021.100067_bib0029
  article-title: Nonlinear instability analysis for partially premixed swirl flames
  publication-title: Combust Sci Technol
  doi: 10.1080/00102202.2013.876420
– start-page: 1
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0043
  article-title: Assessment of supervised machine learning methods for fluid flows
  publication-title: Theor Comput Fluid Dyn
– volume: 22
  start-page: 79
  issue: 1
  year: 1951
  ident: 10.1016/j.egyai.2021.100067_bib0049
  article-title: On information and sufficiency
  publication-title: Ann Math Stat
  doi: 10.1214/aoms/1177729694
– volume: 190
  start-page: 32
  issue: 1
  year: 2018
  ident: 10.1016/j.egyai.2021.100067_bib0012
  article-title: Dynamic characterization of a ducted inverse diffusion flame using recurrence analysis
  publication-title: Combust Sci Technol
  doi: 10.1080/00102202.2017.1374952
– ident: 10.1016/j.egyai.2021.100067_bib0035
  doi: 10.31224/osf.io/ysgp4
– volume: 26
  issue: 1
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0018
  article-title: Investigation of rotational symmetry in vortex-driven acoustic oscillations in a laboratory-scale swirl combustor
  publication-title: J Flow Visual Image Process
  doi: 10.1615/JFlowVisImageProc.2018025857
– volume: 19
  start-page: 751
  issue: 5
  year: 2003
  ident: 10.1016/j.egyai.2021.100067_bib0004
  article-title: Acoustic analysis of gas turbine combustors
  publication-title: J Propuls Power
  doi: 10.2514/2.6192
– volume: 180
  start-page: 557
  issue: 4
  year: 1995
  ident: 10.1016/j.egyai.2021.100067_bib0005
  article-title: The calculation of thermoacoustic oscillations
  publication-title: J Sound Vib
  doi: 10.1006/jsvi.1995.0100
– volume: 61
  start-page: 650
  year: 2017
  ident: 10.1016/j.egyai.2021.100067_bib0050
  article-title: Llnet: A deep autoencoder approach to natural low-light image enhancement
  publication-title: Pattern Recognit
  doi: 10.1016/j.patcog.2016.06.008
– volume: 814
  start-page: 1
  year: 2017
  ident: 10.1016/j.egyai.2021.100067_bib0042
  article-title: Deep learning in fluid dynamics
  publication-title: J Fluid Mech
  doi: 10.1017/jfm.2016.803
– year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0055
  article-title: An explainable framework using deep attention models for sequential data in combustion systems
– volume: 32
  start-page: 2893
  issue: 2
  year: 2009
  ident: 10.1016/j.egyai.2021.100067_bib0027
  article-title: Characterization of acoustically forced swirl flame dynamics
  publication-title: Proc Combust Inst
  doi: 10.1016/j.proci.2008.05.037
– volume: 25
  start-page: 539
  issue: 1
  year: 1993
  ident: 10.1016/j.egyai.2021.100067_bib0019
  article-title: The proper orthogonal decomposition in the analysis of turbulent flows
  publication-title: Annu Rev Fluid Mech
  doi: 10.1146/annurev.fl.25.010193.002543
– volume: 7
  start-page: 1
  issue: 023
  year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0047
  article-title: Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder
  publication-title: Int J Prognost Health Manag
– volume: 22
  start-page: 65
  issue: 1
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0039
  article-title: A cnn-based vortex identification method
  publication-title: J Visual
  doi: 10.1007/s12650-018-0523-1
– volume: 8
  start-page: 235
  issue: 4
  year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0059
  article-title: Dynamic data-driven prediction of instability in a swirl-stabilized combustor
  publication-title: Int J Spray Combust Dyn
  doi: 10.1177/1756827716642091
– volume: 656
  start-page: 5
  year: 2010
  ident: 10.1016/j.egyai.2021.100067_bib0022
  article-title: Dynamic mode decomposition of numerical and experimental data
  publication-title: J Fluid Mech
  doi: 10.1017/S0022112010001217
– year: 2012
  ident: 10.1016/j.egyai.2021.100067_bib0003
– volume: 367
  start-page: 1026
  issue: 6481
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0041
  article-title: Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
  publication-title: Science
  doi: 10.1126/science.aaw4741
– ident: 10.1016/j.egyai.2021.100067_bib0032
– start-page: 283
  year: 2020
  ident: 10.1016/j.egyai.2021.100067_bib0046
  article-title: Deep learning algorithms for detecting combustion instabilities
– volume: 747
  start-page: 635
  year: 2014
  ident: 10.1016/j.egyai.2021.100067_bib0011
  article-title: Multifractality in combustion noise: predicting an impending combustion instability
  publication-title: J Fluid Mech
  doi: 10.1017/jfm.2014.171
– volume: 19
  start-page: 722
  issue: 5
  year: 2003
  ident: 10.1016/j.egyai.2021.100067_bib0001
  article-title: Combustion dynamics and instabilities: Elementary coupling and driving mechanisms
  publication-title: J Propuls Power
  doi: 10.2514/2.6182
– year: 2006
  ident: 10.1016/j.egyai.2021.100067_bib0021
– volume: 20
  start-page: 24
  issue: 1
  year: 2015
  ident: 10.1016/j.egyai.2021.100067_bib0061
  article-title: Effect of a preprocessing method on the inversion of oh* chemiluminescence images acquired for visualizing sng swirl-stabilized flame structure
  publication-title: J Korean Soc Combust
  doi: 10.15231/jksc.2015.20.1.024
– year: 2015
  ident: 10.1016/j.egyai.2021.100067_bib0016
  article-title: Early detection of combustion instability by neural-symbolic analysis on hi-speed video.
– volume: 23
  start-page: 994
  issue: 6
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0014
  article-title: Experimental data-based reduced-order model for analysis and prediction of flame transition in gas turbine combustors
  publication-title: Combust Theory Model
  doi: 10.1080/13647830.2019.1602286
– ident: 10.1016/j.egyai.2021.100067_bib0045
– volume: 158
  start-page: 1980
  issue: 10
  year: 2011
  ident: 10.1016/j.egyai.2021.100067_bib0028
  article-title: Nonlinear combustion instability analysis based on the flame describing function applied to turbulent premixed swirling flames
  publication-title: Combust Flame
  doi: 10.1016/j.combustflame.2011.02.012
– volume: 31
  start-page: 085101
  issue: 8
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0040
  article-title: A deep learning enabler for nonintrusive reduced order modeling of fluid flows
  publication-title: Phys Fluids
  doi: 10.1063/1.5113494
– volume: 807
  start-page: 155-166
  year: 2016
  ident: 10.1016/j.egyai.2021.100067_bib0036
  article-title: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
  publication-title: J Fluid Mech
  doi: 10.1017/jfm.2016.615
– volume: 162
  start-page: 3632
  issue: 10
  year: 2015
  ident: 10.1016/j.egyai.2021.100067_bib0030
  article-title: Prediction of combustion instability limit cycle oscillations by combining flame describing function simulations with a thermoacoustic network model
  publication-title: Combust Flame
  doi: 10.1016/j.combustflame.2015.06.020
– volume: 11
  start-page: 064034
  issue: 6
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0034
  article-title: Early detection of thermoacoustic combustion instability using a methodology combining complex networks and machine learning
  publication-title: Phys Rev Appl
  doi: 10.1103/PhysRevApplied.11.064034
– start-page: 315
  year: 2011
  ident: 10.1016/j.egyai.2021.100067_bib0052
  article-title: Deep sparse rectifier neural networks
– volume: 8
  start-page: 1
  issue: 1
  year: 2009
  ident: 10.1016/j.egyai.2021.100067_bib0002
  article-title: Flame dynamics and combustion noise: progress and challenges
  publication-title: Int J Aeroacoust
  doi: 10.1260/147547209786234984
– start-page: 1
  year: 2019
  ident: 10.1016/j.egyai.2021.100067_bib0031
  article-title: Using machine learning to construct velocity fields from oh-plif images
  publication-title: Combust Sci Technol
SSID ssj0002511977
Score 2.3145885
Snippet highlights•A novel semi-supervised deep learning architecture for early detection of combustion instability.•Capturing transition from a stable to an unstable...
While analytical solutions of critical (phase) transitions in dynamical systems are abundant for simple nonlinear systems, such analysis remains intractable...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 100067
SubjectTerms 3D deep learning
Combustion instability
Convolutional autoencoder
Early detection
Gas turbine engines
Hi-speed video analytics
Instability precursors
Physics-based validation
Title 3D convolutional selective autoencoder for instability detection in combustion systems
URI https://dx.doi.org/10.1016/j.egyai.2021.100067
https://doaj.org/article/1672f29ae157493f904d01b94e71e7d5
Volume 4
WOSCitedRecordID wos001058070400002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2666-5468
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511977
  issn: 2666-5468
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2666-5468
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511977
  issn: 2666-5468
  databaseCode: M~E
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELYQYoAB8RTlpQyMRNiOa8cjTzFAxQAVW2SfL6gIWtSmSCz8dmwnLZnKwhIp1uUcnU--O-fLd4ScUOkcc06k2qD0BYpRqRGQpV2kGgUDZuM5ZP9O9Xr587N-aLX6Cpiwmh64NtwZk4qX3GtiXSV0VmoqHGVWC1QMlYvspT7raRVTYQ_m8fNY-FfaByCZdoXMZ5RDEdyFL19m4KtDzgJMgMYu879hKbL3t6JTK-LcbJD1JlVMzutX3CRLONwiay0CwW3Sz66SgBtv_MdLT2JfG7-FJWZajQJLpcNx4jPTZBASwQiF_UocVhGCNfSjXsG7DT29_F3N6zzZIU8314-Xt2nTKSEFwUSVgpWWIacCHBilUCFom0HpHFCZQ545biQ3GjgzpSopR6nRVxrSCF5CBtkuWR6OhrhHEuk05IJZNKFq9lbMBQhutewaK5G6DuEzQxXQ0IiHbhZvxQwv9lpE6xbBukVt3Q45nT_0UbNoLBa_CCswFw0U2HHAO0bROEbxl2N0iJytX9FkE3WW4FUNFs2-_x-zH5DVoLIGlR2S5Wo8xSOyAp_VYDI-js7qr_ff1z_xbu55
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=3D+convolutional+selective+autoencoder+for+instability+detection+in+combustion+systems&rft.jtitle=Energy+and+AI&rft.au=Gangopadhyay%2C+Tryambak&rft.au=Ramanan%2C+Vikram&rft.au=Akintayo%2C+Adedotun&rft.au=K+Boor%2C+Paige&rft.date=2021-06-01&rft.pub=Elsevier+Ltd&rft.issn=2666-5468&rft.eissn=2666-5468&rft.volume=4&rft_id=info:doi/10.1016%2Fj.egyai.2021.100067&rft.externalDocID=S2666546821000215
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2666-5468&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2666-5468&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2666-5468&client=summon