Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities

Soumalya Sarkar, Devesh K. Jha, Kin G. Lore, Soumik Sarkar, Asok Ray

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Detection and prediction of combustion instabilities are of interest to the gas turbine engine community with many practical applications. This paper presents a dynamic data-driven approach to accurately detect precursors to the combustion instability phenomena. In particular, grey-scale images of combustion flames have been used in combination with pressure time-series data for information fusion to detect and predict flame instabilities in the combustion process. These grey-scale images are analyzed using deep belief network (DBN). The cross-dependencies between the features extracted by the DBN and the symbolic sequences generated from pressure time-series are then analyzed using ×D-Markov (pronounced cross D-Markov) models that are constructed by a combination of state-splitting and cross-entropy rate; this leads to the development of a variable-memory cross-model as a representation of the underlying physical process. These cross-models are then used for detection and prediction of combustion instability phenomena. The proposed concept is validated on experimental data collected from a laboratory-scale swirl-stabilized combustor apparatus, where the instability phenomena are induced by typical protocols leading to unstable flames.

Original languageEnglish (US)
Title of host publication2016 American Control Conference, ACC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4918-4923
Number of pages6
ISBN (Electronic)9781467386821
DOIs
StatePublished - Jul 28 2016
Event2016 American Control Conference, ACC 2016 - Boston, United States
Duration: Jul 6 2016Jul 8 2016

Publication series

NameProceedings of the American Control Conference
Volume2016-July
ISSN (Print)0743-1619

Other

Other2016 American Control Conference, ACC 2016
CountryUnited States
CityBoston
Period7/6/167/8/16

Fingerprint

Information fusion
Bayesian networks
Time series
Combustors
Gas turbines
Turbines
Entropy
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Sarkar, S., Jha, D. K., Lore, K. G., Sarkar, S., & Ray, A. (2016). Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities. In 2016 American Control Conference, ACC 2016 (pp. 4918-4923). [7526132] (Proceedings of the American Control Conference; Vol. 2016-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACC.2016.7526132
Sarkar, Soumalya ; Jha, Devesh K. ; Lore, Kin G. ; Sarkar, Soumik ; Ray, Asok. / Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities. 2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 4918-4923 (Proceedings of the American Control Conference).
@inproceedings{55c5681296654ae486af192182c86498,
title = "Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities",
abstract = "Detection and prediction of combustion instabilities are of interest to the gas turbine engine community with many practical applications. This paper presents a dynamic data-driven approach to accurately detect precursors to the combustion instability phenomena. In particular, grey-scale images of combustion flames have been used in combination with pressure time-series data for information fusion to detect and predict flame instabilities in the combustion process. These grey-scale images are analyzed using deep belief network (DBN). The cross-dependencies between the features extracted by the DBN and the symbolic sequences generated from pressure time-series are then analyzed using ×D-Markov (pronounced cross D-Markov) models that are constructed by a combination of state-splitting and cross-entropy rate; this leads to the development of a variable-memory cross-model as a representation of the underlying physical process. These cross-models are then used for detection and prediction of combustion instability phenomena. The proposed concept is validated on experimental data collected from a laboratory-scale swirl-stabilized combustor apparatus, where the instability phenomena are induced by typical protocols leading to unstable flames.",
author = "Soumalya Sarkar and Jha, {Devesh K.} and Lore, {Kin G.} and Soumik Sarkar and Asok Ray",
year = "2016",
month = "7",
day = "28",
doi = "10.1109/ACC.2016.7526132",
language = "English (US)",
series = "Proceedings of the American Control Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4918--4923",
booktitle = "2016 American Control Conference, ACC 2016",
address = "United States",

}

Sarkar, S, Jha, DK, Lore, KG, Sarkar, S & Ray, A 2016, Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities. in 2016 American Control Conference, ACC 2016., 7526132, Proceedings of the American Control Conference, vol. 2016-July, Institute of Electrical and Electronics Engineers Inc., pp. 4918-4923, 2016 American Control Conference, ACC 2016, Boston, United States, 7/6/16. https://doi.org/10.1109/ACC.2016.7526132

Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities. / Sarkar, Soumalya; Jha, Devesh K.; Lore, Kin G.; Sarkar, Soumik; Ray, Asok.

2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 4918-4923 7526132 (Proceedings of the American Control Conference; Vol. 2016-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities

AU - Sarkar, Soumalya

AU - Jha, Devesh K.

AU - Lore, Kin G.

AU - Sarkar, Soumik

AU - Ray, Asok

PY - 2016/7/28

Y1 - 2016/7/28

N2 - Detection and prediction of combustion instabilities are of interest to the gas turbine engine community with many practical applications. This paper presents a dynamic data-driven approach to accurately detect precursors to the combustion instability phenomena. In particular, grey-scale images of combustion flames have been used in combination with pressure time-series data for information fusion to detect and predict flame instabilities in the combustion process. These grey-scale images are analyzed using deep belief network (DBN). The cross-dependencies between the features extracted by the DBN and the symbolic sequences generated from pressure time-series are then analyzed using ×D-Markov (pronounced cross D-Markov) models that are constructed by a combination of state-splitting and cross-entropy rate; this leads to the development of a variable-memory cross-model as a representation of the underlying physical process. These cross-models are then used for detection and prediction of combustion instability phenomena. The proposed concept is validated on experimental data collected from a laboratory-scale swirl-stabilized combustor apparatus, where the instability phenomena are induced by typical protocols leading to unstable flames.

AB - Detection and prediction of combustion instabilities are of interest to the gas turbine engine community with many practical applications. This paper presents a dynamic data-driven approach to accurately detect precursors to the combustion instability phenomena. In particular, grey-scale images of combustion flames have been used in combination with pressure time-series data for information fusion to detect and predict flame instabilities in the combustion process. These grey-scale images are analyzed using deep belief network (DBN). The cross-dependencies between the features extracted by the DBN and the symbolic sequences generated from pressure time-series are then analyzed using ×D-Markov (pronounced cross D-Markov) models that are constructed by a combination of state-splitting and cross-entropy rate; this leads to the development of a variable-memory cross-model as a representation of the underlying physical process. These cross-models are then used for detection and prediction of combustion instability phenomena. The proposed concept is validated on experimental data collected from a laboratory-scale swirl-stabilized combustor apparatus, where the instability phenomena are induced by typical protocols leading to unstable flames.

UR - http://www.scopus.com/inward/record.url?scp=84992062721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992062721&partnerID=8YFLogxK

U2 - 10.1109/ACC.2016.7526132

DO - 10.1109/ACC.2016.7526132

M3 - Conference contribution

AN - SCOPUS:84992062721

T3 - Proceedings of the American Control Conference

SP - 4918

EP - 4923

BT - 2016 American Control Conference, ACC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sarkar S, Jha DK, Lore KG, Sarkar S, Ray A. Multimodal spatiotemporal information fusion using neural-symbolic modeling for early detection of combustion instabilities. In 2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 4918-4923. 7526132. (Proceedings of the American Control Conference). https://doi.org/10.1109/ACC.2016.7526132