Lean blow-out prediction in gas turbine combustors using symbolic time series analysis

Achintya Mukhopadhyay, Rajendra R. Chaudhari, Tanoy Paul, Swarnendu Sen, Asok Ray

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

This paper develops a novel strategy for prediction of lean blowout in gas turbine combustors based on symbolic analysis of time series data from optical sensors, where the range of instantaneous data is partitioned into a finite number of cells and a symbol is assigned to each cell. Depending on the cell to which a data point belongs, a symbolic value is assigned to the data point. Thus, the set of time series data is converted to a symbol string. The (estimated) state probability vector is computed based on the number of occurrence of each symbol over a given time span. For the purpose of detecting lean blowout in gas turbine combustors, the state probability vector obtained at a condition sufficiently away from lean blowout (reference state) is considered as the reference vector. The deviation of the current state vector from the reference state vector is used as an anomaly measure for early detection of lean blowout. The results showed that the rate of change of the anomaly measure with equivalence ratio changed significantly as the system approached lean blowout. This change in slope of the curve was observed approximately at a similar proximity to lean blowout for different operating conditions and, hence, could be used as an early lean blowout precursor. The actual location of the change of slope depended primarily on the choice of reference state. This technique performed satisfactorily over a wide range of premixing.

Original languageEnglish (US)
Pages (from-to)950-960
Number of pages11
JournalJournal of Propulsion and Power
Volume29
Issue number4
DOIs
StatePublished - Jul 1 2013

Fingerprint

blowout
time series analysis
Time series analysis
gas turbines
combustion chambers
Combustors
turbine
Gas turbines
state vectors
prediction
predictions
gas
cells
premixing
anomalies
slopes
Time series
optical measuring instruments
equivalence
Optical sensors

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Fuel Technology
  • Mechanical Engineering
  • Space and Planetary Science

Cite this

Mukhopadhyay, Achintya ; Chaudhari, Rajendra R. ; Paul, Tanoy ; Sen, Swarnendu ; Ray, Asok. / Lean blow-out prediction in gas turbine combustors using symbolic time series analysis. In: Journal of Propulsion and Power. 2013 ; Vol. 29, No. 4. pp. 950-960.
@article{c9de3ec785254e918c6f8c5fa40ea784,
title = "Lean blow-out prediction in gas turbine combustors using symbolic time series analysis",
abstract = "This paper develops a novel strategy for prediction of lean blowout in gas turbine combustors based on symbolic analysis of time series data from optical sensors, where the range of instantaneous data is partitioned into a finite number of cells and a symbol is assigned to each cell. Depending on the cell to which a data point belongs, a symbolic value is assigned to the data point. Thus, the set of time series data is converted to a symbol string. The (estimated) state probability vector is computed based on the number of occurrence of each symbol over a given time span. For the purpose of detecting lean blowout in gas turbine combustors, the state probability vector obtained at a condition sufficiently away from lean blowout (reference state) is considered as the reference vector. The deviation of the current state vector from the reference state vector is used as an anomaly measure for early detection of lean blowout. The results showed that the rate of change of the anomaly measure with equivalence ratio changed significantly as the system approached lean blowout. This change in slope of the curve was observed approximately at a similar proximity to lean blowout for different operating conditions and, hence, could be used as an early lean blowout precursor. The actual location of the change of slope depended primarily on the choice of reference state. This technique performed satisfactorily over a wide range of premixing.",
author = "Achintya Mukhopadhyay and Chaudhari, {Rajendra R.} and Tanoy Paul and Swarnendu Sen and Asok Ray",
year = "2013",
month = "7",
day = "1",
doi = "10.2514/1.B34711",
language = "English (US)",
volume = "29",
pages = "950--960",
journal = "Journal of Propulsion and Power",
issn = "0748-4658",
publisher = "American Institute of Aeronautics and Astronautics Inc. (AIAA)",
number = "4",

}

Lean blow-out prediction in gas turbine combustors using symbolic time series analysis. / Mukhopadhyay, Achintya; Chaudhari, Rajendra R.; Paul, Tanoy; Sen, Swarnendu; Ray, Asok.

In: Journal of Propulsion and Power, Vol. 29, No. 4, 01.07.2013, p. 950-960.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Lean blow-out prediction in gas turbine combustors using symbolic time series analysis

AU - Mukhopadhyay, Achintya

AU - Chaudhari, Rajendra R.

AU - Paul, Tanoy

AU - Sen, Swarnendu

AU - Ray, Asok

PY - 2013/7/1

Y1 - 2013/7/1

N2 - This paper develops a novel strategy for prediction of lean blowout in gas turbine combustors based on symbolic analysis of time series data from optical sensors, where the range of instantaneous data is partitioned into a finite number of cells and a symbol is assigned to each cell. Depending on the cell to which a data point belongs, a symbolic value is assigned to the data point. Thus, the set of time series data is converted to a symbol string. The (estimated) state probability vector is computed based on the number of occurrence of each symbol over a given time span. For the purpose of detecting lean blowout in gas turbine combustors, the state probability vector obtained at a condition sufficiently away from lean blowout (reference state) is considered as the reference vector. The deviation of the current state vector from the reference state vector is used as an anomaly measure for early detection of lean blowout. The results showed that the rate of change of the anomaly measure with equivalence ratio changed significantly as the system approached lean blowout. This change in slope of the curve was observed approximately at a similar proximity to lean blowout for different operating conditions and, hence, could be used as an early lean blowout precursor. The actual location of the change of slope depended primarily on the choice of reference state. This technique performed satisfactorily over a wide range of premixing.

AB - This paper develops a novel strategy for prediction of lean blowout in gas turbine combustors based on symbolic analysis of time series data from optical sensors, where the range of instantaneous data is partitioned into a finite number of cells and a symbol is assigned to each cell. Depending on the cell to which a data point belongs, a symbolic value is assigned to the data point. Thus, the set of time series data is converted to a symbol string. The (estimated) state probability vector is computed based on the number of occurrence of each symbol over a given time span. For the purpose of detecting lean blowout in gas turbine combustors, the state probability vector obtained at a condition sufficiently away from lean blowout (reference state) is considered as the reference vector. The deviation of the current state vector from the reference state vector is used as an anomaly measure for early detection of lean blowout. The results showed that the rate of change of the anomaly measure with equivalence ratio changed significantly as the system approached lean blowout. This change in slope of the curve was observed approximately at a similar proximity to lean blowout for different operating conditions and, hence, could be used as an early lean blowout precursor. The actual location of the change of slope depended primarily on the choice of reference state. This technique performed satisfactorily over a wide range of premixing.

UR - http://www.scopus.com/inward/record.url?scp=84880558519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880558519&partnerID=8YFLogxK

U2 - 10.2514/1.B34711

DO - 10.2514/1.B34711

M3 - Article

AN - SCOPUS:84880558519

VL - 29

SP - 950

EP - 960

JO - Journal of Propulsion and Power

JF - Journal of Propulsion and Power

SN - 0748-4658

IS - 4

ER -