Symbolic identification for fault detection in aircraft gas turbine engines

S. Chakraborty, S. Sarkar, Asok Ray

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This article presents a robust and computationally inexpensive technique of component-level fault detection in aircraft gas-turbine engines. The underlying algorithm is based on a recently developed statistical pattern recognition tool, symbolic dynamic filtering (SDF), that is built upon symbolization of sensor time series data. Fault detection involves abstraction of a language-theoretic description from a general dynamical system structure, using state space embedding of output data streams and discretization of the resultant pseudo-state and input spaces. System identification is achieved through grammatical inference based on the generated symbol sequences. The deviation of the plant output from the nominal estimated language yields a metric for fault detection. The algorithm is validated for both singleand multiple-component faults on a simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.

Original languageEnglish (US)
Pages (from-to)422-436
Number of pages15
JournalProceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering
Volume226
Issue number4
DOIs
StatePublished - Apr 1 2012

Fingerprint

Fault detection
Gas turbines
Turbines
Aircraft
Aircraft engines
Pattern recognition
NASA
Time series
Identification (control systems)
Dynamical systems
Sensors

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Mechanical Engineering

Cite this

@article{2477e991ff014a1497a461f672388cf5,
title = "Symbolic identification for fault detection in aircraft gas turbine engines",
abstract = "This article presents a robust and computationally inexpensive technique of component-level fault detection in aircraft gas-turbine engines. The underlying algorithm is based on a recently developed statistical pattern recognition tool, symbolic dynamic filtering (SDF), that is built upon symbolization of sensor time series data. Fault detection involves abstraction of a language-theoretic description from a general dynamical system structure, using state space embedding of output data streams and discretization of the resultant pseudo-state and input spaces. System identification is achieved through grammatical inference based on the generated symbol sequences. The deviation of the plant output from the nominal estimated language yields a metric for fault detection. The algorithm is validated for both singleand multiple-component faults on a simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.",
author = "S. Chakraborty and S. Sarkar and Asok Ray",
year = "2012",
month = "4",
day = "1",
doi = "10.1177/0954410011409980",
language = "English (US)",
volume = "226",
pages = "422--436",
journal = "Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering",
issn = "0954-4100",
publisher = "SAGE Publications Ltd",
number = "4",

}

Symbolic identification for fault detection in aircraft gas turbine engines. / Chakraborty, S.; Sarkar, S.; Ray, Asok.

In: Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, Vol. 226, No. 4, 01.04.2012, p. 422-436.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Symbolic identification for fault detection in aircraft gas turbine engines

AU - Chakraborty, S.

AU - Sarkar, S.

AU - Ray, Asok

PY - 2012/4/1

Y1 - 2012/4/1

N2 - This article presents a robust and computationally inexpensive technique of component-level fault detection in aircraft gas-turbine engines. The underlying algorithm is based on a recently developed statistical pattern recognition tool, symbolic dynamic filtering (SDF), that is built upon symbolization of sensor time series data. Fault detection involves abstraction of a language-theoretic description from a general dynamical system structure, using state space embedding of output data streams and discretization of the resultant pseudo-state and input spaces. System identification is achieved through grammatical inference based on the generated symbol sequences. The deviation of the plant output from the nominal estimated language yields a metric for fault detection. The algorithm is validated for both singleand multiple-component faults on a simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.

AB - This article presents a robust and computationally inexpensive technique of component-level fault detection in aircraft gas-turbine engines. The underlying algorithm is based on a recently developed statistical pattern recognition tool, symbolic dynamic filtering (SDF), that is built upon symbolization of sensor time series data. Fault detection involves abstraction of a language-theoretic description from a general dynamical system structure, using state space embedding of output data streams and discretization of the resultant pseudo-state and input spaces. System identification is achieved through grammatical inference based on the generated symbol sequences. The deviation of the plant output from the nominal estimated language yields a metric for fault detection. The algorithm is validated for both singleand multiple-component faults on a simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.

UR - http://www.scopus.com/inward/record.url?scp=84858226573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858226573&partnerID=8YFLogxK

U2 - 10.1177/0954410011409980

DO - 10.1177/0954410011409980

M3 - Article

VL - 226

SP - 422

EP - 436

JO - Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering

JF - Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering

SN - 0954-4100

IS - 4

ER -