Symbolic identification for anomaly detection in aircraft gas turbine engines

Subhadeep Chakraborty, Soumik Sarka, Asok Ray, Shashi Phoha

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

2 Citations (Scopus)

Abstract

This paper presents a robust and computationally inexpensive technique of fault detection in aircraft gas-turbine engines, based on a recently developed statistical pattern recognition tool. The method involves abstraction of a qualitative description from a general dynamical system structure, using state space embedding of the output data-stream and discretization of the resultant pseudo state and input spaces. The system identification is achieved through grammatical inference techniques, and the deviation of the plant output from the nominal estimated language gives a metric for fault detection. The algorithm is validated on a numerical simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.

Original languageEnglish (US)
Title of host publicationProceedings of the 2010 American Control Conference, ACC 2010
Pages5954-5959
Number of pages6
StatePublished - 2010
Event2010 American Control Conference, ACC 2010 - Baltimore, MD, United States
Duration: Jun 30 2010Jul 2 2010

Other

Other2010 American Control Conference, ACC 2010
CountryUnited States
CityBaltimore, MD
Period6/30/107/2/10

Fingerprint

Fault detection
Gas turbines
Turbines
Aircraft
Aircraft engines
Pattern recognition
NASA
Identification (control systems)
Dynamical systems
Computer simulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Chakraborty, S., Sarka, S., Ray, A., & Phoha, S. (2010). Symbolic identification for anomaly detection in aircraft gas turbine engines. In Proceedings of the 2010 American Control Conference, ACC 2010 (pp. 5954-5959). [5531246]
Chakraborty, Subhadeep ; Sarka, Soumik ; Ray, Asok ; Phoha, Shashi. / Symbolic identification for anomaly detection in aircraft gas turbine engines. Proceedings of the 2010 American Control Conference, ACC 2010. 2010. pp. 5954-5959
@inproceedings{5664982660c24b8fb0b1fc6f12670ce5,
title = "Symbolic identification for anomaly detection in aircraft gas turbine engines",
abstract = "This paper presents a robust and computationally inexpensive technique of fault detection in aircraft gas-turbine engines, based on a recently developed statistical pattern recognition tool. The method involves abstraction of a qualitative description from a general dynamical system structure, using state space embedding of the output data-stream and discretization of the resultant pseudo state and input spaces. The system identification is achieved through grammatical inference techniques, and the deviation of the plant output from the nominal estimated language gives a metric for fault detection. The algorithm is validated on a numerical simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.",
author = "Subhadeep Chakraborty and Soumik Sarka and Asok Ray and Shashi Phoha",
year = "2010",
language = "English (US)",
isbn = "9781424474264",
pages = "5954--5959",
booktitle = "Proceedings of the 2010 American Control Conference, ACC 2010",

}

Chakraborty, S, Sarka, S, Ray, A & Phoha, S 2010, Symbolic identification for anomaly detection in aircraft gas turbine engines. in Proceedings of the 2010 American Control Conference, ACC 2010., 5531246, pp. 5954-5959, 2010 American Control Conference, ACC 2010, Baltimore, MD, United States, 6/30/10.

Symbolic identification for anomaly detection in aircraft gas turbine engines. / Chakraborty, Subhadeep; Sarka, Soumik; Ray, Asok; Phoha, Shashi.

Proceedings of the 2010 American Control Conference, ACC 2010. 2010. p. 5954-5959 5531246.

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

TY - GEN

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

AU - Chakraborty, Subhadeep

AU - Sarka, Soumik

AU - Ray, Asok

AU - Phoha, Shashi

PY - 2010

Y1 - 2010

N2 - This paper presents a robust and computationally inexpensive technique of fault detection in aircraft gas-turbine engines, based on a recently developed statistical pattern recognition tool. The method involves abstraction of a qualitative description from a general dynamical system structure, using state space embedding of the output data-stream and discretization of the resultant pseudo state and input spaces. The system identification is achieved through grammatical inference techniques, and the deviation of the plant output from the nominal estimated language gives a metric for fault detection. The algorithm is validated on a numerical simulation test-bed that is built upon the NASA C-MAPSS model of a generic commercial aircraft engine.

AB - This paper presents a robust and computationally inexpensive technique of fault detection in aircraft gas-turbine engines, based on a recently developed statistical pattern recognition tool. The method involves abstraction of a qualitative description from a general dynamical system structure, using state space embedding of the output data-stream and discretization of the resultant pseudo state and input spaces. The system identification is achieved through grammatical inference techniques, and the deviation of the plant output from the nominal estimated language gives a metric for fault detection. The algorithm is validated on a numerical 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=77957802334&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957802334&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424474264

SP - 5954

EP - 5959

BT - Proceedings of the 2010 American Control Conference, ACC 2010

ER -

Chakraborty S, Sarka S, Ray A, Phoha S. Symbolic identification for anomaly detection in aircraft gas turbine engines. In Proceedings of the 2010 American Control Conference, ACC 2010. 2010. p. 5954-5959. 5531246