Information theoretic fault detection

Alok Joshi, Paul Deignan, Peter Meckl, Galen King, Kristofer Jennings

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

3 Citations (Scopus)

Abstract

In this paper we propose a novel method of fault detection based on a clustering algorithm developed in the information theoretic framework. A mathematical formulation for a multi-input multi-output (MIMO) system is developed to identify the most informative signals for the fault detection using mutual information (MI) as the measure of correlation among various measurements on the system. This is a model-independent approach for the fault detection. The effectiveness of the proposed method is successfully demonstrated by employing MI-based algorithm to isolate various faults in 16-cylinder diesel engine in the form of distinct clusters.

Original languageEnglish (US)
Title of host publicationProceedings of the American Control Conference
Pages1642-1647
Number of pages6
Volume3
StatePublished - 2005
Externally publishedYes
Event2005 American Control Conference, ACC - Portland, OR, United States
Duration: Jun 8 2005Jun 10 2005

Other

Other2005 American Control Conference, ACC
CountryUnited States
CityPortland, OR
Period6/8/056/10/05

Fingerprint

Fault detection
Engine cylinders
Clustering algorithms
Diesel engines

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Joshi, A., Deignan, P., Meckl, P., King, G., & Jennings, K. (2005). Information theoretic fault detection. In Proceedings of the American Control Conference (Vol. 3, pp. 1642-1647). [WeC15.2]

Information theoretic fault detection. / Joshi, Alok; Deignan, Paul; Meckl, Peter; King, Galen; Jennings, Kristofer.

Proceedings of the American Control Conference. Vol. 3 2005. p. 1642-1647 WeC15.2.

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

Joshi, A, Deignan, P, Meckl, P, King, G & Jennings, K 2005, Information theoretic fault detection. in Proceedings of the American Control Conference. vol. 3, WeC15.2, pp. 1642-1647, 2005 American Control Conference, ACC, Portland, OR, United States, 6/8/05.
Joshi A, Deignan P, Meckl P, King G, Jennings K. Information theoretic fault detection. In Proceedings of the American Control Conference. Vol. 3. 2005. p. 1642-1647. WeC15.2
Joshi, Alok ; Deignan, Paul ; Meckl, Peter ; King, Galen ; Jennings, Kristofer. / Information theoretic fault detection. Proceedings of the American Control Conference. Vol. 3 2005. pp. 1642-1647
@inproceedings{46dc2be8e5c5416eb6f7f84f01358497,
title = "Information theoretic fault detection",
abstract = "In this paper we propose a novel method of fault detection based on a clustering algorithm developed in the information theoretic framework. A mathematical formulation for a multi-input multi-output (MIMO) system is developed to identify the most informative signals for the fault detection using mutual information (MI) as the measure of correlation among various measurements on the system. This is a model-independent approach for the fault detection. The effectiveness of the proposed method is successfully demonstrated by employing MI-based algorithm to isolate various faults in 16-cylinder diesel engine in the form of distinct clusters.",
author = "Alok Joshi and Paul Deignan and Peter Meckl and Galen King and Kristofer Jennings",
year = "2005",
language = "English (US)",
volume = "3",
pages = "1642--1647",
booktitle = "Proceedings of the American Control Conference",

}

TY - GEN

T1 - Information theoretic fault detection

AU - Joshi, Alok

AU - Deignan, Paul

AU - Meckl, Peter

AU - King, Galen

AU - Jennings, Kristofer

PY - 2005

Y1 - 2005

N2 - In this paper we propose a novel method of fault detection based on a clustering algorithm developed in the information theoretic framework. A mathematical formulation for a multi-input multi-output (MIMO) system is developed to identify the most informative signals for the fault detection using mutual information (MI) as the measure of correlation among various measurements on the system. This is a model-independent approach for the fault detection. The effectiveness of the proposed method is successfully demonstrated by employing MI-based algorithm to isolate various faults in 16-cylinder diesel engine in the form of distinct clusters.

AB - In this paper we propose a novel method of fault detection based on a clustering algorithm developed in the information theoretic framework. A mathematical formulation for a multi-input multi-output (MIMO) system is developed to identify the most informative signals for the fault detection using mutual information (MI) as the measure of correlation among various measurements on the system. This is a model-independent approach for the fault detection. The effectiveness of the proposed method is successfully demonstrated by employing MI-based algorithm to isolate various faults in 16-cylinder diesel engine in the form of distinct clusters.

UR - http://www.scopus.com/inward/record.url?scp=23944502367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23944502367&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 1642

EP - 1647

BT - Proceedings of the American Control Conference

ER -