Non-linear minimum variance estimation for fault detection systems

Alkan Alkaya, Michael John Grimble

Research output: Contribution to journalArticle

1 Citation (Scopus)
77 Downloads (Pure)

Abstract

A novel model-based algorithm for fault detection in stochastic linear and non-linear systems is proposed. The non-linear minimum variance estimation technique is used to generate a residual signal, which is then used to detect actuator and sensor faults in the system. The main advantage of the approach is the simplicity of the non-linear estimator theory and the straightforward structure of the resulting solution. Simulation examples are presented to illustrate the design procedure and the type of results obtained. The results demonstrate that both actuator and sensor faults can be detected successfully.
Original languageEnglish
Pages (from-to)805-812
Number of pages8
JournalTransactions of the Institute of Measurement and Control
Volume37
Issue number6
Early online date24 Sep 2014
DOIs
Publication statusPublished - 29 May 2015

Fingerprint

fault detection
Fault detection
Actuators
actuators
sensors
Sensors
linear systems
nonlinear systems
estimators
Nonlinear systems
simulation

Keywords

  • condition monitoring
  • estimation
  • fault detection/diagnosis
  • non-linear observer
  • non-linear systems

Cite this

@article{975e9877d44f4691b217c490c078664d,
title = "Non-linear minimum variance estimation for fault detection systems",
abstract = "A novel model-based algorithm for fault detection in stochastic linear and non-linear systems is proposed. The non-linear minimum variance estimation technique is used to generate a residual signal, which is then used to detect actuator and sensor faults in the system. The main advantage of the approach is the simplicity of the non-linear estimator theory and the straightforward structure of the resulting solution. Simulation examples are presented to illustrate the design procedure and the type of results obtained. The results demonstrate that both actuator and sensor faults can be detected successfully.",
keywords = "condition monitoring, estimation, fault detection/diagnosis, non-linear observer, non-linear systems",
author = "Alkan Alkaya and Grimble, {Michael John}",
year = "2015",
month = "5",
day = "29",
doi = "10.1177/0142331214548304",
language = "English",
volume = "37",
pages = "805--812",
journal = "Transactions of the Institute of Measurement and Control",
issn = "0142-3312",
number = "6",

}

Non-linear minimum variance estimation for fault detection systems. / Alkaya, Alkan; Grimble, Michael John.

In: Transactions of the Institute of Measurement and Control, Vol. 37, No. 6, 29.05.2015, p. 805-812.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Non-linear minimum variance estimation for fault detection systems

AU - Alkaya, Alkan

AU - Grimble, Michael John

PY - 2015/5/29

Y1 - 2015/5/29

N2 - A novel model-based algorithm for fault detection in stochastic linear and non-linear systems is proposed. The non-linear minimum variance estimation technique is used to generate a residual signal, which is then used to detect actuator and sensor faults in the system. The main advantage of the approach is the simplicity of the non-linear estimator theory and the straightforward structure of the resulting solution. Simulation examples are presented to illustrate the design procedure and the type of results obtained. The results demonstrate that both actuator and sensor faults can be detected successfully.

AB - A novel model-based algorithm for fault detection in stochastic linear and non-linear systems is proposed. The non-linear minimum variance estimation technique is used to generate a residual signal, which is then used to detect actuator and sensor faults in the system. The main advantage of the approach is the simplicity of the non-linear estimator theory and the straightforward structure of the resulting solution. Simulation examples are presented to illustrate the design procedure and the type of results obtained. The results demonstrate that both actuator and sensor faults can be detected successfully.

KW - condition monitoring

KW - estimation

KW - fault detection/diagnosis

KW - non-linear observer

KW - non-linear systems

UR - http://tim.sagepub.com

U2 - 10.1177/0142331214548304

DO - 10.1177/0142331214548304

M3 - Article

VL - 37

SP - 805

EP - 812

JO - Transactions of the Institute of Measurement and Control

JF - Transactions of the Institute of Measurement and Control

SN - 0142-3312

IS - 6

ER -