An intelligent sensor validation and fault diagnostic technique for diesel engines

Research output: Contribution to journalArticle

Abstract

An intelligent sensor validation and on-line fault diagnosis technique for a 6 cylinder turbocharged diesel engine is proposed and studied. A single auto-associative 3-layer Artificial Neural Network (ANN), is trained to examine the accuracy of the measured data and allocate a confidence level to each signal. The same ANN is used to recover the missing or faulty data with a close approximation. For on-line fault detection a feed-forward ANN is trained to classify and consequently recognize faulty and healthy behavior of the engine for a wide range of operating conditions. The proposed technique is also equipped with an on-line learning mechanism, which is activated when the confidence level in predicted fault is poor. It is hoped that a feasible, practical, and reliable sensor reading, as well as highly accurate fault diagnosis system, would be achieved.
Original languageEnglish
Pages (from-to)141-144
JournalJournal of Dynamic Systems, Measurement and Control
Volume123
Issue number1
Publication statusPublished - Mar 2001
Externally publishedYes

Keywords

  • Neural networks
  • identification

Cite this

@article{a9b79abe726447dbba248e5e361ab6f0,
title = "An intelligent sensor validation and fault diagnostic technique for diesel engines",
abstract = "An intelligent sensor validation and on-line fault diagnosis technique for a 6 cylinder turbocharged diesel engine is proposed and studied. A single auto-associative 3-layer Artificial Neural Network (ANN), is trained to examine the accuracy of the measured data and allocate a confidence level to each signal. The same ANN is used to recover the missing or faulty data with a close approximation. For on-line fault detection a feed-forward ANN is trained to classify and consequently recognize faulty and healthy behavior of the engine for a wide range of operating conditions. The proposed technique is also equipped with an on-line learning mechanism, which is activated when the confidence level in predicted fault is poor. It is hoped that a feasible, practical, and reliable sensor reading, as well as highly accurate fault diagnosis system, would be achieved.",
keywords = "Neural networks, identification",
author = "E. Mesbahi",
year = "2001",
month = "3",
language = "English",
volume = "123",
pages = "141--144",
journal = "Journal of Dynamic Systems, Measurement and Control",
issn = "0022-0434",
publisher = "American Society of Mechanical Engineers",
number = "1",

}

An intelligent sensor validation and fault diagnostic technique for diesel engines. / Mesbahi, E.

In: Journal of Dynamic Systems, Measurement and Control, Vol. 123, No. 1, 03.2001, p. 141-144.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An intelligent sensor validation and fault diagnostic technique for diesel engines

AU - Mesbahi, E.

PY - 2001/3

Y1 - 2001/3

N2 - An intelligent sensor validation and on-line fault diagnosis technique for a 6 cylinder turbocharged diesel engine is proposed and studied. A single auto-associative 3-layer Artificial Neural Network (ANN), is trained to examine the accuracy of the measured data and allocate a confidence level to each signal. The same ANN is used to recover the missing or faulty data with a close approximation. For on-line fault detection a feed-forward ANN is trained to classify and consequently recognize faulty and healthy behavior of the engine for a wide range of operating conditions. The proposed technique is also equipped with an on-line learning mechanism, which is activated when the confidence level in predicted fault is poor. It is hoped that a feasible, practical, and reliable sensor reading, as well as highly accurate fault diagnosis system, would be achieved.

AB - An intelligent sensor validation and on-line fault diagnosis technique for a 6 cylinder turbocharged diesel engine is proposed and studied. A single auto-associative 3-layer Artificial Neural Network (ANN), is trained to examine the accuracy of the measured data and allocate a confidence level to each signal. The same ANN is used to recover the missing or faulty data with a close approximation. For on-line fault detection a feed-forward ANN is trained to classify and consequently recognize faulty and healthy behavior of the engine for a wide range of operating conditions. The proposed technique is also equipped with an on-line learning mechanism, which is activated when the confidence level in predicted fault is poor. It is hoped that a feasible, practical, and reliable sensor reading, as well as highly accurate fault diagnosis system, would be achieved.

KW - Neural networks

KW - identification

M3 - Article

VL - 123

SP - 141

EP - 144

JO - Journal of Dynamic Systems, Measurement and Control

JF - Journal of Dynamic Systems, Measurement and Control

SN - 0022-0434

IS - 1

ER -