Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system

Jinxin Wang , Zhongwei Wang, Viacheslav Stetsyuk, Xiuzhen Ma, Fengshou Gu, Wenhui Li

Research output: Contribution to journalArticle

Abstract

Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.
LanguageEnglish
Pages276-286
Number of pages11
JournalISA Transactions
Volume86
Early online date5 Nov 2018
DOIs
Publication statusPublished - Mar 2019

Fingerprint

Fault Isolation
diesel fuels
fuel injection
Fuel injection
Bayesian networks
Diesel fuels
Bayesian Networks
isolation
Injection
Diagnostics
Fault
Conditional probability
Prior Knowledge
diesel engines
machinery
Computational efficiency
simplification
Model Diagnostics
Uncertainty
maintenance

Cite this

@article{4b30c98ed2f84f6d8b450c061759e844,
title = "Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system",
abstract = "Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.",
keywords = "Fault isolation, Bayesian network, Diagnosis under uncertainty, Knowledge reduction, Diesel engine fuel injection system",
author = "Jinxin Wang and Zhongwei Wang and Viacheslav Stetsyuk and Xiuzhen Ma and Fengshou Gu and Wenhui Li",
year = "2019",
month = "3",
doi = "10.1016/j.isatra.2018.10.044",
language = "English",
volume = "86",
pages = "276--286",
journal = "ISA Transactions",
issn = "0019-0578",
publisher = "ISA - Instrumentation, Systems, and Automation Society",

}

Exploiting Bayesian networks for fault isolation : A diagnostic case study of diesel fuel injection system. / Wang , Jinxin; Wang, Zhongwei; Stetsyuk, Viacheslav; Ma, Xiuzhen; Gu, Fengshou; Li, Wenhui.

In: ISA Transactions, Vol. 86, 03.2019, p. 276-286.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploiting Bayesian networks for fault isolation

T2 - ISA Transactions

AU - Wang , Jinxin

AU - Wang, Zhongwei

AU - Stetsyuk, Viacheslav

AU - Ma, Xiuzhen

AU - Gu, Fengshou

AU - Li, Wenhui

PY - 2019/3

Y1 - 2019/3

N2 - Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.

AB - Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.

KW - Fault isolation

KW - Bayesian network

KW - Diagnosis under uncertainty

KW - Knowledge reduction

KW - Diesel engine fuel injection system

UR - http://www.scopus.com/inward/record.url?scp=85056412871&partnerID=8YFLogxK

U2 - 10.1016/j.isatra.2018.10.044

DO - 10.1016/j.isatra.2018.10.044

M3 - Article

VL - 86

SP - 276

EP - 286

JO - ISA Transactions

JF - ISA Transactions

SN - 0019-0578

ER -