Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults

This study puts forward a novel diagnostic approach based on canonical variate residuals (CVR) to implement incipient fault diagnosis for dynamic process monitoring. The conventional canonical variate analysis (CVA) fault detection approach is extended to form a new monitoring index based on Hotelli...

Full description

Bibliographic Details
Main Authors: Xiaochuan Li, David Mba, Demba Diallo, Claude Delpha
Format: Article
Language:English
Published: MDPI AG 2019-02-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/12/4/726
_version_ 1818013567667929088
author Xiaochuan Li
David Mba
Demba Diallo
Claude Delpha
author_facet Xiaochuan Li
David Mba
Demba Diallo
Claude Delpha
author_sort Xiaochuan Li
collection DOAJ
description This study puts forward a novel diagnostic approach based on canonical variate residuals (CVR) to implement incipient fault diagnosis for dynamic process monitoring. The conventional canonical variate analysis (CVA) fault detection approach is extended to form a new monitoring index based on Hotelling&#8217;s <inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mi>T</mi> <mn>2</mn> </msup> </mrow> </semantics> </math> </inline-formula>, <inline-formula> <math display="inline"> <semantics> <mrow> <mi>Q</mi> </mrow> </semantics> </math> </inline-formula> and a CVR-based monitoring index, <inline-formula> <math display="inline"> <semantics> <mrow> <msub> <mi>T</mi> <mi>d</mi> </msub> </mrow> </semantics> </math> </inline-formula>. A CVR-based contribution plot approach is also proposed based on <inline-formula> <math display="inline"> <semantics> <mi>Q</mi> </semantics> </math> </inline-formula> and <inline-formula> <math display="inline"> <semantics> <mrow> <msub> <mi>T</mi> <mi>d</mi> </msub> </mrow> </semantics> </math> </inline-formula> statistics. Two performance metrics: (1) false alarm rate and (2) missed detection rate are used to assess the effectiveness of the proposed approach. The CVR diagnostic approach was validated on incipient faults in a continuous stirred tank reactor (CSTR) system and an operational centrifugal compressor.
first_indexed 2024-04-14T06:34:49Z
format Article
id doaj.art-c47d023757514892924279d7f1cccc7b
institution Directory Open Access Journal
issn 1996-1073
language English
last_indexed 2024-04-14T06:34:49Z
publishDate 2019-02-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj.art-c47d023757514892924279d7f1cccc7b2022-12-22T02:07:30ZengMDPI AGEnergies1996-10732019-02-0112472610.3390/en12040726en12040726Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving FaultsXiaochuan Li0David Mba1Demba Diallo2Claude Delpha3Faculty of Computing, Engineering and Media, De Montfort University, Leicester LE1 9BH, UKFaculty of Computing, Engineering and Media, De Montfort University, Leicester LE1 9BH, UKLaboratoire Génie Electrique et Électronique de Paris (GeePs), CNRS, CentraleSupélec, Université Paris-Sud, 91190 Gif Sur Yvette, FranceLaboratoire des Signaux et Systèmes (L2S), CNRS, CentraleSupélec, Université Paris-Sud, 91192 Gif Sur Yvette, FranceThis study puts forward a novel diagnostic approach based on canonical variate residuals (CVR) to implement incipient fault diagnosis for dynamic process monitoring. The conventional canonical variate analysis (CVA) fault detection approach is extended to form a new monitoring index based on Hotelling&#8217;s <inline-formula> <math display="inline"> <semantics> <mrow> <msup> <mi>T</mi> <mn>2</mn> </msup> </mrow> </semantics> </math> </inline-formula>, <inline-formula> <math display="inline"> <semantics> <mrow> <mi>Q</mi> </mrow> </semantics> </math> </inline-formula> and a CVR-based monitoring index, <inline-formula> <math display="inline"> <semantics> <mrow> <msub> <mi>T</mi> <mi>d</mi> </msub> </mrow> </semantics> </math> </inline-formula>. A CVR-based contribution plot approach is also proposed based on <inline-formula> <math display="inline"> <semantics> <mi>Q</mi> </semantics> </math> </inline-formula> and <inline-formula> <math display="inline"> <semantics> <mrow> <msub> <mi>T</mi> <mi>d</mi> </msub> </mrow> </semantics> </math> </inline-formula> statistics. Two performance metrics: (1) false alarm rate and (2) missed detection rate are used to assess the effectiveness of the proposed approach. The CVR diagnostic approach was validated on incipient faults in a continuous stirred tank reactor (CSTR) system and an operational centrifugal compressor.https://www.mdpi.com/1996-1073/12/4/726slowly evolving faultsfault detectionfault identification
spellingShingle Xiaochuan Li
David Mba
Demba Diallo
Claude Delpha
Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
Energies
slowly evolving faults
fault detection
fault identification
title Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
title_full Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
title_fullStr Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
title_full_unstemmed Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
title_short Canonical Variate Residuals-Based Fault Diagnosis for Slowly Evolving Faults
title_sort canonical variate residuals based fault diagnosis for slowly evolving faults
topic slowly evolving faults
fault detection
fault identification
url https://www.mdpi.com/1996-1073/12/4/726
work_keys_str_mv AT xiaochuanli canonicalvariateresidualsbasedfaultdiagnosisforslowlyevolvingfaults
AT davidmba canonicalvariateresidualsbasedfaultdiagnosisforslowlyevolvingfaults
AT dembadiallo canonicalvariateresidualsbasedfaultdiagnosisforslowlyevolvingfaults
AT claudedelpha canonicalvariateresidualsbasedfaultdiagnosisforslowlyevolvingfaults