Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems

<p>The operation of heating, ventilation, and air conditioning (HVAC) systems is usually disturbed by many uncertainties such as measurement errors, noise, as well as temperature. Thus, this paper proposes a new multiscale interval principal component analysis (MSIPCA)-based machine learning (...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Sondes Gharsellaoui (16870047) (author)
مؤلفون آخرون: Majdi Mansouri (16869885) (author), Mohamed Trabelsi (16869891) (author), Mohamed-Faouzi Harkat (16869897) (author), Shady S. Refaat (16864269) (author), Hassani Messaoud (16870050) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513562757562368
author Sondes Gharsellaoui (16870047)
author2 Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Mohamed-Faouzi Harkat (16869897)
Shady S. Refaat (16864269)
Hassani Messaoud (16870050)
author2_role author
author
author
author
author
author_facet Sondes Gharsellaoui (16870047)
Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Mohamed-Faouzi Harkat (16869897)
Shady S. Refaat (16864269)
Hassani Messaoud (16870050)
author_role author
dc.creator.none.fl_str_mv Sondes Gharsellaoui (16870047)
Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Mohamed-Faouzi Harkat (16869897)
Shady S. Refaat (16864269)
Hassani Messaoud (16870050)
dc.date.none.fl_str_mv 2020-08-25T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2020.3019365
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Interval-Valued_Features_Based_Machine_Learning_Technique_for_Fault_Detection_and_Diagnosis_of_Uncertain_HVAC_Systems/24016068
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Mechanical engineering
Information and computing sciences
Machine learning
Buildings
Fault detection and diagnosis (FDD)
Feature extraction
Feature extraction and selection
HVAC systems
Interval-valued principal component analysis (IPCA)
Machine learning (ML)
Measurement errors
Monitoring
Model uncertainties
Principal component analysis
Standardization
Uncertainty
dc.title.none.fl_str_mv Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>The operation of heating, ventilation, and air conditioning (HVAC) systems is usually disturbed by many uncertainties such as measurement errors, noise, as well as temperature. Thus, this paper proposes a new multiscale interval principal component analysis (MSIPCA)-based machine learning (ML) technique for fault detection and diagnosis (FDD) of uncertain HVAC systems. The main goal of the developed MSIPCA-ML approach is to enhance the diagnosis performance, improve the indoor environment quality, and minimize the energy consumption in uncertain building systems. The model uncertainty is addressed by considering the interval-valued data representation. The performance of the proposed FDD is investigated using sets of synthetic and emulated data extracted under different operating conditions. The presented results confirm the high-efficiency of the developed technique in monitoring uncertain HVAC systems due to the high diagnosis capabilities of the interval feature-based support vector machines and k-nearest neighbors and their ability to distinguish between the different operating modes of the HVAC system.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3019365" target="_blank">https://dx.doi.org/10.1109/access.2020.3019365</a></p>
eu_rights_str_mv openAccess
id Manara2_81ac440fe409e5e81b268f6df2b1f2a4
identifier_str_mv 10.1109/access.2020.3019365
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24016068
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC SystemsSondes Gharsellaoui (16870047)Majdi Mansouri (16869885)Mohamed Trabelsi (16869891)Mohamed-Faouzi Harkat (16869897)Shady S. Refaat (16864269)Hassani Messaoud (16870050)EngineeringElectrical engineeringMechanical engineeringInformation and computing sciencesMachine learningBuildingsFault detection and diagnosis (FDD)Feature extractionFeature extraction and selectionHVAC systemsInterval-valued principal component analysis (IPCA)Machine learning (ML)Measurement errorsMonitoringModel uncertaintiesPrincipal component analysisStandardizationUncertainty<p>The operation of heating, ventilation, and air conditioning (HVAC) systems is usually disturbed by many uncertainties such as measurement errors, noise, as well as temperature. Thus, this paper proposes a new multiscale interval principal component analysis (MSIPCA)-based machine learning (ML) technique for fault detection and diagnosis (FDD) of uncertain HVAC systems. The main goal of the developed MSIPCA-ML approach is to enhance the diagnosis performance, improve the indoor environment quality, and minimize the energy consumption in uncertain building systems. The model uncertainty is addressed by considering the interval-valued data representation. The performance of the proposed FDD is investigated using sets of synthetic and emulated data extracted under different operating conditions. The presented results confirm the high-efficiency of the developed technique in monitoring uncertain HVAC systems due to the high diagnosis capabilities of the interval feature-based support vector machines and k-nearest neighbors and their ability to distinguish between the different operating modes of the HVAC system.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3019365" target="_blank">https://dx.doi.org/10.1109/access.2020.3019365</a></p>2020-08-25T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2020.3019365https://figshare.com/articles/journal_contribution/Interval-Valued_Features_Based_Machine_Learning_Technique_for_Fault_Detection_and_Diagnosis_of_Uncertain_HVAC_Systems/24016068CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240160682020-08-25T00:00:00Z
spellingShingle Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
Sondes Gharsellaoui (16870047)
Engineering
Electrical engineering
Mechanical engineering
Information and computing sciences
Machine learning
Buildings
Fault detection and diagnosis (FDD)
Feature extraction
Feature extraction and selection
HVAC systems
Interval-valued principal component analysis (IPCA)
Machine learning (ML)
Measurement errors
Monitoring
Model uncertainties
Principal component analysis
Standardization
Uncertainty
status_str publishedVersion
title Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
title_full Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
title_fullStr Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
title_full_unstemmed Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
title_short Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
title_sort Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems
topic Engineering
Electrical engineering
Mechanical engineering
Information and computing sciences
Machine learning
Buildings
Fault detection and diagnosis (FDD)
Feature extraction
Feature extraction and selection
HVAC systems
Interval-valued principal component analysis (IPCA)
Machine learning (ML)
Measurement errors
Monitoring
Model uncertainties
Principal component analysis
Standardization
Uncertainty