A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation

<p>This paper proposes a novel fault detection and diagnosis (FDD) technique for grid-tied PV systems. The proposed approach deals with system uncertainties (current/voltage variability, noise, measurement errors, ⋯) by using an interval-valued data representation, and with large-scale systems...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Khaled Dhibi (16891524) (author)
مؤلفون آخرون: Radhia Fezai (16869888) (author), Majdi Mansouri (16869885) (author), Mohamed Trabelsi (16869891) (author), Kais Bouzrara (16869906) (author), Hazem Nounou (16869900) (author), Mohamed Nounou (3489386) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513562738688000
author Khaled Dhibi (16891524)
author2 Radhia Fezai (16869888)
Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Kais Bouzrara (16869906)
Hazem Nounou (16869900)
Mohamed Nounou (3489386)
author2_role author
author
author
author
author
author
author_facet Khaled Dhibi (16891524)
Radhia Fezai (16869888)
Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Kais Bouzrara (16869906)
Hazem Nounou (16869900)
Mohamed Nounou (3489386)
author_role author
dc.creator.none.fl_str_mv Khaled Dhibi (16891524)
Radhia Fezai (16869888)
Majdi Mansouri (16869885)
Mohamed Trabelsi (16869891)
Kais Bouzrara (16869906)
Hazem Nounou (16869900)
Mohamed Nounou (3489386)
dc.date.none.fl_str_mv 2021-04-21T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3074784
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Hybrid_Fault_Detection_and_Diagnosis_of_Grid-Tied_PV_Systems_Enhanced_Random_Forest_Classifier_Using_Data_Reduction_and_Interval-Valued_Representation/24042486
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Information and computing sciences
Data management and data science
Machine learning
Circuit faults
Data mining
Fault diagnosis
Feature extraction and selection
Feature extraction
Fault classification
Interval-valued data
Kernel
PV systems
Principal component analysis
Random forest
Radio frequency
Reduced kernel principal component analysis
Support vector machines
dc.title.none.fl_str_mv A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>This paper proposes a novel fault detection and diagnosis (FDD) technique for grid-tied PV systems. The proposed approach deals with system uncertainties (current/voltage variability, noise, measurement errors, ⋯) by using an interval-valued data representation, and with large-scale systems by using a dataset size-reduction framework. The failures encompassed in this study are the open-circuit/short-circuit, islanding, output current sensor, and partial shading faults. In the proposed FDD approach, named interval reduced kernel PCA (IRKPCA)-based Random Forest (IRKPCA-RF), the feature extraction and selection phase is performed using the IRKPCA models while the fault classification is ensured using the RF algorithm. The main contribution of the proposed approach is to provide a good trade-off between low computation time and high classification metrics. The performance of the proposed IRKPCA-RF approach is assessed using a set of emulated data of a grid-tied PV system operating under healthy and faulty conditions. The presented results show that the proposed IRKPCA-RF approach is characterized by enhanced diagnosis metrics, classification rate, and computation time compared to the classical techniques.</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.2021.3074784" target="_blank">https://dx.doi.org/10.1109/access.2021.3074784</a></p>
eu_rights_str_mv openAccess
id Manara2_284dc7cd56a2c16c117ff8049b60b9fc
identifier_str_mv 10.1109/access.2021.3074784
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24042486
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued RepresentationKhaled Dhibi (16891524)Radhia Fezai (16869888)Majdi Mansouri (16869885)Mohamed Trabelsi (16869891)Kais Bouzrara (16869906)Hazem Nounou (16869900)Mohamed Nounou (3489386)EngineeringElectrical engineeringInformation and computing sciencesData management and data scienceMachine learningCircuit faultsData miningFault diagnosisFeature extraction and selectionFeature extractionFault classificationInterval-valued dataKernelPV systemsPrincipal component analysisRandom forestRadio frequencyReduced kernel principal component analysisSupport vector machines<p>This paper proposes a novel fault detection and diagnosis (FDD) technique for grid-tied PV systems. The proposed approach deals with system uncertainties (current/voltage variability, noise, measurement errors, ⋯) by using an interval-valued data representation, and with large-scale systems by using a dataset size-reduction framework. The failures encompassed in this study are the open-circuit/short-circuit, islanding, output current sensor, and partial shading faults. In the proposed FDD approach, named interval reduced kernel PCA (IRKPCA)-based Random Forest (IRKPCA-RF), the feature extraction and selection phase is performed using the IRKPCA models while the fault classification is ensured using the RF algorithm. The main contribution of the proposed approach is to provide a good trade-off between low computation time and high classification metrics. The performance of the proposed IRKPCA-RF approach is assessed using a set of emulated data of a grid-tied PV system operating under healthy and faulty conditions. The presented results show that the proposed IRKPCA-RF approach is characterized by enhanced diagnosis metrics, classification rate, and computation time compared to the classical techniques.</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.2021.3074784" target="_blank">https://dx.doi.org/10.1109/access.2021.3074784</a></p>2021-04-21T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3074784https://figshare.com/articles/journal_contribution/A_Hybrid_Fault_Detection_and_Diagnosis_of_Grid-Tied_PV_Systems_Enhanced_Random_Forest_Classifier_Using_Data_Reduction_and_Interval-Valued_Representation/24042486CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240424862021-04-21T00:00:00Z
spellingShingle A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
Khaled Dhibi (16891524)
Engineering
Electrical engineering
Information and computing sciences
Data management and data science
Machine learning
Circuit faults
Data mining
Fault diagnosis
Feature extraction and selection
Feature extraction
Fault classification
Interval-valued data
Kernel
PV systems
Principal component analysis
Random forest
Radio frequency
Reduced kernel principal component analysis
Support vector machines
status_str publishedVersion
title A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
title_full A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
title_fullStr A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
title_full_unstemmed A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
title_short A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
title_sort A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
topic Engineering
Electrical engineering
Information and computing sciences
Data management and data science
Machine learning
Circuit faults
Data mining
Fault diagnosis
Feature extraction and selection
Feature extraction
Fault classification
Interval-valued data
Kernel
PV systems
Principal component analysis
Random forest
Radio frequency
Reduced kernel principal component analysis
Support vector machines