A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation
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 system...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9410264/ |
| _version_ | 1828965644447514624 |
|---|---|
| author | Khaled Dhibi Radhia Fezai Majdi Mansouri Mohamed Trabelsi Kais Bouzrara Hazem Nounou Mohamed Nounou |
| author_facet | Khaled Dhibi Radhia Fezai Majdi Mansouri Mohamed Trabelsi Kais Bouzrara Hazem Nounou Mohamed Nounou |
| author_sort | Khaled Dhibi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-14T11:14:59Z |
| format | Article |
| id | doaj.art-7677aa6776524706bcaa021c43bb1245 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T11:14:59Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7677aa6776524706bcaa021c43bb12452022-12-21T23:04:04ZengIEEEIEEE Access2169-35362021-01-019642676427710.1109/ACCESS.2021.30747849410264A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued RepresentationKhaled Dhibi0https://orcid.org/0000-0003-4802-9980Radhia Fezai1https://orcid.org/0000-0002-5281-8301Majdi Mansouri2https://orcid.org/0000-0001-6390-4304Mohamed Trabelsi3https://orcid.org/0000-0003-1955-0355Kais Bouzrara4https://orcid.org/0000-0003-2492-9626Hazem Nounou5https://orcid.org/0000-0001-8075-1581Mohamed Nounou6https://orcid.org/0000-0003-0520-9623Research Laboratory of Automation, Signal Processing and Image, National Engineering School of Monastir, Monastir, TunisiaResearch Laboratory of Automation, Signal Processing and Image, National Engineering School of Monastir, Monastir, TunisiaElectrical and Computer Engineering Program, Texas A&M University at Qatar, Doha, QatarElectronic and Communications Engineering Department, Kuwait College of Science and Technology, Safat, KuwaitResearch Laboratory of Automation, Signal Processing and Image, National Engineering School of Monastir, Monastir, TunisiaElectrical and Computer Engineering Program, Texas A&M University at Qatar, Doha, QatarChemical Engineering Program, Texas A&M University at Qatar, Doha, QatarThis 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.https://ieeexplore.ieee.org/document/9410264/Random forestinterval-valued datareduced kernel principal component analysisfault diagnosisfeature extraction and selectionfault classification |
| spellingShingle | Khaled Dhibi Radhia Fezai Majdi Mansouri Mohamed Trabelsi Kais Bouzrara Hazem Nounou Mohamed Nounou A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation IEEE Access Random forest interval-valued data reduced kernel principal component analysis fault diagnosis feature extraction and selection fault classification |
| 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 | hybrid fault detection and diagnosis of grid tied pv systems enhanced random forest classifier using data reduction and interval valued representation |
| topic | Random forest interval-valued data reduced kernel principal component analysis fault diagnosis feature extraction and selection fault classification |
| url | https://ieeexplore.ieee.org/document/9410264/ |
| work_keys_str_mv | AT khaleddhibi ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT radhiafezai ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT majdimansouri ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT mohamedtrabelsi ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT kaisbouzrara ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT hazemnounou ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT mohamednounou ahybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT khaleddhibi hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT radhiafezai hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT majdimansouri hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT mohamedtrabelsi hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT kaisbouzrara hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT hazemnounou hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation AT mohamednounou hybridfaultdetectionanddiagnosisofgridtiedpvsystemsenhancedrandomforestclassifierusingdatareductionandintervalvaluedrepresentation |