Fault detection in photovoltaic arrays: a robust regularized machine learning approach

Basit Öğe Kaydı
dc.contributor.authorKilic, Heybet
dc.contributor.authorGumus, Bilal
dc.contributor.authorYilmaz, Musa
dc.date.accessioned2024-04-24T17:28:12Z
dc.date.available2024-04-24T17:28:12Z
dc.date.issued2020
dc.departmentDicle Üniversitesien_US
dc.description.abstractIn this paper, a robust data-driven method for fault detection in photovoltaic (PV) arrays is proposed. Our method is based on the random vector functional link networks (RVFLN) which has the advantage of randomly assigning hidden layer parameters with no tuning. To eliminate the effect of measurement noise and overfitting in the training process which reduce the fault detection accuracy, the sparse-regularization method is utilized which uses l2-norm with loss weighting factor to compute the output weights. To attain strong robustness against the outlier samples, the non-parametric kernel density estimation is employed to assign a loss weighting factor. Through rigorous simulation and experimental studies, we validate the performance of our proposed method in detecting the short and open circuit faults based on only the output current and voltage measurements of PV arrays. In addition to stronger robustness comparing with the least square-support vector machine, we also show that our proposed method provides 80% and 100% average detection accuracy for short circuit and open circuit, respectively.en_US
dc.identifier.doi10.6036/9856
dc.identifier.endpage628en_US
dc.identifier.issn0012-7361
dc.identifier.issn1989-1490
dc.identifier.issue6en_US
dc.identifier.startpage622en_US
dc.identifier.urihttps://doi.org/10.6036/9856
dc.identifier.urihttps://hdl.handle.net/11468/20364
dc.identifier.volume95en_US
dc.identifier.wosWOS:000585061800018
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.language.isoenen_US
dc.publisherFederacion Asociaciones Ingenieros Industriales Espanaen_US
dc.relation.ispartofDyna
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCanonical Correlation Analysisen_US
dc.subjectFault Detectionen_US
dc.subjectPhotovoltaic Arrayen_US
dc.subjectRandom Vector-Link Networken_US
dc.subjectSparse Regularizationen_US
dc.titleFault detection in photovoltaic arrays: a robust regularized machine learning approachen_US
dc.titleFault detection in photovoltaic arrays: a robust regularized machine learning approach
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu