Show simple item record

dc.contributor.authorGaroudja, Elyes
dc.contributor.authorChouder, Aissa
dc.contributor.authorKara, Kamel
dc.contributor.authorSilvestre Bergés, Santiago
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica
dc.date.accessioned2017-09-15T13:49:35Z
dc.date.available2019-09-14T00:25:34Z
dc.date.issued2017-09-14
dc.identifier.citationGaroudja, E., Chouder, A., Kara, K., Silvestre, S. An enhanced machine learning based approach for failures detection and diagnosis of PV systems. "Energy Conversion and Management (ECM_4383)", 14 Setembre 2017, vol. 151, p. 496-513.
dc.identifier.urihttp://hdl.handle.net/2117/107670
dc.description.abstractIn this paper, a novel procedure for fault detection and diagnosis in the direct current (DC) side of PV system, based on probabilistic neural network (PNN) classifier, is proposed. The suggested procedure consists of four main stages: (i) PV module parameters extraction, (ii) PV array simulation and experimental validation (iii) elaboration of a relevant database of both healthy and faulty operations, and (iv) network construction, training and testing. In the first stage, the unknown electrical parameters of the one diode model (ODM) are accurately identified using the best-so-far ABC algorithm. Then, based on these parameters the PV array is simulated and experimentally validated by using a PSIM™/Matlab™ co-simulation. Finally, efficient fault detection and diagnosis procedure based on PNN classifier is implemented. Four operating cases were tested in a grid connected PV system of 9.54 kWp: Healthy system, three modules short-circuited in one string, ten modules short-circuited in one string, and a string disconnected from the array. Moreover, the PNN method was compared, under real operating conditions, with the feed forward back-propagation Artificial Neural Network (ANN) classifiers method, for noiseless and noisy data to evaluate the suggested method’s accuracy and test its aptitude to support noisy data. The obtained results have demonstrated the high efficiency of the proposed method to detect and diagnose DC side anomalies for both noiseless and noisy data cases.
dc.format.extent18 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Energies::Energia solar fotovoltaica
dc.subject.lcshNeural networks (Computer science)
dc.subject.otherPhotovoltaic
dc.subject.otherFault detection
dc.subject.otherDiagnosis
dc.subject.otherProbabilistic neural network
dc.subject.otherArtificial neural network
dc.subject.otherBest-so-far ABC
dc.subject.otherMaximum power point
dc.titleAn enhanced machine learning based approach for failures detection and diagnosis of PV systems
dc.typeArticle
dc.subject.lemacXarxes neuronals (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. MNT - Grup de Recerca en Micro i Nanotecnologies
dc.identifier.doi10.1016/j.enconman.2017.09.019
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://www.sciencedirect.com/science/journal/01968904/151/supp/C?sdc=1
dc.rights.accessOpen Access
local.identifier.drac21543419
dc.description.versionPostprint (author's final draft)
local.citation.authorGaroudja, E.; Chouder, A.; Kara, K.; Silvestre, S.
local.citation.publicationNameEnergy Conversion and Management (ECM_4383)
local.citation.volume151
local.citation.startingPage496
local.citation.endingPage513


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain