The number of distributed Photovoltaic (PV) plants that produce electricity has been significantly increased, and issue of monitoringand maintaining a PV plant has become of great importance and involves many challenges as efficiency, reliability, safety, and stability.This paper presents the novel approach to estimate the PV cells degradations with DCNNs. While many studies have performedimages classification, to the best of our knowledge, this is the first exploitation of data acquired with a drone equipped with a thermalinfrared sensor. The experiments on “Photovoltaic images Dataset”, a collected dataset, are presented to show the degradation problemand comprehensively evaluate the method presented in this research. Results in terms of precision, recall and F1-score show theeffectiveness and the suitability of the proposed approach.

Deep convolutional neural network for automatic detection of damaged photovoltaic cells / Pierdicca, R.; Malinverni, E. S.; Piccinini, Fabio; Paolanti, M.; Felicetti, A.; Zingaretti, P.. - In: INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES. - ISSN 1682-1750. - ELETTRONICO. - 42:(2018), pp. 893-900. (Intervento presentato al convegno 2018 ISPRS TC II Mid-term Symposium "Towards Photogrammetry 2020" tenutosi a Riva del Garda, Italy nel 4–7 June 2018) [10.5194/isprs-archives-XLII-2-893-2018].

Deep convolutional neural network for automatic detection of damaged photovoltaic cells

Pierdicca, R.
Methodology
;
Malinverni, E. S.
Methodology
;
PICCININI, FABIO
Data Curation
;
Paolanti, M.
Supervision
;
Felicetti, A.
Formal Analysis
;
Zingaretti, P.
Methodology
2018-01-01

Abstract

The number of distributed Photovoltaic (PV) plants that produce electricity has been significantly increased, and issue of monitoringand maintaining a PV plant has become of great importance and involves many challenges as efficiency, reliability, safety, and stability.This paper presents the novel approach to estimate the PV cells degradations with DCNNs. While many studies have performedimages classification, to the best of our knowledge, this is the first exploitation of data acquired with a drone equipped with a thermalinfrared sensor. The experiments on “Photovoltaic images Dataset”, a collected dataset, are presented to show the degradation problemand comprehensively evaluate the method presented in this research. Results in terms of precision, recall and F1-score show theeffectiveness and the suitability of the proposed approach.
2018
International Archives Photogrammetry Remote Sensing Spatial Information Science
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/265911
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 111
  • ???jsp.display-item.citation.isi??? ND
social impact