Přístupnostní navigace
E-application
Search Search Close
Publication detail
VANĚK, J. REPKO, I. KLÍMA, J. PEROUTKA, T.
Original Title
Automatic Detection of Defective Solar Modules by Thermovision
Type
article in a collection out of WoS and Scopus
Language
English
Original Abstract
This paper deals with the possibility of automated detection of defective solar modules by thermovision camera mounted on a dron or on the car roof. During thermovision imaging analysis of large photovoltaic power plants there are captured large numbers of images. These images are analyzed by human operators. Given the vast amount of images, which are sometimes very similar, and given of the specificity of some defects, the work of operators can be replaced by the automation recognizing of anomalies software. Two methods for the automatic detection of defects in thermal imaging pictures were developed and validated. First one method is based on the geometric information of tested modules and on the assumption that defective cell has an increased temperature along its whole surface and therefore will appear as a regular geometric shape which is recognizable by geometric comparisons. The second method does recognition by usage of trained artificial neural network.
Keywords
Diagnostic, Thermovision, Recognition, Automatic
Authors
VANĚK, J.; REPKO, I.; KLÍMA, J.; PEROUTKA, T.
Released
26. 7. 2016
Publisher
WIP
Location
Mnichov - Něměcko
ISBN
3-936338-41-8
Book
Proceedings of 32st European PV Solar Energy Conference and Exhibition
2196-0992
Periodical
EU PVSEC 2014 Proceedings DVD
State
Federal Republic of Germany
Pages from
1931
Pages to
1935
Pages count
5
BibTex
@inproceedings{BUT129338, author="Jiří {Vaněk} and Ilia {Repko} and Jakub {Klíma} and Tomáš {Peroutka}", title="Automatic Detection of Defective Solar Modules by Thermovision", booktitle="Proceedings of 32st European PV Solar Energy Conference and Exhibition", year="2016", journal="EU PVSEC 2014 Proceedings DVD", pages="1931--1935", publisher="WIP", address="Mnichov - Něměcko", doi="10.4229/EUPVSEC20162016-5BV.2.11", isbn="3-936338-41-8", issn="2196-0992" }