
Precise Inspection Method of Solar Photovoltaic Panel Using Optical and Thermal Infrared Sensor Image Taken by Drones
Author(s) -
Jeongsoo Park,
DongHo Lee
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/611/1/012089
Subject(s) - drone , computer science , point (geometry) , computer vision , photovoltaic system , artificial intelligence , visual inspection , real time computing , simulation , engineering , mathematics , electrical engineering , genetics , geometry , biology
The inspection of the solar panel using the drone has already been put into practical use. However, this method requires an initial investment cost as compared with the conventional method, and it may take a cost such as image processing. In addition, there are challenges such as the ability to carry out the necessary maintenance of the law even if technically possible. Nowadays, the introduction of drones is proceeding in such a way as to check the points of abnormalities through simple flight. The advantage of this method is that safety enhancement and inspection speed are greatly improved compared to the case of performing the inspection by the conventional method. For companies, the use of drones and thermal infrared sensors for inspection can be used to reduce the population and to reduce the problems of recruitment, and to improve the efficiency and reduce the cost by simplifying the inspection procedure with fewer personnel will be. The purpose of this study is to develop a method to accurately detect abnormal points by making thermal infrared images of orthographic images by improving the inspection method through simple flight of drone. The study investigated whether it is possible to precisely check the point where the problem is located under the condition of insufficient solar radiation at the site installed by a small developer. We propose a method that can accurately distinguish between normal and abnormal panel points in images taken using drones and thermal infrared sensors, and how to accurately detect abnormal points by focusing on problem panels. Abnormal points were found to be very accurate and efficient to find and inspect panel more than the temperature range value of each panel.