Automatized segmentation of photovoltaic modules in IR-images with extreme noise |
| |
Affiliation: | 1. Institute of Solar Research, German Aerospace Center (DLR), Karl-Heinz-Beckurts-Str.13, 52428 Jülich, Germany;2. Institute of Solar Research, German Aerospace Center (DLR), Plataforma Solar de Almería, Tabernas 04200, Spain;3. Institute of Solar Research, German Aerospace Center (DLR), Linder Höhe, 51147 Cologne, Germany |
| |
Abstract: | Local electric defects may result in considerable performance losses in solar cells. Infrared thermography is an essential tool to detect these defects on photovoltaic modules. Accordingly, IR-thermography is frequently used in R&D labs of PV manufactures and, furthermore, outdoors in order to identify faulty modules in PV-power plants. Massive amount of data is acquired which needs to be analyzed. An automatized method for detecting solar modules in IR-images would enable a faster and automatized analysis of the data.However, IR-images tend to suffer from rather large noise, which makes an automatized segmentation challenging. The aim of this study was to establish a reliable segmentation algorithm for R&D labs. We propose an algorithm, which detects a solar cell or module within an IR-image with large noise. We tested the algorithm on images of 10 PV-samples characterized by highly sensitive dark lock-in thermography (DLIT). The algorithm proved to be very reliable in detecting correctly the solar module. In our study, we focused on thin film solar cells, however, a transfer of the algorithm to other cell types is straight forward. |
| |
Keywords: | IR-thermography DLIT Segmentation Solar module |
本文献已被 ScienceDirect 等数据库收录! |
|