Browse by author
Lookup NU author(s): Dr Wenxian YangORCiD
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by Springer , 2022.
For re-use rights please refer to the publisher's terms and conditions.
Despite the COVID-19 pandemic, the global photovoltaic (PV) market grew significantly again in 2021, further enhancing the vital role of solar power in the battle against global climate change. One of the main reasons for the rapid growth of this market is that PV panels are almost maintenance-free after deployment, thereby low Levelized cost of solar power. However, this does not mean that PV panels will not fail in service. In fact, they may suffer from performance degradation, structural failure, or even complete loss of power generation capacity during operation. If these problems cannot be detected and solved in time, they may also bring significant economic losses to the operators. However, a large-scale solar power plant will contain hundreds of thousands of PV panels. How to quickly identify those defective ones from so many PV panels is a quite challenging issue. The research of this paper is to address this issue with the aid of intelligent image processing technology. In this study, an intelligent PV panel condition monitoring technique is developed using machine learning algorithms. It can rapidly process, analyze and classify the thermal images of PV panels collected from solar power plants. Therefore, it not only can quickly identify those defective PV panels but also can accurately diagnose the defect types of the PV panels. It is deemed that the successful development of such a technology will be of great significance to further strengthen the scientific management of solar power assets.
Author(s): Wang X, Yang W, Wang J
Editor(s): Zhang, H
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: The 2022 International Conference of Efficiency and Performance Engineering Network (TEPEN 2022)
Year of Conference: 2022
Pages: 103-111
Online publication date: 04/03/2023
Acceptance date: 01/06/2022
Date deposited: 06/02/2023
Publisher: Springer
URL: https://doi.org/10.1007/978-3-031-26193-0_10
DOI: 10.1007/978-3-031-26193-0_10
ePrints DOI: 10.57711/5jmc-ts55
