Defect Identification of Solar Panels Using Improved Faster R-CNN

被引：0

作者：

Zhang W. ^{[1
]}

Ma Y. ^{[1
]}

Bai X. ^{[1
]}

Tan Y. ^{[2
]}

Pi Y. ^{[1
]}

机构：

[1] School of Control and Computer Engineering, North China Electric Power University, Changping District, Beijing

[2] China Electric Power Research Institute, Haidian District, Beijing

来源：

Dianwang Jishu/Power System Technology | 2022年 / 46卷 / 07期

关键词：

CNN; defect identification; image processing; object detection; solar panel;

D O I：

10.13335/j.1000-3673.pst.2021.2373

中图分类号：

学科分类号：

摘要：

Solar energy is playing a more important role in renewable energy. However, the power generation efficiency of solar panels will be greatly reduced by the dust and bird droppings on the panels. Therefore, it is essential to identify the defects of solar panels. This paper investigates the defect identification of solar panels using the improved Faster R-CNN. The improvements on the model are given as follows: Due to insufficient samples, the operations such as color space conversion, rotation and mosaic data enhancement are adopted. The backbone network is replaced by a better ResNeSt-50 network. Because the sizes of dust and bird droppings are quite different, a target size equalization strategy is applied. In order to independently learn the classification and regression tasks, the task-aware disentanglement is used. Moreover, the Cosine learning rate is adopted to avoid the network falling into the local minimum. All these improvements increase the mAP value from the baseline of 78.91% to 94.05%. Finally, the single solar panel is extracted from the UAV images and the angle correction is also implemented. In addition, its defect identification is conducted using the improved Faster R-CNN. The results prove that the defects of dust and bird droppings can be more accurately identified. © 2022 Power System Technology Press. All rights reserved.

引用

页码：2593 / 2600

页数：7

共 28 条

[1] BOURAIOU A, HAMOUDA M, CHAKER A, Analysis and evaluation of the impact of climatic conditions on the photovoltaic modules performance in the desert environment[J], Energy Conversion and Management, 106, pp. 1345-1355, (2015)
[2] Renewables 2019
[3] QU Hongwei, WANG Jingwen, Theory and experimental research of effect of dust deposition on output characteristics of PV module[J], Acta Energiae Solaris Sinica, 39, 8, pp. 2335-2340, (2018)
[4] LIU Xiaoyan, QI Xinmei, ZHENG Shousen, Model and analysis of photovoltaic array under partial shading[J], Power System Technology, 34, 11, pp. 192-197, (2010)
[5] ZANG Jianbin, WANG Yawei, WANG Xiaodong, Computation model and experiment of dust deposition affecting transmittance of photovoltaic module[J], Acta Energiae Solaris Sinica, 35, 4, pp. 624-629, (2014)
[6] SANTHAKUMARI M, SAGAR N．, A review of the environmental factors degrading the performance of silicon wafer-based photovoltaic modules ： Failure detection methods and essential mitigation techniques[J], Renewable and Sustainable Energy Reviews, 110, pp. 83-100, (2019)
[7] ZAIHIDEE F M，, MEKHILEF S, SEYEDMAHMOUDIAN M, Dust as an unalterable deteriorative factor affecting PV panel's efficiency：why and how[J], Renewable and Sustainable Energy Reviews, 65, pp. 1267-1278, (2016)
[8] GASPARIN F P，, BUHLER A J，, RAMPINELLI G A, Statistical analysis of I-V curve parameters from photovoltaic modules[J], Solar Energy, 131, pp. 30-38, (2016)
[9] Yuanliang LI, Kun DING, ZHANG Jingwei, A fault diagnosis method for photovoltaic arrays based on fault parameters identification[J], Renewable Energy, 143, pp. 52-63, (2019)
[10] MARQUEZ F, RAMIREZ I S．, Condition monitoring system for solar power plants with radiometric and thermographic sensors embedded in unmanned aerial vehicles[J], Measurement, 139, pp. 152-162, (2019)

← 1 2 3 →