A novel image enhancement algorithm to determine the dust level on photovoltaic (PV) panels

Siyuan Fan, Xiao Wang, Zun Wang, Bo Sun, Zhenhai Zhang, Shengxian Cao, Bo Zhao and Yu Wang

Renewable Energy, 2022, vol. 201, issue P1, 172-180

Abstract: An accurate evaluation of the dust accumulation on photovoltaic (PV) panels enables the development of cleaning plans and improves the grid connection security of PV power stations. In this paper, a novel image enhancement algorithm is proposed to evaluate the dust accumulation on PV panels. An atmospheric scattering model was used to analyze the difference in the image characteristics of clean and dusty PV panels. A model was proposed to describe the relationship between the model coefficient and the dust level by minimizing the pixel difference between the images of the soiled and clean PV panels. An experiment system was designed to acquire the images of clean and soiled PV panels with different dust levels. The model parameters were determined by data fitting, and the model’s generalization ability was improved by adding a noise item. The results show that the model can estimate the dust level on PV panels with an accuracy of 83.78%. The average root mean square error (RMSE) of samples 1–4 is 1.67, and the error range is 2–3.5 g/m2. In addition, the proposed method has higher accuracy than the optical attenuation and weighing methods, with a mean absolute error (MAE) of 1.61 g/m2. The method is simple and reliable for intelligent cleaning of PV panels.

Keywords: Image enhancement algorithm; Dust level; PV panels; Light transmission (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S096014812201566X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:201:y:2022:i:p1:p:172-180

DOI: 10.1016/j.renene.2022.10.073

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().