Machine learning-assisted design of visibly transparent difunctional coatings for solar cell coloring and anti-reflection

Chengchao Wang, Kai Lu, Chengyuan Li, Lanxin Ma, Xingcan Li and Yan Zhou

Renewable Energy, 2025, vol. 249, issue C

Abstract: Low-efficiency loss functional coatings based on photonics design approaches effectively balance the aesthetic requirements and the conversion efficiency of building integrated photovoltaics (BIPVs). However, developing an effective tool to inversely design the structural parameters of the functional coatings according to the desired PV parameters and colors is still challenging. Here, we propose a visibly transparent difunctional coating with structural coloring and anti-reflective effects based on an inverse design approach combining high throughput radiative transfer calculations and machine learning. The visibly transparent coating consisting of core-shell nanoparticles SiO2@Ag and matrix PMMA achieves the coloration and anti-reflective dual-function by selectively absorbing visible light (localized surface plasmon resonance) and interfacial refractive index differences. Results show that the real colored Si solar cells integrated with difunctional coatings achieve low loss (4.9 %–10.2 %) coloration and have efficient anti-reflective effects. Furthermore, the proposed BDNN model achieves near-perfect prediction of colors and I-V curves and 99.7 % of MSE values are less than 0.1. The model also implements a high-precision (96.36 %) on-demand inverse design of colors and I-V curves. This work provides an efficient and flexible approach for designing real colored Si solar cells with anti-reflection, which is of special significance for promoting the development of BIPVs.

Keywords: Deep neural network; Si PV modules; Coloration and anti-reflecting; Radiative transfer; Core-shell nanoparticles (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148125008225
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:249:y:2025:i:c:s0960148125008225

DOI: 10.1016/j.renene.2025.123160

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 ().