制冷技术2025，Vol.45Issue(4)：1-6,15,7.DOI:10.3969/j.issn.2095-4468.2025.04.101
基于神经网络的微纳颗粒辐射制冷器反射率预测
Prediction of Reflectivity for Radiative Coolers with Micro/Nano Particles Based on Artificial Neural Networks
刘乐洋 1宋锡昊 1张鹏1
作者信息
- 1. 上海交通大学制冷与低温工程研究所,上海 200240
- 折叠
摘要
Abstract
To address the issues of high computational cost and resource consumption in numerically predicting the spectral properties of radiative coolers,a method based on artificial neural network is proposed to predict the reflectivity of radiative coolers containing micro/nano particles.The proposed model demonstrates strong generalization capabilities for predicting radiative coolers with various materials and structural parameters.The influence of structural parameters on spectral reflectivity is investigated using this prediction model.The results indicate that increasing the thickness and volume fraction enhances the reflectivity of radiative coolers in the solar radiation spectrum band.Within the range of 0.1-0.5 μm,an increase in particle radius improves the spectral reflectivity in the solar radiation band,but it decreases when the particle radius exceeds 0.5 μm.Based on this law,parameter inverse optimization design is conducted for the spectral reflectivity of an ideal broadband radiative cooler,the calculated average reflectivity of the radiative cooler can reach 0.96 in the range of 0.25-2.5 μm.关键词
辐射制冷/人工神经网络/光谱反射特性Key words
Radiative cooling/Artificial neural network/Spectral reflection characteristics分类
通用工业技术引用本文复制引用
刘乐洋,宋锡昊,张鹏..基于神经网络的微纳颗粒辐射制冷器反射率预测[J].制冷技术,2025,45(4):1-6,15,7.
