基于机器学习的钙钛矿太阳能电池性能预测与影响因素研究  

Machine Learning-Based Prediction and Influencing Factors on the Performance of Perovskite Solar Cells

作　　者：彭丽玲 钱佳静 贾新航 王越越 范国锋 

机构地区：[1]平顶山学院数学与统计学院,河南 平顶山

出　　处：《可持续能源》2024年第4期53-64,共12页Sustainable Energy

摘　　要：太阳能高效利用是可持续发展核心,太阳能电池性能提升尤为关键。本文针对钙钛矿太阳能电池(PSC)的性能,利用统计学进行特征提取,运用机器学习构建结构–性能模型,快速筛选高效光伏材料,为PSC性能提升提供新途径。通过回归预测分析影响因素,促进PSC实用化,减少研发成本,推动PSC技术落地,助力绿色能源转型。Efficient utilization of solar energy is the core of sustainable development, and improving the performance of solar cells is particularly crucial. Regarding the performance of perovskite solar cells (PSCs), this article uses statistics for feature extraction and machine learning to construct a structure performance model for rapid screening of efficient photovoltaic materials, providing a new approach for improving PSC performance. The regression prediction analysis of influencing factors would promote the practicality of PSC, reduce research and development costs, promote the implementation of PSC technology, and assist in the transformation of green energy.

关 键 词：机器学习 钙钛矿太阳能电池 性能提升 绿色能源转型 

分 类 号：TM9[电气工程—电力电子与电力传动]