基于BP神经网络单硅太阳电池模型参数的解析研究  

ANALYTICAL STUDY ON THE PARAMETERS OF SINGLE SILICON SOLAR CELL MODEL BASED ON BP NEURAL NETWORK

作　　者：胡海燕[1] 胡克满[1,2] 王民权[1] 

机构地区：[1]宁波职业技术学院,浙江宁波315800 [2]宁波华索光伏设备有限公司,浙江宁波315000

出　　处：《计算机应用与软件》2014年第3期55-58,共4页Computer Applications and Software

基　　金：浙江省教育厅科研计划项目(Y201226216);2012年浙江省教育厅高等学校访问工程师校企合作项目:2012年宁波职业技术学院科研项目

摘　　要：利用BP神经网络对单硅太阳电池数学模型进行求解。通过对I-V方程的推导和化简,结合测试得到的开路电压、短路电流、最大功率电压、最大功率电流等数据提出一种通过BP神经网络的训练得到太阳电池串联内阻、反向饱和电流、并联电流、二极管因子和光生电电流等五个重要参数值的计算方法。并分别对单硅太阳电池在标准条件下、弱光照射和强光照射不同的环境下进行测试。把实测数据和计算仿真值进行对比,结果证明该方法具有较好的计算精度。BP neural network is applied to solve the mathematical model of single silicon solar ceils. Through the deduction and simplifica- tion of I-V equation, and combining the tested data of open circuit voltage, short circuit current, the maximum power voltage, the maximum power current, etc. , we put forward a calculation method, it obtains five important parameter values including the series resistance of solar cells, the reverse saturation current, the parallel current, the diode factor and the photocurrent by the training of BP neural network. The sin- gle solar cell is tested under different environment such as standard conditions, weak light and strong light separately. The method is proved to have better calculation accuracy by comparing the measured data with the calculated simulation result.

关 键 词：BP神经网络 太阳电池 模型 参数 

分 类 号：TM914.4[电气工程—电力电子与电力传动] TP3[自动化与计算机技术—计算机科学与技术]