一种基于MEA-BP的太阳辐射反演算法  

Solar Radiation Inversion Algorithm Based on MEA-BP

作　　者：郑丹[1] 马尚昌[1,2] 张素娟[1,2] Zheng Dan;Ma Shangchang;Zhang Sujuan(College of Electronic Engineering,Chengdu University of Information Technology,Chengdu 610225;Key Laboratory of Atmospheric Sounding of China Meteorological Administration,Chengdu 610225)

机构地区：[1]成都信息工程大学电子工程学院,成都610225 [2]中国气象局大气探测重点开放实验室,成都610225

出　　处：《气象科技》2018年第5期860-867,共8页Meteorological Science and Technology

基　　金：四川省科技厅科技支撑项目"2015GZ0278"资助

摘　　要：基于光电原理的日照计即将在全国推广应用,以光照度观测数据为主反演太阳辐射数据可以有效弥补太阳辐射观测站数量不足的现状。针对现有的太阳辐射反演方法的不足,提出一种融合主成分分析(PCA)、思维进化算法(MEA)和BP神经网络的复合模型,利用太阳光照度、太阳高度角、温度和湿度观测分钟数据反演太阳辐照度。首先,以晴空指数为依据,基于概率神经网络(PNN)分类法,将天气类型分为晴、云、阴3类,分类准确率达到96.6948%。再利用PCA降维后的4个影响因子,对3类天气分别采用BP、GA-BP和MEA-BP法反演太阳辐照度,与标准辐射表的实测数据对比。结果表明:晴、云、阴的MEA-BP模型的决定系数最高达到0.9958,与单一BP模型相比,RMSE分别降低了49%、32.45%和10.64%;相比于GA-BP模型误差,MAPE最高减少了42.54%。本文所提出的MEA-BP复合模型的泛化能力得到了有效提高。The sunlight meter based on the photoelectric principle will be soon popularized and applied in the whole country.The inversion of solar radiation data based on the observation data of light intensity can effectively make up for the insufficient number of solar radiation observation stations.Aiming at the shortcomings of the existing solar radiation estimation methods,a composite model combining with the Principal Component Analysis（PCA）,the Mind Evolutionary Algorithm（MEA）and the BP neural network is proposed,using the observation minutes data of solar intensity,solar altitude angle,temperature,and humidity to invert the solar irradiance.Based on the clearness index and the probabilistic neural network（PNN）classification method,the weather types are divided into three categories：sunny,cloudy,and overcast.The classification accuracy is 96.6948%.Then using the four influencing factors after PCA dimensionality reduction,the solar irradiance is obtained by the BP,GA-BP and MEA-BP methods for the three types of weather,and compared with the measured data of the standard radiation meters.The results show that the determination coefficient of the MEA-BP model is up to 0.9958 in sunny,cloudy and overcast weather.Compared with the single BP model,RMSE decreases by 49%,32.45% and 10.64%,respectively.Compared with the GA-BP Model error, MAPE decreases by42.54%.The generalization capability of the MEA-BP composite model proposed in this paper has been effectively improved.

关 键 词：太阳辐射 晴空指数 PNN PCA MEA-BP 误差分析 

分 类 号：P412.14[天文地球—大气科学及气象学]