摘要
太阳辐射是一项对太阳能利用,建筑能耗分析和农业等十分重要的气象数据,本文建立了日总太阳辐 射月均值的神经网络估算模型,在此基础上利用北京市1971年至1995年的气象数据资料对神经网络进行了训 练,用1996至2000年的数据对神经网络的估算进行了检验,并与其它经验模型的估算结果进行了对比,结果表 明神经网络的估算结果与实测值吻合的较好,并且精度高于其它经验模型。因此利用神经网络来估算太阳辐射 具有很好的应用前景。
Solar radiation is one of the most vital meteorological factors as far as solar energy conversion, analysis of building energy consumption and agriculture etc. are concerned. A model based on Artificial Neural Network (ANN) was applied for estimation of monthly mean daily value of solar global radiation. The solar radiation data from 1971 to 1995 of Beijing were used for training the neural networks and data from 1996 to 2000 were used for testing estimated values. The results obtained from the ANN model have been compared with other empirical models. The estimations by ANN model are in good agreement with the actual values and are superior to those of other available models. Results indicate that the ANN model shows promise for evaluating solar global radiation possibilities.
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2005年第4期509-512,共4页
Acta Energiae Solaris Sinica
基金
西安交通大学博士学位论文基金(DFXXJTU2002-10)
关键词
太阳辐射
神经网络
BP算法
solar global radiation
artificial neural networks
back-propagation algorithm