摘要
本文研究提出基于LM_BP神经网络的月总辐射量计算模型,通过对月总辐射量与其若干气象因子的相关分析,筛选确定月天文总辐射量、月日照时数等5个气象因子作为模型的输入向量,利用澳门气象站实测气象数据进行模型训练及验证。研究结果表明,该模型可以较好地反映出月总辐射量与其影响因子之间复杂的非线性关系,与传统计算模型相比,本文模型计算结果更为精确可靠。
In this paper,a model for monthly global radiation calculation based on the LM_BP neural networkwas put forward.Some meteorogical factors were have the correlation test with global radiation.Based on theresult,the paper took the five meteorological factors as the input vector,which included monthly extraterrestrialsolar radiation.And the output vector was the monthly global radiation.A test was carried on the model by using the meteorological data measured by weather station.The result of the test showed that the model had goodgeneralization ability.The data calculated by the model was more accurate than the traditional model.
作者
朱良山
Zhu Liangshan(Guohua Energy Investment Co.,Ltd,Beijing,100011)
出处
《神华科技》
2017年第8期58-62,共5页
Shenhua Science and Technology
作者简介
朱良山（1986-），男，工程师，2009年毕业于武汉大学，现任职于神华国华能源投资有限公司规划发展部。Tel：18001207907，E-mail：zhuliangshan123@163.com
