摘要
以甘肃省瓜州县为例，利用1988~2007年的总需水量数据，采用主成分分析法对影响水资源需求量的7个因子进行主要影响因子分析，根据确定的主要影响因子构造BP神经网络的输入样本，从而进行不同水平的年总需水量预测。结果表明：国内生产总值、工业总产值、农业总产值和大牲口数4个因子为影响研究区需水量的主要因子，将此作为主要因子构造BP神经网络的输入样本，确定网络输入节点数，建立瓜州县总需水量预测模型。模拟计算结果表明，基于主成分分析的BP神经网络模型取，预测结果的绝对误差小于±0．05×10^9m3。
The principle component analysis is based on few extraneous variables that have controlled over all variables and can describe the correlativity among multiple variables. Taking the water demand data from 1988 to 2007 of Guazhou County of Gansu Province for example, this paper analyzes the main factors that influences the water resource quantity based on the principle component analysis method. According to these main factors, the input samples of BP neutral network are definite. Thereby, the BP neutral networks could be trained to predict. The results show that the gross domestic product （GDP）, total industrial output value, total output value of agriculture and animals population are the primary indexes that touch to the water resource demand. The corresponding prediction modeling outcome shows that the simulated experiment is quite fit for the practical situation and the absolute error of prediction is lower than ±0.05×10^9m3.
出处
《成都理工大学学报（自然科学版）》
CAS
CSCD
北大核心
2010年第2期206-210,共5页
Journal of Chengdu University of Technology: Science & Technology Edition
基金
国家科技支撑计划项目(2007BAD88B0804-3)
关键词
需水预测
主成分分析法
BP神经网络
water demand prediction
principle component analysis
BP neutral networks
