基于多元回归分析的大伙房水库径流中长期预报  

Mid-long Term Runoff Forecasting Model for Dahuofang Reservoir Based on Multiple Regression Analysis

作　　者：王琪[1] 张亭亭[1] 游海林[1] 常静[1] 曹永强[1] 

机构地区：[1]辽宁师范大学城市与环境学院,辽宁大连116029

出　　处：《水力发电》2014年第5期17-20,共4页Water Power

摘　　要：以大伙房水库1956年~2000年10项年径流影响指标的统计数据为资料，基于主成分分析和Logtic方程多元回归方法，建立了大伙房水库径流中长期预报模型，并以2001年。200争年实测径流资料进行外推预报检验。研究结果表明，模型具有较高的拟合精度，预报效果较好，可以用来初步预测大伙房水库2000年之后的径流量，从而为水资源规划与管理部门指导实际生产提供参考依据。Ten factors which affecting annual runoff are selected from the statistical data of Dahuofang Reservoir from 1956 to 2000, and then the mid-long term runoff forecasting model is established based on these factors by using principal component analysis and muhiple regression analysis of Logistic equation. The model is also used to conduct a extraploting prediction test by using the measured runoff data from 2001 to 2005. The results show that the mid-long term runoff forecasting model has higher fitting.accuracy and good forecast effect, which can be used to make a primary prediction on the runoff of Dahuofang Reservoir after 2000.

关 键 词：径流中长期预报 多元回归分析 主成分分析 LOGISTIC方程 大伙房水库 

分 类 号：P338.2[天文地球—水文科学]