径流中长期预报模糊识别优化模型及应用  

Fuzzy Recognition Optimization Model for Mid and Long Term Runoff Forecasting

作　　者：李希灿[1,2] 王静[2] 赵庚星[3] 

机构地区：[1]山东农业大学信息科学与工程学院,山东泰安271018 [2]国土资源部土地利用重点实验室,北京100035 [3]山东农业大学资源与环境学院,山东泰安271018

出　　处：《数学的实践与认识》2010年第6期92-98,共7页Mathematics in Practice and Theory

基　　金：国家科技支撑计划项目(2006BAJ05A08;2006BAB15B04)

摘　　要：对水文中长期预报模糊识别方法进一步研究,基于模糊环境下的目标函数,提出了具有主观监督因子和稳定系数的模糊识别预报模型.根据已知样本的最优模糊划分建立预报模型,利用已知样本的指标和样本的最优模糊划分计算预报模型的参数,给定模型的稳定系数,再通过调整主观监督因子对预报模型参数进行优化.径流中长期预报实例的模型检验平均相对误差为7.84%.The paper has further studied the algorithm of fuzzy recognition for mid and long term runoff forecasting,based on the new fuzzy objective function with subjective supervision factor and stability coefficient,the fuzzy recognition model for mid and long term runoff forecasting is presented.The optimization principle is that forecasting model was built according to known samples＇ best fuzzy classification,and the forecasting model＇s parameters are determined by using samples＇ index and best fuzzy classification,and the forecasting model＇s parameter are optimized through adjusting subjective supervision factor at given stability coefficient. The method presented in this paper is applied to runoff forecasting,the predicted result＇s mean relative error is 7.84%.

关 键 词：径流预报 模糊识别 预报参数 主观监督因子 稳定系数 

分 类 号：TV124[水利工程—水文学及水资源]