基于人工神经网络的湘江最大洪峰流量中、长期预报  

Medium-long-term prediction of annual maximum peak discharge at Xiangjiang river basin on artificial neural network

作　　者：胡国华[1] 宋荷花[1] 李正最[2] 

机构地区：[1]长沙理工大学水利河海工程学院,湖南长沙410076 [2]湖南省水文水资源勘测局水政处,湖南长沙410007

出　　处：《长沙交通学院学报》2008年第2期72-77,共6页Journal of Changsha Communications University

基　　金：湖南省自然科学基金资助项目(06JJ20027)

摘　　要：将统计相关性分析与模糊方法相结合,识别出影响湘江湘潭站年最大洪峰流量的前期流域降水、大气环流形势等预报因子,通过比较几种改进的BP网络的优缺点,探讨了BP网络建模过程中存在的几个问题,建立了LMBP算法和自适应BP算法相耦合的神经网络中、长期水文预报模型.预报结果表明:预报效果好、精度高,且具有较高的推广和应用价值.An artificial neural network medium and long-term hydrological forecasting model combining with LM algorithm and fuzzy method was established. Rainfall and atmospheric circulation in earlier stage which affect the annual maximum peak discharge at the Xiangtan station of Xiangjiang river were chosen, the advantage and disadvantage of several modified BP algorithms are given, several problems in modeling process were discussed. The result shows that this model is highly effective and is useful for applications.

关 键 词：LMBP算法 自适应BP算法 湘江 年最大洪峰流量 中 长期预报 

分 类 号：TV213[水利工程—水文学及水资源]