首页 | 官方网站   微博 | 高级检索  
     

梯级-关联算法原理及其在月流量预报中的应用
引用本文:张志果,徐宗学,巩同梁.梯级-关联算法原理及其在月流量预报中的应用[J].水科学进展,2007,18(1):114-117.
作者姓名:张志果  徐宗学  巩同梁
作者单位:1.北京师范大学水科学研究院, 水沙科学教育部重点实验室, 北京, 100875;
基金项目:国家科技攻关项目;北京师范大学校科研和教改项目
摘    要:传统BP网络需要预先设定网络隐含层的层数和每层的节点数,使得在预测过程中难以确定网络的最优结构。与之相反,梯级-关联算法(CC)要求初始网络仅含有输入层和输出层,通过运算不断向网络增加隐含节点。在介绍梯级-关联算法原理的基础上,分别运用梯级-关联算法和BP算法对拉萨河拉萨站的月流量进行了预测,结果显示:在不损失预测精度的前提下,梯级-关联算法的运算次数仅为5次,而BP算法则需要运算70 000次,运算效率有很大的提高,同时网络的规模也有所减小。

关 键 词:梯级-关联算法    BP算法    流量预报    拉萨河
文章编号:1001-6791(2007)01-0114-04
收稿时间:2005-08-01
修稿时间:2005-11-29

Cascade-correlation algorithm and its application in monthly streamflow forecasting
ZHANG Zhi-guo,XU Zong-xue,GONG Tong-liang.Cascade-correlation algorithm and its application in monthly streamflow forecasting[J].Advances in Water Science,2007,18(1):114-117.
Authors:ZHANG Zhi-guo  XU Zong-xue  GONG Tong-liang
Affiliation:1.College of Water Sciences, Beijing Normal University, Key Laboratory of Water and Sediment Sciences, Ministry of Education, Beijing 100875, China;2.Surveying Bureau of Hydrology and Water Resources, Tibet Autonomous Region, Lasa 850000, China
Abstract:The size and structure of neutral networks must be predefined if the standard backpropagation neural network architecture is used for training.On the contrary,the initial network of cascade-correlation(CC) is composed of the input layer and output layer while the hidden unit is inserted into the network one by one.The principle of CC is presented in this paper,and the monthly streamflow in the Lasa river is forecasted by using the CC and the BP models.The result shows that the CC model only needs to run five times while the BP model needs 70000 times to reach the same precision.The efficiency of the CC model is much higher than that of the BP model. Another conclusion is that the network size of a CC model is smaller than that of the BP model.
Keywords:cascade-correlation algorithm  backpropagation algorithm  streamflow forecasting  Lasa River
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《水科学进展》浏览原始摘要信息
点击此处可从《水科学进展》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号