首页 | 本学科首页   官方微博 | 高级检索  
     

基于偏最小二乘回归与神经网络耦合的岩溶泉预报模型
引用本文:陈南祥,黄强,曹连海. 基于偏最小二乘回归与神经网络耦合的岩溶泉预报模型[J]. 水利学报, 2004, 35(9): 0068-0072
作者姓名:陈南祥  黄强  曹连海
作者单位:西安理工大学,水利水电学院,陕西,西安,710048;华北水利水电学院,岩土工程系,河南,郑州,450045;西安理工大学,水利水电学院,陕西,西安,710048;华北水利水电学院,岩土工程系,河南,郑州,450045
摘    要:本文将偏最小二乘回归与神经网络耦合,建立了泉流量预报模型。利用偏最小二乘法对影响岩溶泉流量的诸多因素进行分析,提取对因变量影响强的成分,从而克服了变量之间的多重相关性问题,降低了神经网络的输入维数。同时,利用神经网络建模可以较好地解决非线性问题。实例表明,本耦合模型的拟合和预报精度均优于独立使用偏最小二乘回归或神经网络建模的精度。

关 键 词:岩溶水系统  偏最小二乘回归  神经网络  预报模型
文章编号:0559-9350(2004)09-0068-05
修稿时间:2003-09-17

Model for prediction of karst spring flow based on the coupling of neural network model with partial least square method
CHEN Nan-xiang. Model for prediction of karst spring flow based on the coupling of neural network model with partial least square method[J]. Journal of Hydraulic Engineering, 2004, 35(9): 0068-0072
Authors:CHEN Nan-xiang
Affiliation:1. Xi'an University of Technology, Xi'an 710048, China; 2. North China Institute of Water Conservancy and Hydroelectric Power, Zhengzhou 450008, China
Abstract:A model for predicting karst spring flow based on the combination of neural network and partial least square method is proposed. The factors affecting the spring discharge are analyzed by means of partial least square method to extract the most important components so that not only the problem of multi-correlation among variables can be solves but also the amount of input dimensions of the neural network can be reduced. Besides, the application of neural network helps to solve the problem of non-linearity of the model. The application example shows that the proposed model has higher precision than those models based on neural network method or partial least square method only.
Keywords:karst water   partial least square method   neural network   prediction model
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《水利学报》浏览原始摘要信息
点击此处可从《水利学报》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