|
|||||
|
|
| 偏最小二乘回归神经网络的矿坑涌水量预测 | |
| 引用本文： | 陈南祥,曹连海,李梅,黄强.偏最小二乘回归神经网络的矿坑涌水量预测[J].吉林大学学报(地球科学版),2005,35(6):766-770. |
| 作者姓名： | 陈南祥 曹连海 李梅 黄强 |
| 作者单位： | 1. 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,450008 2. 华北水利水电学院,岩土工程系,河南,郑州,450008 3. 西安理工大学,水利水电学院,陕西,西安,710048 |
| 摘 要： | 影响矿坑充水的因素多且复杂,矿坑涌水量预测模型主要考虑降水、地表水、引水灌溉等影响因素,因变量和自变量的关系比较复杂.将偏最小二乘回归与神经网络耦合,建立了矿坑涌水预报模型.模型将自变量利用偏最小二乘回归处理,提取对因变量影响强的成分,既可以克服变量之间的相关性问题,又可以降低神经网络的输入维数,并能较好地解决非线性问题,提高了模型的学习能力和表达能力.以河南鹤壁八矿涌水量为例,建立了基于偏最小二乘回归和神经网络耦合的矿坑涌水量预测模型.计算验证表明,该类模型具有较高的预报精度和推广应用价值. |
| 关 键 词： | 矿坑涌水量 偏最小二乘回归 神经网络 预报模型 最小 回归神经网络 矿坑涌水 涌水量预测 Neural Network Method Partial Water Yield of Mine 价值 应用 预报精度 计算验证 鹤壁 河南 表达能力 学习 线性问题 维数 输入 相关性问题 |
| 文章编号： | 1671-5888(2005)06-0766-05 |
| 收稿时间： | 2005-01-28 |
| 修稿时间： | 2005年1月28日 |
Forecasting Water Yield of Mine with the Partial Least-Square Method and Neural Network |
|
| CHEN Nan-xiang,CAO Lian-hai,LI Mei,HUANG Qiang.Forecasting Water Yield of Mine with the Partial Least-Square Method and Neural Network[J].Journal of Jilin Unviersity:Earth Science Edition,2005,35(6):766-770. | |
| Authors: | CHEN Nan-xiang CAO Lian-hai LI Mei HUANG Qiang |
| Abstract: | There are many and complex factors affecting the gushing water in pit. The forecasting model of water yield of mine mostly takes into account of precipitation, surface water, irrigation and the relation of following variable and independent variable. The authors establish the forecasting model for water yield of mine, combining neural network model with the partial least square method. To deal with independent variables by the partial least square method can not only solve the relationship between in- dependent variables but also to reduce the input dimensions in neural network model. And when the neural network is applied,it can solve the non-linear problem better,and advance study and expression ability of the model. As the example of water yield of mine in Eighth mine, Hebi City, Henan Province, the model of water yield of mine,coupled with partial least square method and neural network, is founded and the case study shows it has rather high forecasting precision and the extending application value. |
| Keywords: | water yield of mine partial least square method neural network forecasting model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |