|
|||||
|
|
| 基于神经网络的灌溉用水量预测 | |
| 引用本文： | 郑玉胜,黄介生. 基于神经网络的灌溉用水量预测[J]. 灌溉排水学报, 2004, 23(2): 59-61 |
| 作者姓名： | 郑玉胜 黄介生 |
| 作者单位： | 武汉大学,水利水电学院,湖北,武汉,430072;武汉大学,水利水电学院,湖北,武汉,430072 |
| 摘 要： | 采用改进的BP网络对灌溉用水量进行了预测,针对BP网络的不足,采用遗传算法对网络初始权重进行了优化,并采用LM(Levenberg-Marquardt)算法进行了误差逆传播校正。通过引入遗传算法和LM算法,网络比传统的BP网络无论从精度和训练时间上都有了较大的改进。最后对湖北省宜昌市东风渠灌区进行实例分析,证明了该方法的有效性。 |
| 关 键 词： | BP网络 LM算法 遗传算法 灌溉用水量 预测 |
| 文章编号： | 1000-646X(2004)02-0059-03 |
| 修稿时间： | 2004-03-01 |
Forecast of Irrigation Water Use Based on Neural Network |
|
| ZHENG Yu-sheng,HUANG Jie-sheng. Forecast of Irrigation Water Use Based on Neural Network[J]. Journal of Irrigation and Drainage, 2004, 23(2): 59-61 | |
| Authors: | ZHENG Yu-sheng HUANG Jie-sheng |
| Abstract: | Forecast of irrigation water use based on neural network was studied. Genetic algorithm was used to optimize the initial weight and Levenberg-Marquardt (LM) algorithm was used to reduce the error. Case study was conducted for Dongfengqu Irrigation District in Hubei Province and the availability of the forecast method has been approved. |
| Keywords: | BP neural network LM algorithm genetic algorithm irrigation water use forecast. |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |