| 小波神经网络的改进及应用 |
| |
| 引用本文： | 单海欧,李平.小波神经网络的改进及应用[J].甘肃科学学报,2007,19(1):75-78. |
| |
| 作者姓名： | 单海欧 李平 |
| |
| 作者单位： | 辽宁石油化工大学,信息与控制工程学院,辽宁,抚顺,113001 |
| |
| 摘 要： | 提出一种带有动态补偿的双隐层小波神经网络,其中过程神经元隐层完成对输入信息过程模式提取和对时间的聚合运算,小波函数代替非时变一般神经元隐层函数,用于提高网络对系统输入输出之间复杂关系的映射能力,动态补偿用于提高建模精度.将其应用于管道泄漏故障的检测,收到良好的效果.
|
| 关 键 词： | 小波神经网络 双隐层 动态补偿 过程神经元 泄漏检测 |
| 文章编号： | 1004-0366（2007）01-0075-04 |
| 收稿时间： | 2005-11-22 |
| 修稿时间： | 2005年11月22 |
An Improved Wavelet Neural Netrwork and Its Application |
| |
| SHAN Hai-ou,LI Ping.An Improved Wavelet Neural Netrwork and Its Application[J].Journal of Gansu Sciences,2007,19(1):75-78. |
| |
| Authors: | SHAN Hai-ou LI Ping |
| |
| Institution: | School of Information and Control Engineering, Liaoning University of Petroleum and Chemical Technology, Fushun 113001, China |
| |
| Abstract: | A dynamically compensating class of wavelet neural network model with two hidden-layers is proposed. The process neuron is used to perform the aggregation operation of time; wavelet function is used to raise the mapping capability of network to the complex relation between the system input and output, and dynamical compensation is used to improve the modeling accuracy . The application to detect the leakage of pipelines is included to demonstrate the effectiveness of the new model. |
| |
| Keywords: | wavelet neural network two hidden-layers dynamicaly compensation process neuron leakage detection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
