| 基于信息熵加权的Elman神经网络状态趋势预测 |
| |
| 引用本文： | 陈涛,徐小力,王少红.基于信息熵加权的Elman神经网络状态趋势预测[J].北京机械工业学院学报,2011(6):26-29. |
| |
| 作者姓名： | 陈涛 徐小力 王少红 |
| |
| 作者单位： | [1]北京信息科技大学现代测控教育部重点实验室,北京100192 [2]北京理工大学机械与车辆学院,北京100081 |
| |
| 基金项目： | 国家自然科学基金项目（50975020）; 北京市属高等学校人才强教计划资助项目（PHR201106132）; 北京信息科技大学学校科研基金项目（1125048） |
| |
| 摘 要： | 为克服预测神经网络输入值对网络输出预测值贡献程度基本等同的缺陷,提出一种信息熵加权的神经网络智能预测方法。提出信息熵权值的计算方法和延时重构的加权前处理方法,并以Elman神经网络为基础,构建基于信息熵加权Elman神经网络的预测模型。烟气轮机状态趋势预测实例表明,基于信息熵加权Elman神经网络预测方法的预测效果较好,为状态趋势预测提供了一种新方法。
|
| 关 键 词： | 趋势预测 神经网络 信息熵加权 延迟重构 |
Condition trend prediction based on information entropy weighted Elman neural network |
| |
| CHEN Tao,XU Xiao-li,WANG Shao-hong.Condition trend prediction based on information entropy weighted Elman neural network[J].Journal of Beijing Institute of Machinery,2011(6):26-29. |
| |
| Authors: | CHEN Tao XU Xiao-li WANG Shao-hong |
| |
| Affiliation: | 1.Key Laboratory of Modern Measurement ＆ Control Technology,Ministry of Education,Beijing Information Science and Technology University,Beijing 10092,China;2.School of Mechanical and Vehicular Engineering, Beijing Institute of Technology,Beijing 100081,China) |
| |
| Abstract: | In order to overcome the deficiency of basically the same probability contribution of neural network input to output predicted,an intelligent prediction method is proposed based on information entropy weighted neural network.The information entropy weight calculation method and pre-treatment of delay reconstruction are provided,taking Elman neural network as the basis to construct prediction model of information entropy weighted Elman neural network.Condition trend prediction results of the flue gas turbine shows that the proposed new method has better prediction effect with higher prediction precision and real time performance. |
| |
| Keywords: | trend prediction neural network information entropy weighted delay reconstruction |
| 本文献已被 维普 等数据库收录！ |
