| 一种改进的递归神经网络及其仿真研究 |
| |
| 引用本文： | 唐富华,郭银景,杨阳,康景利. 一种改进的递归神经网络及其仿真研究[J]. 北京理工大学学报, 2005, 25(5): 399-401 |
| |
| 作者姓名： | 唐富华 郭银景 杨阳 康景利 |
| |
| 作者单位： | 北京理工大学,机电工程学院,北京,100081;山东科技大学,信息与电气工程学院,山东,青岛,266510 |
| |
| 摘 要： | 针对BP神经网络在学习速度方面的不足,在Jordan和Elman网络结构的基础上,提出了一种带偏差单元的IRN(internally recurrent network)网络模型,根据BP算法推导出了该网络模型的权系数调整规则,并应用该网络模型进行了故障诊断方面的仿真分析.试验结果表明,该网络模型的收敛速度比一般BP网络有了很大提高,具有很好的实用性.
|
| 关 键 词： | BP神经网络 递归神经网络 故障诊断 系统仿真 |
| 文章编号： | 1001-0645(2005)05-0399-03 |
| 收稿时间： | 2004-06-28 |
| 修稿时间： | 2004-06-28 |
An Improved Recurrent Neural Network and Its Simulation |
| |
| TANG Fu-hu,GUO Yin-jing,YANG Yang and KANG Jing-li. An Improved Recurrent Neural Network and Its Simulation[J]. Journal of Beijing Institute of Technology(Natural Science Edition), 2005, 25(5): 399-401 |
| |
| Authors: | TANG Fu-hu GUO Yin-jing YANG Yang KANG Jing-li |
| |
| Affiliation: | School of Mechatronics Engineering, Beijing Institute of Technology, Beijing 100081, China;College of Information and Electronic Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266510, China;School of Mechatronics Engineering, Beijing Institute of Technology, Beijing 100081, China;School of Mechatronics Engineering, Beijing Institute of Technology, Beijing 100081, China |
| |
| Abstract: | To deal with the weakness of the BP neural network in learning speed, an internally recurrent network model with bias cells is presented based on the Jordan and Elman neural networks. The weight-regulating method is developed based on BP algorithm. Simulations on fault diagnosis are performed with this neural network model. Experimental results show that the converging speed of this network model is faster than the traditional BP network and this model has a good practicability. |
| |
| Keywords: | BP neural network recurrent neural network fault diagnosis system simulation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京理工大学学报》浏览原始摘要信息 |
|
点击此处可从《北京理工大学学报》下载全文 |
|
