| BP神经网络的LM算法及其对颗粒碰撞振动阻尼的预测 |
| |
| 引用本文： | 李来强,王树林,赵兵涛. BP神经网络的LM算法及其对颗粒碰撞振动阻尼的预测[J]. 上海理工大学学报, 2006, 28(4): 331-333 |
| |
| 作者姓名： | 李来强 王树林 赵兵涛 |
| |
| 作者单位： | 上海理工大学,动力工程学院,上海,200093;上海理工大学,动力工程学院,上海,200093;上海理工大学,动力工程学院,上海,200093 |
| |
| 基金项目： | 国家自然科学基金资助项目(50375100) |
| |
| 摘 要： | 介绍了一种BP神经网络的改进Levenberg Marquardt(LM)算法原理,用这种方法对颗粒碰撞振动系统的阻尼进行了训练和仿真,并将此改进算法与传统算法进行比较.结果表明,该算法稳定、快捷,预测准确,适合应用于对实时性要求比较高的场合,且预测得到的模型与相关文献中的结果一致.
|
| 关 键 词： | 神经网络 Levenberg-Marquardt算法 颗粒碰撞振动阻尼 |
| 文章编号： | 1007-6735（2006）04-0331-03 |
| 收稿时间： | 2005-07-02 |
| 修稿时间： | 2005-07-02 |
Improved Levenberg-Marquardt algorithm for BP neural network and its application in predicting the particle impact damping |
| |
| LI Lai-qiang,WANG Shu-lin,ZHAO Bing-tao. Improved Levenberg-Marquardt algorithm for BP neural network and its application in predicting the particle impact damping[J]. Journal of University of Shanghai For Science and Technology, 2006, 28(4): 331-333 |
| |
| Authors: | LI Lai-qiang WANG Shu-lin ZHAO Bing-tao |
| |
| Affiliation: | College of Power Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China |
| |
| Abstract: | Using an improved LevenbergMarquardt algorithm and based on the experimental data,the BP neural network is trained to study and simulate the damping performance of the particle impact vibration system,and the results are compared with those from conventional calculation methods.It is demonstrated that the LevenbergMarquardt algorithm can greatly speed up the learning process and therefore reduce the training time,and is suitable for real time system identification.The recognized models agree qualitatively well with those in the literatures. |
| |
| Keywords: | neural network Levenberg-Marquardt algorithm particle impact damping |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《上海理工大学学报》浏览原始摘要信息 |
|
点击此处可从《上海理工大学学报》下载全文 |
|
