| 基于遗传神经网络的机械振动信号预测 |
| |
| 引用本文： | 薛小兰,温秀兰,张鹏.基于遗传神经网络的机械振动信号预测[J].弹箭与制导学报,2007,27(3):239-240,246. |
| |
| 作者姓名： | 薛小兰 温秀兰 张鹏 |
| |
| 作者单位： | 1. 内蒙古工业大学机械学院,呼和浩特,010051
2. 内蒙古工业大学机械学院,呼和浩特,010051;中北大学信息与通信学院,太原,030051 |
| |
| 基金项目： | 内蒙古工业大学重点研究项目（ZD200508）资助 |
| |
| 摘 要： | 针对传统的BP神经网络学习算法存在易陷入局部极小及收敛速度慢等缺陷,文中提出了利用实数编码改进遗传算法对神经网络进行优化训练,并把训练好的神经网络用于对机械振动信号的预测, 并与传统BP算法以及改进BP算法预测结果进行比较,充分证实了文中方法的有效性.
|
| 关 键 词： | 遗传算法 实数编码 神经网络 机械振动 |
| 收稿时间： | 2006-08-25 |
| 修稿时间： | 2006-08-252006-11-03 |
Prediction of Mechanical Vibration Signals Based on Genetic Algorithms and Neural Network |
| |
| XUE Xiao-lan,WEN Xiu-lan,ZHANG Peng.Prediction of Mechanical Vibration Signals Based on Genetic Algorithms and Neural Network[J].Journal of Projectiles Rockets Missiles and Guidance,2007,27(3):239-240,246. |
| |
| Authors: | XUE Xiao-lan WEN Xiu-lan ZHANG Peng |
| |
| Affiliation: | 1 Department of Mechanical. Inner Mongolia University of Technology, Hohhot 010051. China 2 School of Information and Communication, North University of China, Taiyuan 030051. China |
| |
| Abstract: | In this paper, an improved genetic algorithm based on real-coded is proposed to train neural network, which overcomes the drawbacks of slow convergence rate and easily falling into local minimums in traditional 15P neural network. Then. the trained neural network was used to predict mechanical vibration signals. Compared with the prediction result of traditional BP and the improved BP, it is proved that the proposed algorithm is effective. |
| |
| Keywords: | genetic algorithms real-coded neural network mechanical vibrations |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
