| 基于BP神经网络的迭代学习初始控制策略研究 |
| |
| 引用本文： | 郝晓弘,段晓燕,李恒杰.基于BP神经网络的迭代学习初始控制策略研究[J].计算机应用,2009,29(4):1025-1027. |
| |
| 作者姓名： | 郝晓弘 段晓燕 李恒杰 |
| |
| 作者单位： | 兰州理工大学 兰州理工大学 兰州理工大学电信学院 |
| |
| 基金项目： | 甘肃省自然科学基金，甘肃省国际合作项目 |
| |
| 摘 要： | 针对传统迭代学习控制(ILC)在面临新的环境或控制任务时学习时间长、收敛速度慢的问题，提出基于BP神经网络的迭代学习初始控制策略。通过BP神经网络拟和经验数据，对以往控制经验加以充分利用，避免了对初始控制输入量的盲目选择。仿真验证了方法的可行性和有效性。
|
| 关 键 词： | 迭代学习控制 BP神经网络 经验数据库 初始控制 |
| 收稿时间： | 2008-10-16 |
| 修稿时间： | 2008-12-08 |
Research of initial iterative learning control strategy based on BP neural network |
| |
| HAO Xiao-hong,DUAN Xiao-yan,LI Heng-jie.Research of initial iterative learning control strategy based on BP neural network[J].journal of Computer Applications,2009,29(4):1025-1027. |
| |
| Authors: | HAO Xiao-hong DUAN Xiao-yan LI Heng-jie |
| |
| Affiliation: | College of Electrical and Information Engineering;Lanzhou University of Technology;Lanzhou Gansu 730050;China |
| |
| Abstract: | In order to avoid the blend choice of the initial control input in Iterative Learning Control (ILC) when the control system faced a new desired trajectory-tracked task or a new environment, an improved algorithm was proposed to obtain the initial value of the iterative learning control based on Back Propagation (BP) neural network. Desired control input of iterative learning control was estimated by BP neural network incorporated experience database. The simulation results show that the algorithm is feasible and effective. |
| |
| Keywords: | Iterative Learning Control (ILC) Back Propagation (BP) neural network experience database initial control |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
