设为首页 联系我们 加入收藏

当前位置: 网站首页 期刊分类目录 2011第1期 正文

基于启发式学习算法的空间柔性机械臂神经网络控制

作者:时间:2014-11-21点击数:

PDF全文下载: 2011010085

齐乃明1,  张文辉1*,  马静2,  高九州1

(1. 哈尔滨工业大学 航天学院,黑龙江 哈尔滨 150001;2. 东北农业大学 工程学院,黑龙江 哈尔滨 150001)

摘要:  针对非线性强耦合的空间漂浮基柔性机器人,提出了一种启发式学习算法的神经网络的前馈控制策略。首先通过拉格朗日法和假设模态方法建立了漂浮基柔性空间机器人的动力学模型,然后采用两个神经网络及一个PID控制器来构建前馈在线学习控制系统,其中一个神经网络充当前馈控制器,另一个神经网络通过学习逆动态模型来为前馈控制器提供在线学习参数,而PID控制器主要作为辅助补偿控制器。该控制策略不是在PID控制器的指导下进行学习,且无需预先的离线学习,因而学习精度更高,且减少了对学习样本选择不当的影响,采用固定中心参数,而扩展宽度采用启发式关系确定,网络权值采用改进的最优准则算法进行调整的算法来实现快速学习能力,具有较好的实时性。仿真结果证明了所提方案的有效性。

关键词: RBF神经网络;  柔性空间机器人;  启发式学习;  PID控制

中图分类号:  TP 242                     文献标志码:  A

Heuristic Learning Algorithm of Neural Network Control for Space Flexible Manipulators

QI Nai-ming1,ZHANG Wen-hui1,MA Jing2,GAO Jiu-zhou1

 (1.Harbin Institute of Technology,School of Aerospace,Harbin 150001, China;2.Northeast Agriculture University,College of Engineering,Harbin 150001, China)

Abstract: According to nonlinear strong coupling of free-floating space robot with flexible manipulators, a neural network feedforward control scheme based on heuristic learning algorithm is proposed. Firstly, the dynamics of free-floating space flexible robot is established by the Lagrange and assumed modes methods. And then two neural network controllers and one PID controller are used to construct feedforward on-line learing control system. One neural network controller is used as a feedforward controller, and the other is applied to study inverse-model of the robot and provide on-line learning parameters for the feedforward controller. The PID controller is an assistant controller. The propsed control strategy can improve the control accuracy and the asymptotic convergence of tracking error, without the help of  PID and off-line learning. The neural network parameters can adjust adaptively by adopting the heuristic learning algorithm. The learning speed of the neural network is enhanced greatly and has better real time property. Finally, The simulation results have shown that the presented strategy is effective.

Key words: RBF neural network;flexible space robot;heuristic learning;PID control

收稿日期:2010-09-03

基金项目: 中国航天科技集团创新基金资助项目(CAST09C01).

作者简介: 齐乃明(1962—),男,教授.             *通信联系人.

Copyright © 2011-2017 青岛科技大学学报 (自然科学版)