• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2020, Vol. 42 ›› Issue (08): 1423-1429.

• 图形与图像 • 上一篇    下一篇

基于LM_RBF-PID的板球系统轨迹控制

黄文杰,向凤红,毛剑琳   

  1. (昆明理工大学信息工程与自动化学院,云南 昆明 650500)
  • 收稿日期:2019-10-21 修回日期:2020-02-07 接受日期:2020-08-25 出版日期:2020-08-25 发布日期:2020-08-29
  • 基金资助:
    国家自然科学基金(61163051);云南省教育厅科学研究基金(2015Y071)

Trajectory control of ball and plate system based on LM_RBF-PID

HUANG Wen-jie,XIANG Feng-hong,MAO Jian-lin   

  1. (Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

  • Received:2019-10-21 Revised:2020-02-07 Accepted:2020-08-25 Online:2020-08-25 Published:2020-08-29

摘要: 板球系统是一个典型的两输入两输出系统。针对RBF-PID控制算法存在响应速度慢、震荡严重等问题,在忽略干扰因素的条件下应用拉格朗日方程对板球系统进行数学建模,利用RBF神经网络在线辨识板球系统的离散模型,实现自适应控制。在此基础上用LM算法代替梯度下降法整定控制参数,设计出LM_RBF-PID控制器并与RBF-PID控制器进行阶跃信号响应和方波信号响应对比,最后在板球系统中完成方形轨迹跟踪实验。实验结果表明,所提控制算法提高了轨迹跟踪控制精度,能够确保板球系统跟踪控制良好的稳定性和收敛性。


关键词: 板球系统, Levenberg-Marquardt算法, 神经网络, Matlab

Abstract: Ball and plate system is a typical two-input two-output system. Aiming at the problems of slow response and serious shocks in RBF-PID control algorithm. The Lagrange equation is used to model the ball and plate system under the condition of ignoring the interference factors. Radical Basis Function (RBF) neural network is used to identify the discrete model of ball and plate system on line and realize adaptive control. On this basis, the Levenberg-Marquardt (LM) algorithm replaces the gradient descent method to set the control parameters. The LM_RBF-PID controller is designed and compared with the RBF-PID controller in terms of step signal response and square wave signal response. Finally, a square trajectory tracking experiment is completed in the ball and plate system. The experimental results show that proposed algorithm improves trajectory tracking control accuracy, and it can ensure the stability and convergence of the tracking control in the ball and plate system.

Key words: ball and plate system, Levenberg-Marquardt algorithm, neural network, Matlab