期刊文献+

DRNN在倒立摆摆起控制中的研究 被引量:1

Control for swing-up of inverted pendulum based on DRNN
在线阅读 下载PDF
导出
摘要 针对小车一级倒立摆的起摆控制,以DRNN神经网络作为辨识器,在线自适应调整PD控制器的两项参数。在起摆范围相同的情况下,DRNN神经网络控制的倒立摆系统其模型参数变化范围为-50%~30%,传统PD控制倒立摆系统其参数变化范围为-40%~20%。结果表明,基于DRNN神经网络的PD控制器比传统的PD控制器具有较强的抗干扰能力和自适应能力,系统鲁棒性增强,效果明显优于传统的PD控制器。 The swing-up control of an inverted pendulum,a Diagonal Recurrent Neural Network(DRNN) is built to identify the system and self-tuning the PD gains.At the same ranges of swing-up,the system parameters ranged from -50% to 30% for selftuning PD control based on DRNN,from -40% to 20% for conventional PD controller.The simulation results show that the system,compared with conventional PD controller,the presented control system has great anti-jamming,adaptability and robustness.
出处 《计算机工程与应用》 CSCD 北大核心 2009年第26期223-225,共3页 Computer Engineering and Applications
关键词 倒立摆 DRNN神经网络 PD控制 摆起 inverted pendulum diagonal recurrent neural network PD control swing-up
作者简介 谢慕君(1969-),女,副教授,博士后,主要从事智能控制理论研究; 杨海蓉(1982-),女,硕士研究生,主要从事智能控制理论研究。
  • 相关文献

参考文献4

二级参考文献17

  • 1王轶卿,赵英凯.基于Bang-Bang控制的倒立摆系统摆起和镇定[J].机械与电子,2004,22(8):16-18. 被引量:12
  • 2陶永华.新型PID控制及其应用[M].北京:机械工业出版社,2002..
  • 3Aldhiro Sakagneh, Toru Yamamoto. A Design of Predictive PID Control Systems Using GA and GMDH Network [A]. Proceedings of the 2002 IEEE International Conference on Control Applications.Sep.18-20, Glasgow Scotland UK. 2002, 266-271.
  • 4C W Anderson.Learning to control an inverted pendulum using neural networks[J].IEEE Control System Magazine,1989,9(3):31-37.
  • 5A G Barto,R S Sutton,C W Anderson.Neuronlike adaptive elements that can solve difficult learning control problems[J].IEEE Trans.on SMC,1983,13(5):834-846.
  • 6J Peng.Efficient dynamic programming-based learning for control[M].USA:Northeastern University,1993.
  • 7W Charles.Anderson.Q-learning with hidden-unit restarting[M].Advances in Neural Information Processing Systems 5,1992.81-88.
  • 8C J C H Watkins and P Dayan.Q-learning.Machine learning[J].May 1992,8(3/4):257-277.
  • 9K Doya.Reinforcement learning in continuous time and space[J].Neural Computation,1999,12:243-269.
  • 10Akira Ohsumi,Takeya Lzumikawa.Nonlinear Control of Swing-up and Stabilization of an Inverted-Pendulum[C].Proceedings of the 34th Conference on Decision and Control.New Orieans,LA,December 1995.3873-3880.

共引文献62

同被引文献6

引证文献1

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部