期刊文献+

带有干扰观测器的PID-CMAC控制系统设计 被引量:3

Disturbance Observer Design Based on PID-CMAC Control System
下载PDF
导出
摘要 PID神经网络有很强的拟合能力,它用于基于神经网络逆模型的干扰观测器设计,并进一步设计了带一种带有干扰观测器的PID-CMAC复合控制系统。该系统解决了内扰无法观测的问题,通过设置干扰观测器加快了消除内扰的过程,CMAC的控制作用使系统输出能够更快地跟踪系统输入。实验表明,该控制系统不仅能够提高系统输出跟踪系统输出的能力,而且能够更快地消除内扰。 A disturbance observer was designed based on PID neural networks' inverse model. The disturbance observer was used to construct a complex PID-CMAC control strategy. Then PID neural network was used to solve the problems that mathematical models and inverse models were difficult to get when constructing disturbance observer. PID-CMAC control strategy designed is more robust than normal PID control strategy. Simulation result shows the disturbance observer applying in PID-CMAC control system can increase system's robust and can reduce the disturbances' influence on system's output effectively.
出处 《系统仿真学报》 EI CAS CSCD 北大核心 2007年第22期5226-5229,5233,共5页 Journal of System Simulation
关键词 干扰观测器 PID神经网络 逆模型 CMAC disturbance observer PID neural network inverse model CMAC
  • 相关文献

参考文献14

  • 1舒怀林.基于PID神经网络的非线性时变系统辨识[J].自动化学报,2002,28(3):474-476. 被引量:23
  • 2S E Fahlman. Faster-leraning Variations on Back-propagation: An Empirical Study [C]//Proccedings of the 1988 Connectionist Models Summer School, 38-51, San Mateo, CA, 1988. Carnegie Mellon University: Morgan Kaufmann, 1988.
  • 3J Moody, C Darken. Fast Learning in Networks of Locally Tuned Processing Units [J]. Neural Computation (S0889-7667), 1989, 1(2): 281-294.
  • 4Elman J L. Finding Structure in Time [J]. Cognitive Science (S0364-0213), 1990, 14(2): 179-211.
  • 5焦嵩鸣,韩璞,周黎辉.一种新型的动态递归神经网络及其算法[J].计算机仿真,2002,19(5):64-66. 被引量:6
  • 6Kreinovich V, Quintana C. Genetic Algorithms: What Fitness Scaling is Optimal [J]. Cybernetics and Systems (S0196-9722), 1993, 24(1): 9-36.
  • 7Martin Riedmiller, Heinrich Braun. A Direct Adaptive Method for Faster Back-propagation Learning: The RPROP Algorithm [C]// Proceedings of the IEEE International Conference on Neural Networks (ICNN). San Francisco: IEEE, 1993: 586-591.
  • 8JIAO song-ruing, HAN pu, ZHOU li-hui, LI jian-bo. Recurrent Neural Network Applied in Dynamitic Process Identification Based on RPROP and Chaos Optimization Coupling Algorithm[C]// Proceedings of 2004 International Conference on Machine Learning and Cybernetics. Shanghai: IEEE, 2004. V6: 3339-3343.
  • 9任子武,伞冶,陈俊风.改进PSO算法及在PID参数整定中应用研究[J].系统仿真学报,2006,18(10):2870-2873. 被引量:42
  • 10韩江洪,李正荣,魏振春.一种自适应粒子群优化算法及其仿真研究[J].系统仿真学报,2006,18(10):2969-2971. 被引量:122

二级参考文献55

共引文献218

同被引文献25

引证文献3

二级引证文献7

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