摘要
文章针对网络控制系统(NCS)存在的网络延时问题,设计了一种基于RBF神经网络的分数阶PID控制器,并将该控制器应用在网络控制系统中,减小网络延时对控制系统的影响。该控制器利用RBF神经网络具有任意精度逼近非线性函数及训练速度快的优点,在线整定分数阶PID控制器,并采用分数阶PID控制器直接控制被控对象;选取Ethernet控制的弹簧-阻尼控制系统作为实验对象。实验结果表明:该控制系统具有响应速度快、控制精度高、鲁棒性强的特点,有效地减少了网络延时对NCS的影响。
For the network latency problem existing in the Networked Control System（NCS）, a fractional order PID controller based on radial basis function（RBF） neural network is designed and applied to the NCS to reduce the impact of network latency on the control system. Taking the advantages of the RBF neural network sUch as arbitrary precision approximation of nonlinear function and high training speed, the fractional order PID controller is online tuned and applied to directly controlling the controlled object. The Ethetnet control spring-damping control system is selected as the experimental object and the experimental results show that the control system possesses fast response, high control accuracy and robustness, and can effectively reduce the impact of network latency on the NCS.
出处
《合肥工业大学学报（自然科学版）》
CAS
CSCD
北大核心
2015年第2期171-174,共4页
Journal of Hefei University of Technology：Natural Science
关键词
网络控制系统
RBF神经网络
分数阶PID控制器
Networked Control System（NCS）
radial order PID controller basis function（RBF） neural network
fractional order PID controller
