摘要
经典的基于对象精确数学模型的PID控制方法的自适应性较差 ,难以适应具有非线性、时变不确定性的被控对象 .神经网络控制算法的稳定性又受到迭代初值的影响 ,且算法复杂 .为此提出了一种基于RBF神经网络的、结构简单的、稳定的PID直接自适应控制方法 .讨论了控制器参数迭代初值选取的基本原则 ,并给出了在保证系统稳定性前提下参数的迭代算法 .仿真研究结果表明 ,该方法的鲁棒性和跟踪性能均优于经典PID方法 .
Classic PID control method which is based on precise mathematical model has poor adaptivity and is not adaptive to nonlinear and time-variant plants. Conventional neural network is always complicated and its stability often suffers from the effect of initial weight value selecting. A simple stable direct adaptive PID control algorithm is proposed, which is based on RBF neural network. To guarantee the system stability and improve the system precision, initial weight value selecting problem for the neural network is discussed and corresponding iterative algorithm is provided. Simulation results indicate that the system robustness and tracking performance are superior to those of classic PID method.
出处
《北京航空航天大学学报》
EI
CAS
CSCD
北大核心
2001年第2期153-156,共4页
Journal of Beijing University of Aeronautics and Astronautics
基金
航空基础科学基金资助项目! (0 0E5 10 2 2 )
关键词
神经网络
自适应控制
PID控制
RBF网络
Algorithms
Computer simulation
Initial value problems
Iterative methods
Mathematical models
Neural networks
Position control
Robustness (control systems)
System stability
Systematic errors