基于RBF神经网络的PID参数自校正方法研究  

PID parameter self-correction method based on RBF neural networkZhang

作　　者：张静静 太飞 ZHANG Jingjing;TAI Fei(Hebei University of Architecture,Zhangjiakou,Hebei 075000)

机构地区：[1]河北建筑工程学院,河北张家口075000

出　　处：《河北建筑工程学院学报》2024年第4期180-186,共7页Journal of Hebei Institute of Architecture and Civil Engineering

基　　金：河北省高等学校科学技术研究项目资助(QN2022108)。

摘　　要：在非线性系统的控制过程中,由于输入参数不停的变化,传统PID控制很难设定到理想参数,为了快速有效的设置最优控制参数KP、KI、KD,采用RBF神经网络算法进行参数自校正整定。给定初始值后,此算法会逐步调整KP、KI、KD三个参数,最终稳定到最优值。通过仿真可以得出在RBF神经网络的PID自校正控制算法的调节控制下,能够快速有效的对PID进行参数稳定,从而对非线性系统进行优化控制。In the control process of nonlinear system,due to the constant change of input parameters,it is difficult for traditional PID control to set the ideal parameters.In order to set the optimal control parameters KP,KI and KD quickly and effectively,this paper adopts RBF neural network algorithm for parameter self-tuning.After the initial value is given,the algorithm will gradually adjust KP,KI and KD,and finally stabilize to the optimal value.Through simulation,it can be concluded that under the control of the PID self-correcting control algorithm of RBF neural network,the PID parameters can be stabilized quickly and effectively,so as to optimize the control of the nonlinear system.

关 键 词：RBF神经网络 自校正 PID控制 非线性系统 

分 类 号：TP15[自动化与计算机技术—控制理论与控制工程]