摘要
针对常规PID控制器和模糊PID控制器存在控制精度差、不能自适应、模糊规则难以确定等问题,本文提出一种基于RBF模糊神经网络的PID自整定控制算法,RBF模糊神经网络参数先采用遗传算法粗调,达到预定精度后,继续使用BP算法提高精度。通过在MATLAB中进行神经网络训练和PID仿真实验,表明了改进RBF模糊神经网络PID控制器具有收敛速度快、能够自适应、控制精度高等优点,具有一定的可行性。
Aiming at the problems of poor control precision,inability to adapt,and difficulty in determi ning fuzzy rules for conventional PID controllers and fuzzy PID controllers,this paper proposes a PID self⁃tuning control algorithm based on RBF fuzzy neural network.The parameters of RBF fuzzy neural network are first roughly adjusted by genetic algorithm,when it reaches the predetermined precision,then used BP algorithm to improve the precision.The neural network training and PID simulation experiments in MATLAB show that the improved RBF fuzzy neural network PID controller has the advantages of fast convergence,adaptive and higher control precision,and has certain feasibility.
作者
牛坤
张志安
王鹏飞
朱新年
NIU Kun;ZHANG Zhi-an;WANG Peng-fei;ZHU Xin-nian(School of Mechanical Engineering,Nanjing University of Science&Technology,Nanjing 210000,China)
出处
《电子设计工程》
2020年第12期172-177,182,共7页
Electronic Design Engineering
