摘要
随着数控技术的发展,传统的PID整定方式已经不能满足伺服系统的控制要求.利用改进共轭梯度法对BP神经网络算法进行优化.将改进BP神经网络算法应用到PID的整定中,构建改进BP神经网络自整定PID控制器.将设计好的BP神经网路PID控制器应用到伺服系统的控制结构图中.与BP神经网络自整定PID控制器,在Matalab的simulink里面进行建模仿真比较.仿真结果表明改进BP神经网络自整定PID控制器具有较好的快速响应能力、系统稳定性和抗干扰能力.
With the development of numerical control technology,the traditional PID setting method is unable to meet the control requirements of the servo system.The improved method of conjugate gradient is used to optimize the BP neural network algorithm.The improved BP neural network algorithm is applied to the tuning of PID,and an improved BP neural network self-tuning PID controller is constructed.The designed BP neural network PID controller is applied to the control structure of the servo system.The PID controller of the improved BP neural network is compared with the traditional self-tuning PID controller in Matalab.The simulation results show that this PID controller has fast response ability,a good system stability and anti-interference ability.
作者
叶海平
YE Hai-ping(Mechanical and Automation Engineering,Zhangzhou Institute of Technology,Zhangzhou 363000,China)
出处
《云南民族大学学报（自然科学版）》
CAS
2018年第2期136-139,共4页
Journal of Yunnan Minzu University:Natural Sciences Edition
基金
福建省中青年教师教育科研基金(JAT160872)
关键词
改进共轭梯度法
伺服系统
BP神经网络
PID控制器
自整定
improved method of conjugate gradient
servo system
BP neural network
PID controller
self-tuning
作者简介
叶海平(1982-),男,硕士,讲师.主要研究方向:数控技术.
