北京航空航天大学学报 ›› 2005, Vol. 31 ›› Issue (09): 1045-1048.

• 论文 • 上一篇    

基于神经网络的仿真转台控制系统

裴忠才, 尹丽, 王占林   

  1. 北京航空航天大学 自动化科学与电气工程学院, 北京 100083
  • 收稿日期:2004-03-04 出版日期:2005-09-30 发布日期:2010-09-20
  • 作者简介:裴忠才(1968-),男,山东滕州人,副教授, peizc@buaa.edu.cn.

Simulating turntable control system with neural network

Pei Zhongcai, Yin Li, Wang Zhanlin   

  1. School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
  • Received:2004-03-04 Online:2005-09-30 Published:2010-09-20

摘要: 在转台存在偏载、摩擦等不确定负载干扰的情况下,用神经网络与PID(Proportional-Integral-Differential)控制相结合的方法,设计了适应负载变化的转台控制系统.分析了基于BP(Back Propagation)神经网络的自适应PID控制器的基本原理,建立了转台位置控制系统的数学模型,并对控制系统进行仿真分析和实验验证,通过与传统PID控制的对比实验与仿真表明:所设计系统由于有自学习能力,能动态调整PID参数,使系统表现出良好的抗干扰能力和跟踪性能,证明了所设计系统的有效性.该算法结构简单,PID初始参数调整方便,易于在转台实时控制系统中应用.

Abstract: To solve the turntable uncertain partial load and friction disturbance, a turntable control system was designed with neural-proportion-integral-differential (PID) theory. Because of the learning capacity of neural network, the control system showed adaptive capacity to the load disturbance. The basic theory of a self-adaptive PID controller based on back propagation (BP) neural network was described, The mathematic model of the turntable position control system was set up. A thorough analysis on the system was given by simulation and experiments. The simulation and experiment results prove that the turntable with neural-PID controller shows good track performance and capacity against the load disturbance, but the traditional PID controller hasn’t. The neural-PID system can regulate the PID parameters dynamically by self-learning to fit for the load changes and makethe PID parameters regulation become easier. The controller has a simple structure and can be easily realized in engineering. The results show the effectiveness of the control algorithm.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发