«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:

期数:

2015年05期

页码:

97

栏目:

出版日期:

2015-10-15

文章信息/Info

Title:

PID neural network decoupling control based on seeker optimization algorithm

文章编号:

1000-0682(2015)05-0000-00

作者:

刘 俊

（商洛学院 电子信息与电气工程学院，陕西 商洛 726000）

Author(s):

LIU Jun

(Electronic Information and Electrical Engineering College,Shangluo University, Shaanxi Shangluo 726000,China）

关键词:

搜寻者优化算法; PID; 解耦控制; 神经网络

Keywords:

seeker optimization algorithm;  PID;  decoupling control;  neural network

分类号:

TP183

DOI:

-

文献标志码:

A

摘要:

传统的PID神经网络，由于初始权值随机选择，权值学习采用BP算法，所以容易陷入局部极值，进而导致该方法无法得到高精度控制结果。该文提出采用搜寻者优化算法优化PID神经网络初始权值，再把最优初始权值带入PID神经网络，实现解耦控制。对一个耦合系统进行仿真实验。结果表明，与目前控制效果较好的粒子群算法优化PID神经网络相比，该算法收敛速度更快、稳态误差更小，同时也具有良好的自适应和抗干扰能力，能够实现快速、高精度、稳定的解耦控制。

Abstract:

Traditional PID neural network, in which initial weights are randomly selected and weight learning method uses BP algorithm, tends to fall into local extremum, so the method cannot get precise control. Seeker optimization algorithm(SOA) is adopted to optimize the initial weights of PID neural network, and the decoupling control is realized by putting the optimal initial weights into PID neural network. A coupling system is simulated, and the result shows that, compared with PID neural network which is based on particle swarm algorithm(PSO), PID neural network which is based on SOA(SOA-PIDNN) shares better control effect and smaller steady-state error; moreover, SOA-PIDNN is endowed with adaptive and anti-interference ability, which facilitate rapid, accurate and stable decoupling control.

备注/Memo

备注/Memo:

收稿日期 ： 2015-02-05

作者简介 ：刘俊（ 1986 ），男，山西省大同市人，硕士研究生，讲师，主要研究智能控制和智能算法。

常用功能

更新日期/Last Update: 1900-01-01