›› 2015, Vol. 28 ›› Issue (11): 25-.

• 论文 • 上一篇    下一篇

PM2.5测量系统中改进神经网络控制算法优化补偿

邹孔雨,佟国香   

  1. (上海理工大学 光电信息与计算机工程学院,上海 200093)
  • 出版日期:2015-11-15 发布日期:2015-12-15
  • 作者简介:邹孔雨(1989—),男,硕士研究生。研究方向:嵌入式系统。E-mail:1013874609@qq.com。佟国香(1989—),女,副教授。研究方向:嵌入式系统设计与开发,计算机控制应用

Optimization and Compensation of PM2.5 Measurement System Based on the Improved Neural Network Control Algorithm

ZOU Kongyu,TONG Guoxiang   

  1. (School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)
  • Online:2015-11-15 Published:2015-12-15

摘要:

针对现阶段PM2.5测量系统的测量精度较低的问题,提出了改进的BP神经网络PID控制算法对其进行优化补偿。通过对粒子群优化算法的速度公式进行了改进,采用优化的粒子群算法优化了BP神经网络,将其用于PID的在线参数调节,以PM2.5测量系统作为研究对象,将改进的BP神经网络PID控制算法与传统PID分别作了仿真研究。研究结果表明,基于改进的粒子群优化算法改进的BP神经网络PID控制算法与传统的PID控制相比,提高了测量精度,在一定程度上减少了误差。

关键词: 粒子群优化, BP神经网络, PID控制, 测量精度

Abstract:

An improved BP neural network PID control algorithm is proposed to optimize and compensate the PM2.5 measuring system for a better accuracy.Firstly,the velocity formula of particle swarm optimization algorithm is improved,then the improved PSO algorithm is applied to optimize the BP neural network to adjust the PID parameters online,and finally the improved PSO optimize BP neural network PID control algorithm and the traditional PID are simulated.The result proves that the improved PSO optimize BP neural network PID control algorithm can improve the accuracy of measurement with a reduced error compared with PID.

Key words: PSO;BP neural network;PID control;accuracy of measurement

中图分类号: 

  • TP18