基于模糊神经网络PID控制的粉体包装计量控制系统  

Powder packaging measurement control system based on fuzzy neural network PID control

作　　者：王艳[1] 陈静[1] 王志山[1] 李昆祥 徐芸[1] 徐雪萌[1] WANG Yan;CHEN Jing;WANG Zhi-shan;LI Kun-xiang;XU Yun;XU Xue-memg(Henan University of Technology,Zhengzhou,Henan 450001,China)

机构地区：[1]河南工业大学

出　　处：《食品与机械》2020年第1期136-139,共4页Food and Machinery

基　　金：国家重点研发计划(编号：2018YFD0400704);河南省科技厅自然科学项目(编号：182102110163)

摘　　要：针对粉体包装计量控制系统由于传感器、螺杆的旋转惯性、零点漂移,下料冲击力等因素的影响而造成的系统延迟、非线性等问题,提出一种基于模糊神经网络PID控制粉体包装计量控制系统。利用模糊神经网络良好的动态控制特性和自学习能力来调整PID控制比例、积分、微分3个调整参数。借助MATLAB simulink仿真软件进行系统的模拟仿真。结果表明,该模糊神经网络PID控制系统稳定时间能缩短约45%,超调量约减少16%。由此可得模糊神经网络PID控制系统优于传统的PID控制系统。The work aims to the delay and nonlinearity of powder packaging metering control system caused by sensor,screw rotation inertia,zero drift,cutting impact and other factors,the powder packaging metering control system based on fuzzy neural PID control is proposed.Using the good dynamic control characteristic and self-learning ability of the fuzzy neural network to adjust the PID control proportion,integral and differential three adjustment parameters.The simulation and simulation of the system was carried out with the help of MATLAB simulink simulation software.The results show that the fuzzy neural network PID control system can shorten the stability time by about 45%and the overshoot by about 16%,Therefore,the fuzzy neural PID control system is superior to the traditional PID control system.

关 键 词：粉体包装 计量系统 模糊神经网络 PID控制 MATLAB simulink 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程] TB48[一般工业技术—包装工程]