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

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.