基于RBF神经网络的烟叶烤房PID解耦控制  

PID Decoupling Controller Based on RBF Neural Network for Tobacco Barn

作　　者：张峻颖[1] 刘东红[1] 

机构地区：[1]上海电子信息职业技术学院,上海201411

出　　处：《计算机与数字工程》2011年第8期21-24,共4页Computer & Digital Engineering

摘　　要：针对具有非线性、大滞后、时变耦合特点的烟叶烤房系统,提出将基于RBF神经网络的智能PID控制器应用于烟叶烤房,并给出控制系统的控制结构和原理。通过算法实现、与常规PID控制的性能比较以及模型参数不确定性等多方面的仿真研究表明:该方法可以实现PID控制参数的自整定,控制效果明显优于常规PID,控制精度高,响应速度快,跟踪性能、解耦性能良好,且对模型不确定性具有较强的鲁棒性,符合烟叶烤房控制系统的设计要求。PID Decoupling Controller based on RBF Neural Network was proposed for the tobacco barn system which are of characteristics of nonlinear and long time-delay, time-varying and coupling. The structure and the principle of control system was given. The simulation result shows that the control system works well with quick response, good robustness and perfect self adaptation. The design is effective to reduce the coupling influence of each control loop and improve the dynamic behavior and static characteristic of the system. It is suitable for the tobacco barn control system.

关 键 词：RBF神经网络 PID控制 解耦 烟叶烤房 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]