连续搅拌反应釜的混合监督学习控制

A Hybrid Supervised Learning Control of Continuous Stirred Tank Reactor

提出了一种连续搅拌反应釜 (CSTR)的混合监督学习控制方法。控制系统有远程控制与极值控制两种模式。极值控制时神经网络进行有监督的学习 ,远程控制时神经网络进行无监督的学习。控制系统的设计不需要 CSTR系统的精确模型。仿真实验结果表明 ,所提出的混合控制方案具有满意的动态和稳态控制性能 。

A new hybrid supervised learning control scheme is presented for continuous stirred tank reactor(CSTR)systems.The control system works at distal supervised learning control mode or extreme control mode.Neural networks controller is trained under supervised signal when system works at extreme control mode and there is no supervised signal when system works at distal control mode.The precise model of the CSTR is not necessary for design of control system.Simulation results show satisfactory dynamic and stationary performances and strong adaptability.