CSTR系统的基于CMFC神经元网络的学习控制研究  

The CMAC Neural Network Based Learning Control of the CSTR System

作　　者：许力[1] 蒋静坪[1] 

机构地区：[1]浙江大学电机系,杭州310027

出　　处：《控制与决策》1992年第2期131-136,共6页Control and Decision

基　　金：国家教委博士点基金

摘　　要：CMAC(Cerebellar Model Articulation Controller或Cerebellar Model Arithmetic Computer)神经元网络是由Albus提出的一种表达复杂非线性函数的表格查询的自适应系统。本文将CMAC应用到具体的连续搅拌反应釜(CSTR)系统的学习控制研究中,仿真结果表明,该学习控制策略具有较强的自学习能力且容易实现,对于改善非线性控制的性能,不失为一种有益的尝试。Proposed by J.S. Albus in 1975, the CMAC neural nework is an adaptive system by which complex nonlinear functions can be represented by referring to a look-up table. In this paper, the CMAC neural network is applied to the learning control of the Continuous-Stirred Tank Reactor(CSTR) system, with the simulation results showing that this learning strategy is strong in self-learning and easy to realize, and is helpful for the improving of nonlinear control performance.

关 键 词：神经网络 反应器 CSTR 

分 类 号：TQ052.5[化学工程]