连续搅拌反应釜的智能PID控制  

Intelligent PID Control of Continuous Stirred Tank Reactors

作　　者：翟廉飞[1] 柴天佑[1,2] 靖峰[3] 

机构地区：[1]东北大学流程工业综合自动化教育部重点实验室,沈阳110004 [2]东北大学自动化研究中心,沈阳110004 [3]沈阳东北电力调节技术有限公司,沈阳110179

出　　处：《系统仿真学报》2009年第12期3753-3757,共5页Journal of System Simulation

基　　金：国家973计划项目(2009CB320601);国家自然科学基金项目(60828007);国家创新研究群体科学基金项目(60821063);高等学校学科创新引智计划项目(B08015)

摘　　要：针对一类具有强非线性的连续搅拌反应釜,常规的控制策略难以取得满意的控制效果。为解决上述问题,本文将常规PID控制与非线性项的神经网络补偿相结合,提出了连续搅拌反应釜的智能PID控制方法。该方法基于常规增量式数字PID控制器,采用多层神经网络对非线性项进行估计和在线自适应补偿,易于在DCS中实现。仿真和实验结果表明了算法的有效性和可实现性。For a class of continuous stirred tank reactors （CSTR） which has strong nonlinearity, satisfied control performance can hardly be achieved by using traditional control methods. To deal with such problem, an intelligent proportional- integral-derivative （PID） control method was proposed by combining a traditional PID controller and a neural network compensator for nonlinear term. The proposed control method is based on the traditional incremental digital PID controller, and multi-layer neural network is employed to estimate and compensate the nonlinear term, therefore, the proposed control can be easily realized in distributed control system （DCS）. Simulation results and experiment result illustrate the effectiveness and practicability of the proposed control.

关 键 词：PID控制 神经网络 DCS 连续搅拌反应釜 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]