引用本文:黄道平,朱学峰,周其节.基于一种继承模型的多变量非线性预测控制[J].控制理论与应用,1999,16(1):38~42.[点击复制]
Huang Daoping,Zhu Xuefeng and Zhou Qijie.Multivariable Nonlinear Predictive Control Based on an Integrating Model[J].Control Theory and Technology,1999,16(1):38~42.[点击复制]
基于一种继承模型的多变量非线性预测控制
Multivariable Nonlinear Predictive Control Based on an Integrating Model
摘要点击 872  全文点击 415  投稿时间:1997-07-18  修订日期:1998-02-16
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  1999,16(1):38-42
中文关键词  预测控制  多变量非线性系统  人工神经网络  集成模型  CSTR反应器
英文关键词  predictive control  multivariable nonlinear system  ANN  integrating model  CSTR
基金项目  
作者单位
黄道平,朱学峰,周其节  
中文摘要
      提出了一种由人工神经网络与线性ARX模型结合的集成模型,给出了其辨识训练方法。以此模型为基础,提出了一种多变量非线性预测控制算法。他利用线性预测的成果,得到一解析式的非线性优化控制输入,避免了通常非线性模型(包括普通人工神经网络模型)预测控制所需的在线数值寻优计算,节约了在线计算时间,提高了算法可靠性和稳定性。进一步给出了CSTR反应器上的仿真实验结果。
英文摘要
      An integrating model combining the artificial neutal network with the linear ARX model and its identification method is ptoptsed.Based on that model,a multivariable nonlinear predictive control algorithm is presented.The algoruthm employs the result the linear predictive control,obtains explicit nonlinear optimal controlling inputs and doesn't need on-line numerical optimizing which is necessary in general nonlinear model(including ANN model) predictive control.That simulation results in CSTR and shown.