基于Tank-Hopfield神经网络的有约束多变量广义预测控制器

The Constrained Multivariable Predictive ControllerBased on Tank-Hopfield Nenral Network

中文关键词  神经网络  T-H网络  预测控制  多变量控制  二次优化

英文关键词  neural network  T-H network  predictive control  multivariable control  quadratie opti-mization

中文摘要

      通过对系统的信号约束，构成有约束多变量广义预测控制问题，并运用T-H优化神经网络来求解这一复杂的优化问题. 在求解过程中，有约束广义预测控制的求解被转化为一个T-H优化电路弼络的稳态解. 因此可以通过硬件电路或龙格一库塔数值方法进行求取. 在一个工业过程模型上的仿真研究证明了这一方法是非常有效的.

英文摘要

      Through the constrain of the signals of sy8tem，this paper drives the generalized predictive control，and solves the complicate optimizing problem with T-H neural network It is transformed into the solving of a stable state of a T-H optimizing neural networks for the constrainetl general ized predictive controllcr. Hence，the solution can be obtained through hardware electricity circuit or Runge-Kutta numerical algorithm. The simulation research on a process verifies that the method is very effective.