基于动态递归神经网络的动态矩阵控制

DYNAMIC MATRIX CONTROL BASED ON DYNAMIC RECURRENT NEURAL NETWORKS

给出了利用动态递归神经网络 (DRNN)重构一个非线性动态过程的方法 ,对权值调整算法进行了推导。采用的动态递归神经网络具有非线性系统状态观测器的结构特征 ,容易实现并进行稳定性分析。利用训练好的网络作为预估模型 ,设计了基于DRNN的动态矩阵控制算法。

A nonlinear dynamic process is reconstructed by using dynamic recurrent neural networks (DRNN). The main idea is to construct an observer liked dynamic recurrent neural network to match a practical process. The network is trained by using input and output information of practical systems. An algorithm for adjusting weight matrix of the network is given. After a dynamic recurrent neural network is well trained, the so called DRNN based on predictive control can be implemented. The well trained dynamic recurrent neural network is taken as a predictive model in the proposed control scheme. A simulation for a nonisothermal continuous stirred tank reactor (CSTR) system demonstrates the effectiveness of the training algorithm and the control strategy.