具有Hammerstein模型描述的非线性系统的基于混合神经网络的预测控制  

A model-predictive control method based on hybrid neural networks for nonlinear systems described by Hammerstein model

作　　者：向微[1] 陈宗海[1] 盛捷[1] 

机构地区：[1]中国科学技术大学自动化系,安徽合肥230027

出　　处：《控制理论与应用》2008年第5期857-861,共5页Control Theory & Applications

基　　金：国家自然科学基金资助项目(60575033).

摘　　要：本文针对多输入多输出Hammerstein模型提出了一种基于混合神经网络的模型预测控制策略,控制器采用线性优化机构和高斯径向基神经网络串联.该策略不需要假设Hammerstein模型的非线性部分由多项式构成,避免了已有研究在无根或重根情况下存在导致预测控制的优化特征丧失问题,而采用混合神经网络则避免了采用传统神经网络拟合动态映射时存在的网络规模大和实时性差的不足.A model-predictive control strategy based on hybrid neural networks for the multi-input and multi-output Hammerstein model is presented, which uses a linear optimal component and radial basis function neural networks in series. By this method, the nonlinear block is not limited to a polynomial equation, thus the requirement of real roots of the polynomial equation in traditional control designs is removed with no deterioration of the optimal performance. On the other hand, the hybrid neural networks are more efficient than the traditional neural networks which require complicated net structures in approximating dynamic mappings and show poor real-time performance.

关 键 词：HAMMERSTEIN模型 多输入多输出系统 混合神经网络 模型预测控制 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]