非线性互联系统的分散混合自适应智能控制

针对一类高阶互联MIMO非线性系统，利用TS模糊系统和神经网络的通用逼近能力，在神经网络控制器中引入模糊基函数，提出一种分散混合自适应智能控制器设计的新方案．基于等价控制思想，设计分散自适应控制器，无需计算TS模型．通过对不确定项进行自适应估计，取消了其存在已知上界的假设．通过理论分析，证明了闭环智能控制系统所有信号有界，跟踪误差收敛到零．

Decentralized hybrid adaptive intelligent control of nonlinear interconnected systems

A new design scheme of decentralized hybrid adaptive intelligent controller for a class of MIMO nonlinear systems with the high-order interconnections is proposed. The design is based on the universal approximation capability of the Takagi-Seguno (TS) fuzzy systems and neural networks. According to the principle of certainty equivalent control, a decentralized adaptive neural network controller embedded with fuzzy basis functions is designed to achieve the tracking objective without computation of the TS fuzzy model. The approach does not require the upper bound of the uncertainty term to be known through some adaptive estimation. The closed-loop intelligent control system is proven to be globally stable in the sense that all involved signals are bounded, with tracking errors converging to zero.