基于模糊与神经网络技术的复杂非线性跟踪控制

针对一类具有不确定性、多重时延和状态未知的复杂非线性系统,把模糊T-S模型和RBF神经网络结合起来,提出了一种基于观测器的跟踪控制方案.首先,应用模糊T-S模型对非线性系统建模,设计观测器用来观测系统状态,并由线性矩阵不等式得到模糊模型的控制律;其次,构建了自适应RBF神经网络,应用自适应RBF神经网络作为补偿器来补偿建模误差和不确定非线性部分.证明了闭环系统满足期望的跟踪性能.示例仿真结果表明了该方案的有效性.

Complex Nonlinear Tracking Control Based on Fuzzy and Neural Network Technique

Combining fuzzy T-S model and RBF neural networks, this paper presents an observer-based tracking control scheme for a class of complex nonlinear system including uncertainty, multiple time delays and unknown states. Firstly, the fuzzy T-S model is used to approximate the nonlinear systems. An observer is designed to observe the system states. The fuzzy control law of the fuzzy model is derived by the linear matrix inequality. Secondly, the adaptive RBF neural networks are constructed. The modeling errors and the uncertain nonlinear parts are eliminated by a compensator based on the adaptive RBF neural networks. It is proved that the closed loop system satisfies the anticipant tracking performance. The simulation results demonstrate that the control scheme is effective.