新型神经网络模型参考自适应控制系统设计

Novel design of neural network model reference adaptive control systems

针对任意复杂非线性系统,即控制器具有不可分离结构的离散非线性系统,提出新型神经网络模型参考自适应控制.该方案的提出简化了基于神经网络的模型参考自适应控制系统的设计,只需一个神经网络辨识器.统一了任意神经网络模型参考自适应控制的设计方法,更接近于工程实际.仿真结果证明了该方案的合理性和有效性.

This paper presents a novel scheme of neural network model reference control for arbitrary complex nonlinear, which in other words the controller is an inseparability discrete time nonlinear system. This scheme simplifies design process of NNMRACS, only with a single neural network identificationer. The scheme unifies the design of arbitrary NNMRACS, it even more closes to engineering process. Simulation shows its rationality and validity.