基于自适应交互算法的神经网络控制器设计

Neural Network Controller Based on Adaptive Interaction Algorithm

自适应交互算法是一种简单有效的算法 ,可以应用于不同类型的系统。与常用的BP算法相比 ,它不需要反馈网络反向传播误差 ,可以直接用来设计自适应神经网络控制器 ,使控制器的设计简单化。将这种算法应用于神经网络 ,并设计了神经网络控制器。通过仿真研究表明 ,用自适应交互算法设计的控制器不仅结构简单 。

Adaptive interaction algorithm is a simple and efficient methodology, which can be applied to arbitrary systems.Compared to BP algorithm,it can be applied without the need of backward propagating the error throughout a feedback network.This important property makes it possible to design the simple neural network controller directly.The algorithm is applied to neural networks and used to design neural network controller.Simulation results demonstrate that the controller is not only simple in structure but also good in control effectiveness.