模糊神经网络算法在倒立摆控制中的应用

本文利用一种可以进行结构和参数学习的模糊神经网络成功地控制一级倒立摆，该网络是一种多层前馈网络，它将传统模糊控制器的基本要件综合到网络结构中。从而使该网络既具备神经网络的低级学习能力，从而还具备模糊逻辑系统类似人的高级推理能力。因而，给定训练数据后，该网络不仅可以学习网络参数，同时还可以学习网络结构。结构学习确定了表示了模糊规则和模糊分段数的连接类型以及隐节点数目。对一级倒立摆的实际控制效果可以证明该算法的性能和实用性。

Application of Fuzzy Neural Network in An Inverted Pendulum

This paper uses a supervised learning algorithm for controlling the single pendulum successfully,The Fuzzy Neural Network(FNN)is a feedforward multi-layered network,which integrates the basic elements of traditional fuzzy logic controller into a network structure.So tins network not only has low-level learning abilities,but also provides high-level human-like reasoning of fuzzy logic systems.Given training data,this algorithm can learn network parameters and structure simultaneously.The structure learning decides the proper connection types and the number of hidden units which represent fuzzy logic rules and the number of fuzzy partitions.The control results can illustrate its performance and applicability.