一种基于模糊径向基函数神经网络的自学习控制器

A Self-learning Controller Based on Fuzzy Radial Basis Functi on Neural Networks

摘要: 提出了一种新型的基于模糊径向基函数（RBF）的神经网络学习控制器，并应用于电液伺服系统．由于RBF网络和模糊推理系统具有函数等价性，采用模糊经验值方法选取网络中心值和基函数数目．与一般的神经网络自学习控制器不同，以系统动态误差作为网络输入量，RBF神经网络控制器学习的是整个系统的动态逆过程，因而控制性能明显提高．对电液位置伺服系统的仿真和实验结果表明，该控制方案可以有效提高系统的控制精度和自适应能力．

Abstract: A new learning controller based on fuzzy radial basis function neural networks is proposed and used in electrohydraulic servo system.Due to the function equivalence between RBF neural networks and fuzzy inference system,fuzzy experience method is adopted to select the centers and the number of basis function networks.Unlike common neural network learning controller,the dynamic errors are served as the network input.The RBF neural networks learn dynamic inverse process of the whole system,so the control performance is improved obviously.The results of simulation and experiment on an electrohydraulic position servo system show that this control strategy can improve control prec ision and adaptive ability effectively.