基于T-S模糊模型的RBF网络的自适应学习算法  

An adaptive learning algorithm for T-S fuzzy model based RBF neural network

作　　者：李战明[1] 王君[1] 康爱红[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,甘肃兰州730050

出　　处：《兰州理工大学学报》2004年第2期82-85,共4页Journal of Lanzhou University of Technology

基　　金：国家863计划(西部专项)(2002BA901A28)

摘　　要：针对多维模糊推理中的推理规则庞大和参数难辨识的问题,提出一种基于T S模糊模型的RBF神经网络的自适应学习算法.该算法不仅能动态调节T S型模糊RBF网络的隐节点数,还能使网络的数据中心值自适应变化,有较好的自学习能力和优化能力.仿真结果验证了该算法是有效和可行的,表明此T S型模糊RBF网络不仅可以快速逼近任意多变量非线性函数,而且具有良好的自适应能力.An adaptive learning algorithm for T-S fuzzy model based RBF neural network is developed,with which the difficulties due to enormous fuzzy inference rules as well as parameter identification in multi-dimension fuzzy inferences can be overcome. The number of hidden layer nodes of T-S fuzzy RBF net is not only modified dynamically but also the position of RBF net data centers is changed adaptively during learning progress, so that the algorithm has better self-learning and generalization ability. Simulation results show that the algorithm is effective and feasible, and any nonlinear function can be approximated with any required degree of accuracy.

关 键 词：T-S模糊模型 RBF网络 自适应学习算法 模糊推理 隐节点数 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置]