基于UKF的自组织直觉模糊神经网络  

Self-Organising Intuitionistic Fuzzy Neural Networks Based on UKF

作　　者：徐小来[1] 雷英杰[1] 谢文彪[2] 

机构地区：[1]空军工程大学导弹学院,陕西西安710049 [2]长沙理工大学电气与信息工程学院,湖南长沙410076

出　　处：《电子学报》2010年第3期638-645,共8页Acta Electronica Sinica

基　　金：国家自然科学基金项目(No.60773209);陕西省自然科学基金项目(No.2006F18)

摘　　要：模糊集在语义描述上存在不足,因此,如何对模糊神经网络进行扩展是当前模糊神经网络研究的热点,针对这一问题,本文提出了基于UKF的自组织直觉模糊神经网络.首先,给出了直觉模糊神经网络的结构和各层的含义;其次,推导了直觉模糊神经网络的学习算法,用LLS和UKF分别学习线性和非线性参数;然后,给出了模糊规则生成的准则,并用误差下降率方法作为规则修剪的策略,删除作用不大的规则;最后,通过典型的函数逼近、系统辨识和时间序列预测实例,表明本文算法得到的直觉模糊神经网络的结构更为紧凑,泛化性能也更佳.Because fuzzy sets exist deficiency on semantic description,much of the current research interest in neuro-fuzzy hybrid systems is focused on how to extend fuzzy neural networks.To deal with this problem,a self-organizing intuitionistic fuzzy networks based on UKF is presented.Firstly,structure of intuitionistic fuzzy networks and meanings of each layer is proposed.Sec-ondly,training algorithm is deduced,and LLS and UKF are used to learn linear and non-linear parameters respectively.Thirdly,guideline of how to generate a new rule is given,and method of error descending rate is used as fuzzy rule pruning strategy,so that rule which plays an unimportant role in the system is deleted.At last,typical experiments of function approximation,system identifi-cation and prediction of time-series indicate that a fuzzy network obtained by the proposed algorithm has a more tighten structure and better generalization than other algorithms.

关 键 词：直觉模糊集合 UKF 自组织模糊神经网络 系统辨识 函数逼近 时间序列预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]