基于最小二乘支持向量机的模糊辨识及其在热工对象逆系统建模中的应用  

Fuzzy Identification Based on Least Squares Support Vector Machine and Its Application on Modeling the Inverse System of Thermal Object

作　　者：陈红[1] 王广军[1] 王志杰[1] 沈曙光[1] 

机构地区：[1]重庆大学动力工程学院,重庆市沙坪坝区400044

出　　处：《中国电机工程学报》2010年第29期103-106,共4页Proceedings of the CSEE

基　　金：国家自然科学基金项目(50776103)~~

摘　　要：建立1种基于最小二乘支持向量机(least squares support vector machine,LSSVM)的模糊辨识方法,根据学习样本集的模糊聚类结果,产生LSSVM的模糊核函数,并证明该模糊核函数是Mercer核函数,为LSSVM提供1种构造核函数的简便方法。此外,由于所建立的模糊辨识方法在T-S模糊模型的后件参数学习过程中采用结构风险最小化准则,提高了模型的泛化能力。利用所建立的辨识方法进行热工对象逆系统模型辨识,证明了该方法的有效性。A fuzzy identification method was established based on the least squares support vector machine（LSSVM）.The fuzzy kernel function of LSSVM was generated on the base of fuzzy clustering results of learning sample set and it is proved that the fuzzy kernel function is the Mercer kernel function,which provides an easy way to construct the kernel function for LSSVM.In addition,the fuzzy identification model established has improved the generalization performance through the use of structural risk minimization criterion in the learning process of the consequent parameters of T-S fuzzy model.The established identification method was used to identify the inverse model of thermal object and its effectiveness was proved.

关 键 词：最小二乘支持向量机 核函数 T-S模糊模型 逆模型 辨识 

分 类 号：TK172[动力工程及工程热物理—热能工程]