基于模糊模型的结构和参数的一体化辨识

基于模糊集合的模糊建模捕述复杂、病态、非线性系统的特性是一种有效方法．文中讨论了从样本数据中通过正交变换和模糊聚类获取模糊规则的方法．利用正交最小二乘对模糊聚类的结果进行变换，采用CGS（Classical Gram—Schmidt）方法确定对建模贡献大的规则，删除对建模贡献小的规则，并对模型中的参数进行估计，能够同时模对糊模型的结构和参数进行辨识．仿真结果表明，提出的方法能够对非线性系统进行模糊建模．

An Integrated Algorithm for Structure Identification and Parameter Identification of Fuzzy Model

Abstract For dynamic systems with complex, ill-conditioned, or nonlinear characteristics, the fuzzy modeling method based on fuzzy sets is very effective to describe the properties of the sys- tems. The orthogonal transform and fuzzy clustering algorithm are used to extract fuzzy rules from sampling data in the paper. The results acquired from fuzzy clustering algorithm are trans- formed to confirm the fuzzy rules by means of the orthogonal least squares. The classical Gram Schmidt method is used to acquire the important rules and remove the bad important rules. The parameters of fuzzy model are estimated by using the proposed method. The structure identifica- tion and the parameter identification of fuzzy model are synchronously confirmed in the proposed algorithm. With the illustration of the simulating results, the fuzzy model of non-linear system can be built by using the proposed algorithm.