基于模糊聚类的改进模糊辨识方法

Improving Fuzzy Identifying Method Based on Fuzzy Clustering

针对以往模糊建模方法不能很好优化模糊模型输入空间的问题 ,本文提出了一种基于新的目标函数的模糊聚类方法 ,从而使模型的输入输出空间映射空间具有逼近实际输出的能力 ,从而达到优化模型结构的目的 .仿真实例表明 ,该方法能够辨识非线性系统 ,能显著提高建模的精度 .

Aiming at the problem that the past fuzzy identifying method can not optimize the input-output space of fuzzy model, this paper proposes a fuzzy clustering method based on a new objective function. This method enables the input-output mapping space to approach the real output, thus optimizing the model structure. Simulation example demonstrates that this method can identify non-linear systems and significantly improve modeling accuracy.