【摘要】 T-S模糊模型已得到了广泛的研究与应用.但在该模型的建模过程中,在结构辨识、参数优化等方面仍存在一些不足,为此提出了一种基于ISODATA算法的自组织T-S模糊系统.该方法基于输入输出数据,分两步对模糊系统进行建模.第一步,使用基于线性原型的ISODATA算法,对输入输出数据进行聚类,确定系统结构.第二步,建立初始T-S模糊系统,然后使用粒子群算法优化系统参数.与传统方法相比,具有自动优化系统结构的优点.仿真结果验证了该方法的有效性.更多还原

【Abstract】 T-S fuzzy model has been studied and applied widely.While during the modeling progress of T-S fuzzy model,there’re some problems on structure identification、parameter optimization etc.This paper proposes a self-organizing T-S fuzzy system based on ISODATA algorithm.From the input-output data,we model the fuzzy system during two steps.Step 1 gets optimal class of the input-output data using ISODATA algorithm based on linear prototype,and determines the system structure.Step 2 builds a simple T-S fuzzy model and optimizes the system parameters by Padicle Swarm Optimization algorithm.Simulation results show the effectiveness of the proposed method.更多还原