摘要: 提出一种基于微分进化算法的TS模糊模型设计方法。该方法利用“匹茨堡型”实数编码的微分进化算法,对初始模糊模型的结构和参数进行学习。微分进化算法的目标函数同时考虑模型的精确性和解释性。利用该方法进行一类合成非线性动态系统的辨识,仿真结果验证了该方法的有效性。
关键词:
TS模糊模型,
模糊聚类,
遗传算法,
微分进化算法,
解释性,
精确性
Abstract: This paper proposes an approach to construct TS fuzzy model based on Differential Evolution(DE) algorithm. The structure and parameters of the fuzzy model are optimized by the Pittsburgh-style real-coded DE algorithm. The fitness function that combines the interpretability index and the precision index is calculated on the differential evolution algorithm. Compared with other methods reported in the literature on the synthetic nonlinear dynamic system, simulation results show that the proposed approach is valid.
Key words:
TS fuzzy model,
fuzzy clustering,
Genetic Algorithm(GA),
Differential Evolution(DE) algorithm,
interpretability,
precision
中图分类号:
张永, 黄成, 徐志良, 吴晓蓓. 基于微分进化算法的模糊模型设计[J]. 计算机工程, 2011, 37(21): 165-166,169.
ZHANG Yong, HUANG Cheng, XU Zhi-Liang, TUN Xiao-Bei. Design of Fuzzy Model Based on Differential Evolution Algorithm[J]. Computer Engineering, 2011, 37(21): 165-166,169.