基于Pareto协同进化算法的TS模糊模型设计  

Design of TS Fuzzy Model Based on Pareto-coevolution Algorithm

作　　者：张永[1] 邢宗义[1] 向峥嵘[1] 胡维礼[1] 

机构地区：[1]南京理工大学自动化学院,南京210094

出　　处：《控制与决策》2006年第12期1332-1337,1342,共7页Control and Decision

基　　金：国家自然科学基金项目(60474034);中国博士后科学基金项目(2005037733)

摘　　要：提出一种可同时构造多个精确性和解释性较好折中的TS模糊模型的设计方法.该方法由以下两步组成:1)采用模糊聚类算法辨识初始模型;2)利用Pareto协同进化算法对所获得的初始模型进行结构和参数优化.Pareto协同进化算法由规则前件种群和隶属函数种群组成,其目标函数同时考虑模型的精确性和解释性,采用一种新的基于非支配排序的多种群合作策略.利用该方法对一类合成非线性动态系统进行建模,仿真结果验证了该方法的有效性.A novel approach to construct accurate and interpretable TS fuzzy systems is proposed. The approach is composed of two phases. The first one is to identify the initial fuzzy system using the fuzzy clustering algorithm. The second one is to optimize the structure and the parameters of the fuzzy system by the Pareto-coevolution algorithm. The Pareto-coevolution algorithm owns two species including the premise structure species and the parameters species. Considering both precision and interpretability, three objective functions of the fuzzy system are defined and calculated by a new non-dominated sorting method. The proposed approach is applied to a benchmark problem to show its validity.

关 键 词：TS模糊模型 模糊聚类 PARETO解 协同进化算法 解释性 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]