采用差分进化算法优化模糊Petri网参数  

Optimizing parameters of fuzzy Petri net using differential evolution algorithm

作　　者：张弛[1] 乐晓波[1] 周恺卿 莫礼平[3] 

机构地区：[1]长沙理工大学计算机与通信工程学院,湖南长沙410114 [2]马来西亚理工大学计算机科学与信息系统系,柔佛州新山市马来西亚81310 [3]吉首大学信息科学与工程学院,湖南吉首416000

出　　处：《计算机工程与科学》2014年第6期1095-1100,共6页Computer Engineering & Science

基　　金：国家自然科学基金资助项目(61170199);湖南省自然科学基金资助项目(08JJ3124)

摘　　要：如何有效地确定模糊Petri网(FPN)的各项参数、摆脱自学习能力差的缺点,一直是悬而未决的问题。针对此问题,将差分进化算法首次引入到FPN参数优化中,根据FPN的实际特征,提出了一种改进的差分进化算法。算法采用混沌策略产生初始种群,融合自适应变异因子及早熟惩罚策略提高种群多样性,同时保证很强的收敛性与全局性。仿真实验表明,将改进的差分进化算法与传统算法相比较,收敛到理想参数值的速度提高了5倍。It is significant and being unsolved yet for building a Fuzzy Petri Net （FPN） so as to get rid of the shortcomings of poor self learning ability.To address this problem,differential evolution algorithm is originally introduced into the procedure of exploring parameters of FPN.According to the actual characteristics of FPN,an improved differential evolution algorithm is proposed.The algorithm utilizes the chaotic strategy to generate initial population and integrates self adaptive factors with precocious punishment strategies as a result of enhancing the diversity of population,while ensuring being strong convergent and global.Simulation experiment shows that the trained parameters gained from the proposed algorithm are 5 times accurate than any other traditional algorithms.

关 键 词：模糊PETRI网 模糊推理 改进的差分进化算法 早熟惩罚 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]