模糊Petri网与遗传算法相结合的优化策略  

Optimization strategies of combining fuzzy Petri nets with genetic algorithm

作　　者：李洋[1] 乐晓波[1] 

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410076

出　　处：《计算机应用》2006年第1期187-190,共4页journal of Computer Applications

基　　金：湖南省教育厅自然科学基金资助项目(01JJY2061);湖南省教育厅科研基金资助项目(01C306)

摘　　要：如何确定模糊产生式规则的各项参数对模糊Petri网(FPN)的建立具有非常重要的意义,一直是尚未解决的难题。文中首次将遗传算法引入到模糊Petri网的参数寻优过程,提出了一种基于遗传算法的参数寻优算法,该算法实现不依赖于经验数据,对初始输入无严格要求。仿真实例表明,由此训练出的参数正确率较高,所得的FPN具有很强的泛化能力和自适应功能。How to determine parameters of fuzzy production rules is significant for building a fuzzy Petri net but remains unsolved. Genetic Algorithm was originally introduced into the procedure of exploring the parameters of FPN and an exploring algorithm based on GA was proposed. The realization of this algorithm did not depend on experiential data and the requirements for primary input were not critical. Simulated experiment showed that the trained parameters gained from above alzorithm were hizhly accurate and the resultant FPN model owned strong generalizing capability and self-adjusting purpose.

关 键 词：模糊PETRI网 产生式规则 模糊推理 改进的遗传算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]