基于SDNA-GA优化的模糊神经网络控制  

Optimal design of fuzzy neural network controller based on SDNA genetic algorithm

作　　者：宋春宁[1] 刘少东[1] 

机构地区：[1]广西大学电气工程学院,南宁530004

出　　处：《控制与决策》2014年第4期731-734,共4页Control and Decision

基　　金：国家自然科学基金项目(60924002)

摘　　要：针对最新的生物DNA研究,病毒中同一DNA碱基顺序可以编码出2条或者3条不同的多肽链.在此基础上分析与模仿了重叠基因和重叠密码的机理,得到一种新的基于重叠基因编码框架,从而提高了问题求解的效率;同时,得到一种移码解读框架的DNA遗传算法(SDNA-GA)计算模型,并将其应用于一类广义隶属度型T-S模糊神经网络控制器(GTS-FNNC)的优化设计,实现了GTS-FNNC的在线学习.According to the latest biological research of DNA, the virus in the same DNA base sequence can encode two or three different polypeptide chains. Further analysis and imitation of overlapping genes and password mechanism are inspired by using the above mechanism, and a new overlapping gene encoding framework is found, thereby improving the efficiency of problem solving. A frame shift interpretation framework based on this mechanism of DNA genetic algorithm（SDNA-GA） computing model is applied to a class of the generalized membership type T-S fuzzy neural network controller（GTS-FNNC） optimization design to achieve GTS-FNNC online learning.

关 键 词：重叠基因编码框架 自适应变异 SDNA编码框架 遗传算法 T-S模糊神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]