自重构的人工免疫网络模型  

Artificial Immune Network Model with Self Reconfiguration

作　　者：龚涛[1] 

机构地区：[1]东华大学信息科学与技术学院,上海201620

出　　处：《计算机测量与控制》2008年第12期1915-1918,共4页Computer Measurement &Control

基　　金：国家自然科学基金项目(60404021);上海市教育发展基金会晨光项目(2007CG42);东华大学校基金项目(104-10-0044017)。

摘　　要：由于未知环境、突发故障、不可预测攻击等因素,人工免疫系统的故障检测与修复、网络重构等问题影响系统的整体功能和鲁棒性;为了探究此类问题的解决方法,提出了自重构的人工免疫网络模型,利用系统的正常模型提高故障的检测率和修复率,利用重构策略增强系统的适应性和容错性;进而,设计了人工免疫网络的自重构算法和免疫算法,探讨了自重构人工免疫网络在多机器人系统中的应用方法;通过网络特性分析和实验验证,自重构的人工免疫网络模型是有效而有用的。Due to such factors as unknown environment, sudden fault and unpredictable attack, the problems, which include fault detec tion, repairing, and network reeonfiguration, of some artificial immune systems affect the whole functions and robustness of the system. To investigate the methods for solving the problems, an artificial immune network model with self reconfiguration was proposed, the normal model was used to increase probability for detecting faults ＆ repairing the damaged system, and the reconfiguration strategies were used to make the system more adaptive with fault tolerance. Moreover, the self reconfiguration algorithm and immune algorithms were designed for the artificial immune network, and the methods for utilizing the self--reconfigurable artificial immune network in the multi--robot system were discussed. The analysis of network features and the experiments shows that the model of artificial immune network is effective and use ful.

关 键 词：重构 人工免疫网络模型 免疫算法 多机器人 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]