基于病毒猴群算法的传感器优化布置方法研究  

Virus monkey algorithm for optimal sensor placement

作　　者：伊廷华[1] 张旭东[1] 李宏男[1] 

机构地区：[1]大连理工大学建设工程学部土木工程学院,大连116023

出　　处：《计算力学学报》2014年第3期285-290,共6页Chinese Journal of Computational Mechanics

基　　金：国家优秀青年科学基金(51222806);国家自然科学基金面上项目(51178083);教育部博士点基金(20130041110031);2013大连市建设科技计划资助项目

摘　　要：将病毒进化理论引入到猴群算法中,提出了一种用于传感器优化布置的病毒猴群算法。采用双重编码的方式,克服了原猴群算法只能解决连续变量优化问题的缺陷;在猴群中引入生物病毒机制对其进行感染,通过病毒和猴群的分工协作,来实现猴群个体之间纵向和横向的信息交流,以此维持个体的多样性,来大幅度增强算法的局部搜索能力;并将猴群不断的进行分类,采用大病毒和小病毒分别对其进行感染操作,加强算法的搜索精度。文末以大连国贸大厦为例,进行了参数敏感性分析以及传感器优化布置方案的选择,结果表明,病毒猴群算法的搜索效率较原猴群算法有了大幅提高,能较好地解决传感器优化布置问题。The virus m algorithm（VMA）for optimal sensor placement（OSP）is proposed by introducing the virus infections mechanism into the m algorithm（MA）.The dual-structure coding method is used to overcome that the original MA can only solve the optimization of continuous variables.The m is infected by the introduced biological virus mechanism,then to realize the exchange of information between the m individuals vertically and horizontally by the collaboration of viruses and m,so as to maintain the diversity of individuals,which can greatly improve the capability of local search.Furthermore,the m should be continuously classified and infected by the big virus and small virus,which can enhance the search accuracy.Finally,the parametric sensitivity analysis and OSP is done on the Dalian international trade mansion.The results show that the search efficiency of the VMA greatly increases compared with the original MA,which can better solve the OSP problem.

关 键 词：传感器优化布置 猴群算法 病毒感染机制 大连国贸大厦 

分 类 号：TU973.23[建筑科学—结构工程] O329[理学—一般力学与力学基础]