基于小生境猴群算法的传感器优化布置方法研究

发布时间：2018-10-14 14:39

【摘要】：将小生境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小生境猴群算法。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,并采用混沌搜索的方式产生初始猴群位置,使猴群均匀分布;将猴群分为多个小生境猴群系统,形成各自独立的搜索空间;基于共享适应度的方法对小生境猴群进行末尾淘汰,并随机初始化产生新的猴子,提高小生境猴群的多样性;利用各个小生境猴群的平均适应度替换机制使得优良猴子位置信息能够得到共享,提高算法的整体搜索性能和收敛效率。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,结果表明小生境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。
[Abstract]:The niche evolution theory is introduced into the monkey swarm algorithm, and a niche monkey swarm algorithm is proposed for the optimal placement of sensors. The dual coding method is used to overcome the defect that the original monkey swarm algorithm can only solve the optimization problem of continuous variables, and the initial monkey group position is generated by chaotic search method, and the monkey group is distributed evenly, and the monkey colony is divided into several niche monkey colony systems. To form their own independent search space, based on the method of shared fitness to eliminate the niche monkey group, and random initialization to create new monkeys, improve the diversity of niche monkeys; By using the average fitness substitution mechanism of each niche group, the good monkey location information can be shared, and the overall search performance and convergence efficiency of the algorithm can be improved. At the end of this paper, taking Dalian Guomao Tower as an example, the sensitivity analysis of parameters and the selection of optimal sensor layout scheme are carried out. The results show that the searching efficiency of the niche monkey swarm algorithm is much higher than that of the original monkey swarm algorithm. It can solve the problem of optimal sensor layout.
【作者单位】：大连理工大学建设工程学部土木工程学院;
【基金】：国家自然科学基金委创新研究群体基金项目(51121005) 国家自然科学基金优秀青年科学基金项目(51222806) 教育部新世纪优秀人才支持计划项目(NCET-10-0287)
【分类号】：TU311

【相似文献】