摘要
为有效搜寻坠毁航空器及失联飞行员,本文提出一种过渡粒子群算法,为搜寻设施制订高质量的搜寻计划。针对搜寻区域范围较大,过渡粒子群算法首先对解空间进行有效的全局搜索。其在构建记忆库的基础上通过学习、随机生成的方式生成初始解。为保证备选解的多样性,将解空间分割为多个网格,每个网格至多有一个备选解保存在记忆库中。当记忆库中备选解所在网格不再发生变化时,利用粒子群策略对解空间进行有效的局部搜索,种群中的个体通过信息交换在解空间中展开搜索。试验结果表明,相较其余几种启发式算法,过渡粒子群算法可制订具有更高任务成功率的搜寻计划。
In order to search crashed aircraft and lost pilots effectively, a transition particle swarm optimization algorithm(TPSO) is proposed to make high quality search plans for search units. Considering that the search area is large, TPSO makes an effective global search at first. It constructs a memory bank and generates new candidate solutions based on memory consideration and random selection. In order to ensure the good diversity of candidate solutions, the solution space is segmented into multi lattices, and for each lattice there is one solution stored in the memory bank at most. When the memory bank is stable, effective local search is made by making use of particles swarm optimization strategy, and particles exchange information to search the solution space. The experimental results show that compared with other heuristic algorithms, TPSO can generate better search plans with higher possibility of success.
作者
吕进锋
贾晓洪
王明昌
Lyu Jinfeng;Jia Xiaohong;Wang Mingchang(Henan University of Science and Technology,Luoyang 471000,China;China Airborne Missle Academay,Luoyang 471009,China;Aviation Key Laboratory of Science and Technology on Airborne Guided Weapons,Luoyang 471009,China)
出处
《航空科学技术》
2020年第10期69-74,共6页
Aeronautical Science & Technology
关键词
搜寻计划
粒子群
记忆库
全局搜索
局部搜索
search plan
particle swarm
memory bank
global search
local search
