新搜索策略的花授粉算法  

Flower pollination algorithm with new search strategies

作　　者：肖辉辉 段艳明 林芳 Xiao Huihui;Duan Yanming;Lin Fang(College of Computer and Information Engineering,Hechi University,Yizhou 546300,China)

机构地区：[1]河池学院计算机与信息工程学院

出　　处：《电子测量与仪器学报》2019年第7期11-20,共10页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(61173146,61562032);基础能力提升项目(2018KY0496);河池学院2019年高层次人才科研启动费项目资助

摘　　要：针对花授粉算法(FPA)的全局授粉和局部授粉存在的缺点而导致花授粉算法局部开发能力差、求解精度低及收敛速度慢等问题,提出一种新搜索策略的FPA。该算法把全局领域搜索策略融入到花授粉算法中,以提高FPA的探测能力;运用带惯性权重的三角变异和精英变异策略对其局部授粉进行重构,以提升FPA的探索能力和加快算法收敛速度。此外,为了减轻种群个体演化的随意性,提高FPA的优化精度和速度,运用精英个体机制来引导种群其他个体的演化方向。通过对13个经典测试函数的求解结果表明,新算法与标准花授粉算法和其他改进花授粉算法相比,其优化能力至少提升了20.08%,显示出其良好的竞争力。同时,利用新算法对无人作战飞行器航线规划问题进行求解,实验结果表明,其用于解决实际工程问题是可行的,且与对比算法相比,其优化能力也具有一定的优势。In order to solve the problem that the shortcomings of global pollination and local pollination of the flower pollination algorithm(FPA)cause flower pollination algorithm’s poor partial development ability,low solving precision,and slow convergence,a flower pollination algorithm with new search strategies is presented in this paper.the global neighborhood search strategy is integrated into the flower pollination algorithm to improve the detection capability of FPA,a new local pollination based on the triangle variation with inertia weight and elitist mutation strategy is reconstructed to improve the exploratory ability of FPA and accelerate the convergence rate of the algorithm.In addition,in order to reduce the randomness of individual evolution and improve the optimization accuracy and speed of FPA,elite individual mechanism is used to guide the evolution direction of other individuals in the population.The results of solving 13 classical test functions show that the optimization ability of the new algorithm is improved by at least 20.08%compared with the standard flower pollination algorithm and other improved flower pollination algorithms,which shows good competitiveness.At the meanwhile,the new algorithm is used to solve the route planning problem of unmanned combat aircraft,the experimental results show that it is feasible to solve practical engineering problems,and its optimization ability also has certain advantages over the compared algorithms.

关 键 词：花授粉算法 三角变异 全局领域搜索 精英变异 无人作战飞行器 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]