花授粉算法的改进及在压力容器设计中的应用

发布时间：2017-12-26 23:15

本文关键词：花授粉算法的改进及在压力容器设计中的应用　出处：《计算机工程与应用》2017年13期 　论文类型：期刊论文

【摘要】：虽然花授粉算法对于求解优化问题十分有效,但也存在收敛性慢的问题。为了解决此问题,提出一种带有时变因子的差分进化花授粉算法(Differential Evolution Flower Pollination Algorithm with Time Variant Factor,TVDFPA)。对步长因子进行改进,同时在迭代过程中加入差分进化的策略,通过种群杂交,提高算法的收敛速度和寻优能力。通过标准测试函数进行测试,仿真结果表明TVDFPA的收敛速度比原始花授粉算法、混沌和声的花授粉(HFPCHS)、模拟退火花授粉算法(SFPA)快,收敛精度也有较大提高。进而结合花授粉算法的特点,建立带有变参数的双适应值比较法来求解压力容器设计问题,实验结果表明改进之后的算法具有较好的求解性能。
[Abstract]:Although the pollination algorithm is very effective for solving the optimization problem, there is also a slow convergence problem. To solve this problem, a Differential Evolution Flower Pollination Algorithm with Time Variant Factor (TVDFPA) with time varying factor is proposed. The step size factor is improved, and the differential evolution strategy is added to the iterative process, and the convergence speed and optimization ability of the algorithm are improved through the population hybridization. Through the test of standard test function, the simulation results show that the convergence speed of TVDFPA is faster than that of primordial pollination algorithm, chaotic harmonic flower pollination (HFPCHS) and simulated spark discharge pollination algorithm (SFPA), and the convergence accuracy is also greatly improved. Based on the characteristics of flower pollination algorithm, a dual fitness comparison method with variable parameters is established to solve the design problem of pressure vessels. Experimental results show that the improved algorithm has better solution performance.
【作者单位】：西安工程大学理学院;密德萨斯大学科学与技术学院;
【基金】：陕西省自然科学基础研究计划项目(No.JM1006) 陕西省自然软科学研究计划项目(No.2014KRM2801) 陕西省教育厅专项科研计划项目(No.14JK1282)
【分类号】：TH49;TP18
【正文快照】： 1引言2012年,Yang通过模拟自然界中显花植物花朵授粉的过程提出花授粉算法[1](Flower Pollination Algorithm,FPA)。花授粉算法具有需调整的参数少,操作简单,易实现等优点,同时利用转换概率参数p控制全局搜索和局部搜索,较好地解决了全局搜索和局部搜索的平衡问题[2]。花授粉

【参考文献】