自适应高斯变异花授粉算法  

Adaptive Gaussian Mutation Flower Pollination Algorithm

作　　者：李文超 贺兴时[1] 贺飞跃[1] 杨新社[2] LI Wenchao;HE Xingshi;HE Feiyue;YANG Xinshe(School of Science,Xi’an Polytechnic University,Xi’an 710048,China;School of Science and Technology,Middlesex University,London NW44BT,UK)

机构地区：[1]西安工程大学理学院,西安710048 [2]密德萨斯大学科学与技术学院,英国伦敦NM44BT

出　　处：《河南科学》2022年第5期689-700,共12页Henan Science

基　　金：国家自然科学基金(12001417);陕西省科技厅软件科学(2019KRM072)。

摘　　要：花朵授粉算法(Flower Pollination Algorithm,FPA)是一种新颖的智能优化算法,广泛应用于解决复杂工程优化和多目标优化问题.针对该算法收敛精度低、速度慢和维数敏感等问题,通过引入佳点集理论初始化种群,使用自适应转化概率调整自花授粉与异花授粉,提出一种自适应高斯变异花授粉算法.对11个测试函数进行仿真,结果表明:改进算法有较高的收敛精度和收敛速度,并改善了基本花授粉算法对维数敏感问题.The flower pollination algorithm,a novel intelligent optimization algorithm,is commonly used to solve the problems of complex engineering optimization and multi-objective optimization.Aiming at the flaws of low convergence precision,slow speed,and dimension sensitivity of the algorithm,an adaptive Gaussian mutation flower pollination algorithm is proposed by introducing the good point set theory to initialize the population and adjusting the balance between the self-pollination and cross-pollination with adaptive transformation probability.The simulation results of 11 test functions show that the improved algorithm has superior convergence precision and convergence speed,and improves the dimension sensitivity of the traditional flower pollination algorithm.

关 键 词：佳点集 自适应转化概率 高斯变异 收敛精度 

分 类 号：O242.1[理学—计算数学]