具有导向功能的改进烟花算法  

Improved firework algorithm with directional function

作　　者：陶小华 陈基漓[1] 谢晓兰[1] TAO Xiao-hua;CHEN Ji-li;XIE Xiao-lan(College of Information Science and Engineering,Guilin University of Technology,Guilin 541006,China)

机构地区：[1]桂林理工大学信息科学与工程学院

出　　处：《计算机工程与设计》2019年第12期3479-3486,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(61762031)

摘　　要：为消除烟花算法(firework algorithm,FWA)中爆炸半径对搜索范围的限制,增强各类搜索算子的导向性,提出具有导向功能的改进烟花算法(improved fwa with directional function,IdFWA)。充分利用当代最优个体的位置信息以及历代的全局最优解,设计两种具有导向功能的搜索算子。使用12个标准测试函数对增强型烟花算法EnFWA、自适应烟花算法AFWA、有导烟花算法GFWA和IdFWA进行对比测试,实验结果表明,改进后的烟花算法无论在单峰函数还是多峰函数上的收敛速度和求解精度皆优于其它3个算法。To eliminate the limitation of the radius of the explosion on the search radius and strengthen the directional ability when searching in different ranges,an improved firework algorithm with directional function was proposed.Two search methods with directional function were designed according to the information of the location of best seed and historical optimal solution.12 standard benchmark functions were used to test the solution accuracy and the convergence speed of enhanced firework algorithm,adaptive firework algorithm,guided firework algorithm and improved firework algorithm with directional function.Results show that the improved firework algorithm performs better than others in solution accuracy and convergence speed whether in handling uni modal function or multi model function.

关 键 词：增强型烟花算法 导向功能 自适应变异率 西格玛函数 自适应烟花算法 有导烟花算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]