| 基于同步扰动随机逼近的混合萤火虫算法 |
| |
| 作者姓名： | 李维刚 冯宁 刘超 刘翱 |
| |
| 作者单位： | 武汉科技大学信息科学与工程学院,湖北 武汉,430081;武汉科技大学冶金工业过程系统科学 湖北省重点实验室,湖北 武汉,430065,武汉科技大学信息科学与工程学院,湖北 武汉,430081,武汉科技大学信息科学与工程学院,湖北 武汉,430081,武汉科技大学冶金工业过程系统科学 湖北省重点实验室,湖北 武汉,430065;武汉科技大学管理学院,湖北 武汉,430081;武汉科技大学智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉,430065 |
| |
| 基金项目： | 湖北省教育厅科学技术研究计划重点项目(D20161103)；武汉科技大学冶金工业过程系统科学湖北省重点实验室开放基金资助项目(Z201501)；武汉科技大学智能信息处理与实时工业系统湖北省重点实验室开放基金面上项目(2016znss18B)；武汉科技大学青年科技晨光计划资助项目(2016070204010099). |
| |
| 摘 要： | 针对标准萤火虫算法(FA)中存在的种群过早收敛、容易陷入局部最优等不足,提出一种以memetic算法为框架、将同步扰动随机逼近和萤火虫算法相结合的混合算法(FA-SPSA),即首先使用萤火虫算法对种群进行全局寻优,然后使用同步扰动随机逼近算法对选出的部分最优个体进行局部搜索,从而增强萤火虫算法跳出局部最优解的能力。通过6个标准测试函数对FA-SPSA算法的性能进行检验,并与标准萤火虫算法、果蝇算法、改进的果蝇算法等其他4种算法进行比较,结果表明,FA-SPSA算法在寻优精度、收敛速度、鲁棒性等方面的性能总体上优于对比算法。
|
| 关 键 词： | 萤火虫算法 同步扰动随机逼近(SPSA) memetic算法 全局搜索 局部搜索 |
| 收稿时间： | 2016/3/30 0:00:00 |
Hybrid firefly algorithm based on simultaneous perturbation stochastic approximation |
| |
| Authors: | Li Weigang Feng Ning Liu Chao and Liu Ao |
| |
| Institution: | College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China;Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan University of Science and Technology, Wuhan 430065, China,College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China,College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China and Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan University of Science and Technology, Wuhan 430065, China;College of Management, Wuhan University of Science and Technology, Wuhan 430081, China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China |
| |
| Abstract: | To overcome such disadvantages as premature convergence and falling into local optimum easily in the basic firefly algorithm (FA), a hybrid algorithm named as FA-SPSA is presented,which introduces simultaneous perturbation stochastic approximation (SPSA) into FA under the frame of memetic algorithm. Firstly, FA is employed to search for global optimal solutions. Then SPSA is used in the local search aiming at the selected part of the best individuals, which enhances the ability of firefly algorithm to jump out of local optimum. The performances of FA-SPSA are testified by six benchmark functions and the calculation results are compared with those of basic firefly algorithm, fruit fly optimization and two improved fruit fly optimization algorithms, which indicates that FA-SPSA is generally superior to the other four algorithms in optimization accuracy, convergence speed and robustness. |
| |
| Keywords: | firefly algorithm SPSA memetic algorithm global search local search |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
