摘要
教与学优化算法(teaching-learning-based optimization,TLBO)是一种模仿教学过程的新型启发式优化算法。针对TLBO算法寻优精度低、稳定性差的特点,提出了基于讨论组和自主学习的教与学优化算法DSTLBO(discussion group and self-learning TLBO)。在原TLBO算法的"教"阶段当中加入了小组讨论,随机将全体同学分成若干组,通过组内学生向本组中学习最好的组长学习,提高了算法的局部开发和寻优能力;组长受老师和组内同学影响进行变异,提高了算法的探索能力;在"教""学"阶段后,每个学生进入自我学习阶段,从而提高了算法的全局搜索能力。通过对八个复杂的Benchmark函数的测试表明:DSTLBO算法与基本TLBO算法和其经典改进算法ETLBO算法相比,在寻优精度、稳定性和收敛速度方面更具优势。
TLBO is a new heuristic optimization algorithm that imitates the teaching process.Aiming at the low precision and poor stability of TLBO algorithm,this paper proposed an improved teaching-learning-based optimization algorithm named DSTLBO TLBO based on discussion group and autonomous learning.In the process of teaching,it added the group discussion mechanism into the TLBO,and divided randomly all the students into several groups.The students in the group learned from the group monitor,and then which improved the local search ability of the algorithm.And the mutation of the group monitors enhanced the ability to explore the algorithm.After the“teaching”and“learning”phases,all students got into the self-learning which improved the global optimization ability of the algorithm.Finally,it used 8 complex benchmark functions to test the algorithm and compared the performance of the algorithms.The resualt showes that DSTLBO algorithm has advantages over TLBO and ETLBO in optimizing precision,stability and convergence speed.
作者
吴聪聪
贺毅朝
陈嶷瑛
张祖斌
刘雪静
Wu Congcong;He Yichao;Chen Yiying;Zhang Zubin;Liu Xuejing(College of Information Engineering,Hebei GEO University,Shijiazhuang 050031,China;College of Computer Science,Sichuan University,Chengdu 610065,China)
出处
《计算机应用研究》
CSCD
北大核心
2018年第5期1386-1389,1407,共5页
Application Research of Computers
基金
河北省高等学校科学研究计划资助项目(ZD2016005)
河北省自然科学基金资助项目(F2016403055)
关键词
教与学优化算法
讨论组
自主学习
变异
teaching-learning-based optimization algorithms
discussion group
self-learning
mutation
