基于多互动的精英智能优化算法
|
摘要
教与学优化(teaching-learning-based optimization,TLBO)算法是一种模拟现实生活中教师与学生之间的教学过程的新型启发式优化算法,针对基本TLBO算法寻优精度低、稳定性差的问题,给出一种"因材施教"和"多学习"精英教与学优化算法.在基本TLBO算法的基础上,采用保留班级精英学员策略的方法加强算法的收敛能力,在教学阶段实行"因材施教"教学过程,使教学过程更符合实际、每个学员都受益、更具有针对性、保证班级学员的多样性,在学习阶段实行"多学习"学习过程,学员随意互动交流学习,提高算法的搜索能力.对6个标准函数的测试结果表明,ETLBO-AM算法与其他算法相比在寻优精度和稳定性上更有优势,可以取得满意的结果.
Teaching-learning-based optimization( TLBO) is a novel heuristic optimization algorithm based on the simulation of the teaching-learning process between teachers and students in real life. We propose a teaching students in accordance with their aptitude and multi-learning teaching-learning-based optimization( ETLBO-AM) to solve the problem of low precision and poor stability of TLBO. Based on TLBO,a strategy of keeping the class elite is introduced to strengthen the convergence ability of the algorithm. Teaching students in accordance with their aptitude is introduced to make the teaching process more practical and every student benefited,make more pertinent and ensure the diversity of students. Multi-learning process is introduced at the learner phase so that students can interact and exchange at will and improve the searching ability of the algorithm. Six standard function tests show that ETLBO-AM algorithm outperforms the other algorithm in precision and stability and obtains satisfactory results.
Teaching-learning-based optimization( TLBO) is a novel heuristic optimization algorithm based on the simulation of the teaching-learning process between teachers and students in real life. We propose a teaching students in accordance with their aptitude and multi-learning teaching-learning-based optimization( ETLBO-AM) to solve the problem of low precision and poor stability of TLBO. Based on TLBO,a strategy of keeping the class elite is introduced to strengthen the convergence ability of the algorithm. Teaching students in accordance with their aptitude is introduced to make the teaching process more practical and every student benefited,make more pertinent and ensure the diversity of students. Multi-learning process is introduced at the learner phase so that students can interact and exchange at will and improve the searching ability of the algorithm. Six standard function tests show that ETLBO-AM algorithm outperforms the other algorithm in precision and stability and obtains satisfactory results.
引文
[1]Holland J H.Adaptation in Natural and Artificial Systems[M].Ann Arbo:University of Michigan Press,1975:1-53.
[2]Kennedy J,Eberhart R C.Particle swarm optimization.In:Proceedings of IEEE International Conference on Neural Networks[M].Perth:IEEE,1995:1942-1948.
[3]Stom R,Price K.Differential evolution:a simple and efficient heuristic for global optimization over continuous spaces[J].Journal of Global Optimization,1997,11(4):341-359.
[4]刘俊梅,马永刚,高岳林.求解约束优化问题的动态目标迁移差分进化算法[J].武汉理工大学学报(交通科学与工程版),2012,36(5):1083-1086.
[5]刘俊梅,高岳林.一种带有随机变异的动态差分进化算法[J].计算机应用,2009,29(10):2719-2722.
[6]刘俊梅,高岳林.非线性混合整数规划问题的改进差分进化算法[J].工程数学学报,2010,27(6):967-974.
[7]Colomi A,Dorigo M,Maniezzo V.An investigation of some properties of an ant algorithm[A].Proc of the Parallel Problem Solving from Nature Conference(PPS N’92)[C].Brussels:Elsevier Publishing,1992:509-520.
[8]Geem Z W,Kim J H,Loganathan G V.A new heuristic optimization algorithm:harmony search[J].Simulation,2001,76(2):60-70.
[9]Karaboga D.An idea based on honey bee swarm for nume-rical optimization,TR06[R].Kayseri:Erciyes Univ ersity,2005.
[10]Eusuff M,Lansey E.Optimization of water distribution network design using the shuffled frog leaping algorithm[J].Journal of Wate Resources Planning and Management,2003,129(3):210-225.
[11]Raor V,Savsaniv J,Vakharia D P.Teaching-learning based optimization:a novel method for constrained mechanical design optimization problems[J].Computer Aided Design,2011,43(3):303-315.
[12]Raor V,Patel V.An elitist teaching-learning based optimiz-ation algorithm for solving complex constrained optimization problems[J].International Journal of Industrial Engineering Computations,2012,3(4):535-560.
[13]于坤杰,王昕,王振雷.基于反馈的精英教学优化算法[J].自动化学报,2014,40(9):1976-1983.
[14]李志南,南新元,李娜,等.多学习教与学优化算法[J].计算机应用与软件,2016,33(2):246-250.
[15]拓守恒,雍龙泉,邓方安.“教与学”优化算法研究综述[J].计算机应用研究,2013,30(7):1933-1938.
[2]Kennedy J,Eberhart R C.Particle swarm optimization.In:Proceedings of IEEE International Conference on Neural Networks[M].Perth:IEEE,1995:1942-1948.
[3]Stom R,Price K.Differential evolution:a simple and efficient heuristic for global optimization over continuous spaces[J].Journal of Global Optimization,1997,11(4):341-359.
[4]刘俊梅,马永刚,高岳林.求解约束优化问题的动态目标迁移差分进化算法[J].武汉理工大学学报(交通科学与工程版),2012,36(5):1083-1086.
[5]刘俊梅,高岳林.一种带有随机变异的动态差分进化算法[J].计算机应用,2009,29(10):2719-2722.
[6]刘俊梅,高岳林.非线性混合整数规划问题的改进差分进化算法[J].工程数学学报,2010,27(6):967-974.
[7]Colomi A,Dorigo M,Maniezzo V.An investigation of some properties of an ant algorithm[A].Proc of the Parallel Problem Solving from Nature Conference(PPS N’92)[C].Brussels:Elsevier Publishing,1992:509-520.
[8]Geem Z W,Kim J H,Loganathan G V.A new heuristic optimization algorithm:harmony search[J].Simulation,2001,76(2):60-70.
[9]Karaboga D.An idea based on honey bee swarm for nume-rical optimization,TR06[R].Kayseri:Erciyes Univ ersity,2005.
[10]Eusuff M,Lansey E.Optimization of water distribution network design using the shuffled frog leaping algorithm[J].Journal of Wate Resources Planning and Management,2003,129(3):210-225.
[11]Raor V,Savsaniv J,Vakharia D P.Teaching-learning based optimization:a novel method for constrained mechanical design optimization problems[J].Computer Aided Design,2011,43(3):303-315.
[12]Raor V,Patel V.An elitist teaching-learning based optimiz-ation algorithm for solving complex constrained optimization problems[J].International Journal of Industrial Engineering Computations,2012,3(4):535-560.
[13]于坤杰,王昕,王振雷.基于反馈的精英教学优化算法[J].自动化学报,2014,40(9):1976-1983.
[14]李志南,南新元,李娜,等.多学习教与学优化算法[J].计算机应用与软件,2016,33(2):246-250.
[15]拓守恒,雍龙泉,邓方安.“教与学”优化算法研究综述[J].计算机应用研究,2013,30(7):1933-1938.