跳跃海豚群算法

Jumping dolphin swarm algorithm

中文关键词  海豚群算法  函数优化  长度自适应策略  跳跃步骤  早熟收敛机制

英文关键词  dolphin swarm algorithm  function optimization  length adaptive strategy  jumping steps  premature convergence mechanism

中文摘要

      针对海豚群算法收敛速度慢、容易陷入局部最优等缺陷, 提出一种跳跃海豚群算法. 在搜寻阶段, 考虑进化时期对算法的影响, 对固定长度的声波参数实施自适应操作, 平衡算法的全局搜索和局部开发能力; 为加快算法的收敛速度, 在搜寻阶段之后加入跳跃步骤, 使个体直接跳到邻域最优解; 改进了捕猎阶段位置更新方式, 并加入变异扰动因子, 加快算法收敛速度的同时维持了种群的多样性; 为避免算法陷入局部最优, 在捕猎阶段后加入早熟收敛机制. 与6种进化算法在16个标准测试函数上进行测试, 结果表明, 本文算法较其他算法在收敛速度、收敛精度以及鲁棒性上优势明显.

英文摘要

      Jumping?Dolphin?Swarm?Algorithm(JDSA)?is?proposed?in?this?paper?to?improve?the?convergence?speed?of?Dolphin?Swarm?Algorithm(DSA)?and?prevent?it?from?falling?into?local?optimum.? Considering?the?influence?produced?by?different?periods?during?the?evolutionary?process,?adaptive?operations?are?added?to?fixed?length?acoustic?wave?parameters?in?the?search?phase,?which?balances?the?capabilities?of?global?search?and?local?development.The?jump?step?makes?the?individuals?jump?to?the?neighborhood?optimal?solution?directly?after?the?search?phase,?which?accelerates?the?convergence?speed?of?DSA.Besides,?the?updated?method?in?the?predation?stage?is?improved?and?the?variation?perturbation?factor?is?added?into?the?predation?stage,?which?improve?the?convergence?speed?as?well?as?maintain?the?diversity?of?the?population.In?order?to?prevent?the?algorithm?from?falling?into?local?optimum,?prematurity?convergence?mechanism?is?adopted?after?predation?stage.Compared?with?6?evolutionary?algorithms?on?19?standard?test?functions,?the?experimental?results?show?that?the?proposed?algorithm?has?obvious?advantages?on?convergence?speed,?convergence?accuracy?and?robustness.