智能系统学报
智能繫統學報
지능계통학보
CAAI TRANSACTIONS ON INTELLIGENT SYSTEMS
2015年
1期
131-137
,共7页
差分算法%优化%自适应%逆向学习%收敛速度%精度%高维%初始化
差分算法%優化%自適應%逆嚮學習%收斂速度%精度%高維%初始化
차분산법%우화%자괄응%역향학습%수렴속도%정도%고유%초시화
differential evolution%optimization%generalized opposition-based learning%convergencespeed%accuracy%highdimension%initialization
针对差分算法（ differential evolution ， DE）在解决高维优化问题时参数设置复杂、选择变异策略困难的现象，提出了广义逆向学习方法的自适应差分进化算法（ self-adaptive DE algorithm via generalized opposition-based learning ， SDE-GOBL）。利用广义的逆向学习方法（ generalized opposition-based learning ， GOBL）来进行多策略自适应差分算法（ Self-adaptive DE， SaDE）的初始化策略调整，求出各个候选解的相应逆向点，并在候选解和其逆向点中选择所需要的最优初始种群，然后再进行自适应变异、杂交、选择操作，最后通过CEC2005国际竞赛所提供的9个标准测试函数对SDE-GOBL算法进行验证，结果证明该算法具有较快的收敛速度和较高的求解精度。
針對差分算法（ differential evolution ， DE）在解決高維優化問題時參數設置複雜、選擇變異策略睏難的現象，提齣瞭廣義逆嚮學習方法的自適應差分進化算法（ self-adaptive DE algorithm via generalized opposition-based learning ， SDE-GOBL）。利用廣義的逆嚮學習方法（ generalized opposition-based learning ， GOBL）來進行多策略自適應差分算法（ Self-adaptive DE， SaDE）的初始化策略調整，求齣各箇候選解的相應逆嚮點，併在候選解和其逆嚮點中選擇所需要的最優初始種群，然後再進行自適應變異、雜交、選擇操作，最後通過CEC2005國際競賽所提供的9箇標準測試函數對SDE-GOBL算法進行驗證，結果證明該算法具有較快的收斂速度和較高的求解精度。
침대차분산법（ differential evolution ， DE）재해결고유우화문제시삼수설치복잡、선택변이책략곤난적현상，제출료엄의역향학습방법적자괄응차분진화산법（ self-adaptive DE algorithm via generalized opposition-based learning ， SDE-GOBL）。이용엄의적역향학습방법（ generalized opposition-based learning ， GOBL）래진행다책략자괄응차분산법（ Self-adaptive DE， SaDE）적초시화책략조정，구출각개후선해적상응역향점，병재후선해화기역향점중선택소수요적최우초시충군，연후재진행자괄응변이、잡교、선택조작，최후통과CEC2005국제경새소제공적9개표준측시함수대SDE-GOBL산법진행험증，결과증명해산법구유교쾌적수렴속도화교고적구해정도。
The problem related to defects of complex parameter setting and difficult selection of mutation strategies existing in the differential evolution ( DE) algorithm when solving high-dimensional optimization problem is studied . This paper proposed a new self-adaptive DE algorithm based on generalized opposition-based learning ( SDE-GOBL).The generalized opposition-based learning (GOBL) is utilized for the adjustment of initiation strategy on multi-strategy self-adaptive DE (SaDE) algorithm.The corresponding reverse points of each candidate solution are figured out .In addition , the necessary optimal initial population is selected among the candidate solutions and its reverse points.Next, the self-adaptive mutation, hybridization and selection operations are conducted .Finally, nine standard test functions provided in CEC 2005 International Competition are applied for demonstrating SDE-GOBL al-gorithm.The result showed that the algorithm has fast convergence speed and high solution precision .
