微电子学与计算机
微電子學與計算機
미전자학여계산궤
MICROELECTRONICS & COMPUTER
2013年
6期
126-130
,共5页
粒子群优化%量子优化%反向学习%函数优化
粒子群優化%量子優化%反嚮學習%函數優化
입자군우화%양자우화%반향학습%함수우화
particle swarm optimization%quantum optimization%opposition‐based learning%function optimization
为了克服标准粒子群算法容易陷入局部最优的缺点,结合量子优化和反向学习的思想,提出一种混合反向学习和量子优化的粒子群算法.该混合算法在种群初始化、种群的跳越和种群最优个体的局部改进三方面上提高了量子粒子群算法的性能,有效地避免粒子群陷入局部最优并加速种群收敛.数值实验表明,混合算法在不同的函数优化方面具有较高的性能.
為瞭剋服標準粒子群算法容易陷入跼部最優的缺點,結閤量子優化和反嚮學習的思想,提齣一種混閤反嚮學習和量子優化的粒子群算法.該混閤算法在種群初始化、種群的跳越和種群最優箇體的跼部改進三方麵上提高瞭量子粒子群算法的性能,有效地避免粒子群陷入跼部最優併加速種群收斂.數值實驗錶明,混閤算法在不同的函數優化方麵具有較高的性能.
위료극복표준입자군산법용역함입국부최우적결점,결합양자우화화반향학습적사상,제출일충혼합반향학습화양자우화적입자군산법.해혼합산법재충군초시화、충군적도월화충군최우개체적국부개진삼방면상제고료양자입자군산법적성능,유효지피면입자군함입국부최우병가속충군수렴.수치실험표명,혼합산법재불동적함수우화방면구유교고적성능.
@@@@In order to overcome the drawback of standard particle swarm algorithm which is easy to fall into local optimum ,an improved particle swarm optimization algorithm is proposed combined with quantum optimization and opposition‐based learning .There are three aspects that improve the quantum particle swarm algorithm performance :the initialization of population ,population jumps and the best individual in the population of the local improvement . The improved algorithm can effectively avoid particle swarm into local optimum and accelerated population to the optimal position of the convergence . The numerical experiments show that the hybrid algorithm has high performance in different function optimization