CAJ | 학술논문

各种智能优化算法由于进化原理不同,优化性能各异,将不同种类的智能优化算法混合起来,往往能够取长补短,互相促进,提高混合算法的优化性能。利用粒子群优化(PSO)算法的快速收敛特性和混合蛙跳算法(SFLA)突出的全局协同搜索能力,提出了一种PSO-SFLA混合优化算法。该混合算法在执行过程中将种群分为2个子群体,一个子群体采用PSO算法进化寻优,另一个子群体采用改进的SFLA进化寻优,2个子群体共享整个种群极值信息。通过对3个标准函数进行实验并与基本PSO算法进行比较,实验结果表明混合算法获得了更好的解,具有更好的优化性能。
각충지능우화산법유우진화원리불동,우화성능각이,장불동충류적지능우화산법혼합기래,왕왕능구취장보단,호상촉진,제고혼합산법적우화성능。이용입자군우화(PSO)산법적쾌속수렴특성화혼합와도산법(SFLA)돌출적전국협동수색능력,제출료일충PSO-SFLA혼합우화산법。해혼합산법재집행과정중장충군분위2개자군체,일개자군체채용PSO산법진화심우,령일개자군체채용개진적SFLA진화심우,2개자군체공향정개충군겁치신식。통과대3개표준함수진행실험병여기본PSO산법진행비교,실험결과표명혼합산법획득료경호적해,구유경호적우화성능。
All kinds of intelligent optimization algorithm show different optimized performance because of different evolution principle. To mix different kinds of intelligent optimized algorithm can complement and promote each othera,and improve the optimization perform-ance of hybrid algorithm. A hybrid algorithm combined Particle Swarm Optimization ( PSO) and Shuffled Frog Leaping Algorithm ( SF-LA) is proposed by using the rapid convergence properties of PSO algorithm and the outstanding global cooperative search ability of SF-LA. The algorithm divides the swarm into two sub-groups. In each iteration,one sub-group evolves using PSO algorithm,the other sub-group evolves using SFLA,and two algorithms share the information of groups extremum. The algorithm is experimented for three stand-ard functions and compared with basic PSO algorithm,results show that PSO-SFLA hybrid algorithm outperforms PSO algorithm.