一种改进的粒子群人工鱼群算法
|
摘要
针对人工鱼群算法在高维度求解中收敛速度慢且寻优结果有待于提高等问题,提出一种改进的粒子群人工鱼群算法(PSO-AFSA)。该算法基于精英策略改进,结合了人工鱼群算法(AFSA)的快速跳出局部极值的能力和粒子群算法(PSO)局部快速收敛的优点。此外,该算法将粒子的飞行速度和惯性权重属性与鱼群算法相结合。采用Matlab验证了PSO-AFSA算法在高维度寻优中比AFSA具有更快的收敛速度和更好的寻优结果。
The basic artificial fish swarm algorithm(AFSA) has a slow convergence rate and poor precision in the high-dimensional optimization. An algorithm called the particle swarm optimization-artificial fish swarm algorithm(PSO-AFSA) is proposed in the present paper. The PSO-AFSA is based on the elite strategy. It synthesizes the advantages of the convergent performance and the quick jump out of the local minima of the AFSA and the informational strategy and the quick local convergent performance of the particle swarm optimization algorithm(PSO). Furthermore, this algorithm inherits the velocity and inertia weight characteristics from the PSO. Through simulation, the PSO-AFSA has a faster convergence speed and a better precision than the AFSA, and has a stable performance in the high-dimensional optimization.
The basic artificial fish swarm algorithm(AFSA) has a slow convergence rate and poor precision in the high-dimensional optimization. An algorithm called the particle swarm optimization-artificial fish swarm algorithm(PSO-AFSA) is proposed in the present paper. The PSO-AFSA is based on the elite strategy. It synthesizes the advantages of the convergent performance and the quick jump out of the local minima of the AFSA and the informational strategy and the quick local convergent performance of the particle swarm optimization algorithm(PSO). Furthermore, this algorithm inherits the velocity and inertia weight characteristics from the PSO. Through simulation, the PSO-AFSA has a faster convergence speed and a better precision than the AFSA, and has a stable performance in the high-dimensional optimization.
引文
[1]李晓磊.一种新型的智能优化方法-人工鱼群算法[D].杭州:浙江大学,2003:22-40.
[2]姚正华.改进人工鱼群智能优化算法及其应用研究[D].徐州:中国矿业大学,2016:16-31.
[3]费腾,张立毅,陈雷.混合Levy变异与混沌变异的改进人工鱼群算法[J].计算机工程,2016,42(7):146-152,158.
[4]刘东林,李乐乐.一种新颖的改进人工鱼群算法[J].计算机科学,2017,44(4):281-287.
[5]KENNEDY J,EBERHART C.Particle swarm optimization[C]∥International Symposium on Neural Networks.Perth:IEEE,1995:1942-1948.
[6]SHI H,EBERHART R C.Fuzzy adaptive particle swarm optimization[C]∥Congress on Evolutionary Computation.South Korea:IEEE,2001,1(12):101-106.
[7]张强,李盼池.一种自适应多策略行为粒子群优化算法[EB/OL].(2018-08-16)[2018-10-18].https:∥doi.org/10.13195/j.kzyjc.2018.0240.
[8]蔡泽凡.仿生优化群算法及应用研究[D].广州:华南理工大学,2017:13-14.
[9]袁光辉,樊重俊,张惠珍,等.一种新的粒子群算法与人工鱼群算法的混合算法[J].上海理工大学学报,2014,36(3):223-226,238.
[10]梁毓明,裴兴环.粒子群优化人工鱼群算法[J].计算机仿真,2016,33(6):213-217,281.
[11]李君,梁昔明.对精英加速的改进人工鱼群算法[J].计算机应用研究,2018,35(7):1960-1964,1981.
[12]曲良东,何登旭,黄勇.一种新型的启发式人工鱼群算法[J].计算机工程,2011,37(17):140-142.
[13]LI H.Parameter optimization of lowest secondary crushing rate for coal auger based on artificial fish school algorithm[J].Journal of China Coal Society,2011,36(2):346-350.
[14]牛晋财,李茂青,张雁鹏.基于人工鱼群算法的列车运行调整方法研究[EB/OL].(2018-06-22)[2018-10-21].http:∥kns.cnki.net/kcms/detail/11.2127.TP.20180620.1631.022.html.
[15]张文辉,林子安,刘彤,等.基于改进人工鱼群算法的机器人路径规划[J].计算机仿真,2016,33(12):374-379,448.
[2]姚正华.改进人工鱼群智能优化算法及其应用研究[D].徐州:中国矿业大学,2016:16-31.
[3]费腾,张立毅,陈雷.混合Levy变异与混沌变异的改进人工鱼群算法[J].计算机工程,2016,42(7):146-152,158.
[4]刘东林,李乐乐.一种新颖的改进人工鱼群算法[J].计算机科学,2017,44(4):281-287.
[5]KENNEDY J,EBERHART C.Particle swarm optimization[C]∥International Symposium on Neural Networks.Perth:IEEE,1995:1942-1948.
[6]SHI H,EBERHART R C.Fuzzy adaptive particle swarm optimization[C]∥Congress on Evolutionary Computation.South Korea:IEEE,2001,1(12):101-106.
[7]张强,李盼池.一种自适应多策略行为粒子群优化算法[EB/OL].(2018-08-16)[2018-10-18].https:∥doi.org/10.13195/j.kzyjc.2018.0240.
[8]蔡泽凡.仿生优化群算法及应用研究[D].广州:华南理工大学,2017:13-14.
[9]袁光辉,樊重俊,张惠珍,等.一种新的粒子群算法与人工鱼群算法的混合算法[J].上海理工大学学报,2014,36(3):223-226,238.
[10]梁毓明,裴兴环.粒子群优化人工鱼群算法[J].计算机仿真,2016,33(6):213-217,281.
[11]李君,梁昔明.对精英加速的改进人工鱼群算法[J].计算机应用研究,2018,35(7):1960-1964,1981.
[12]曲良东,何登旭,黄勇.一种新型的启发式人工鱼群算法[J].计算机工程,2011,37(17):140-142.
[13]LI H.Parameter optimization of lowest secondary crushing rate for coal auger based on artificial fish school algorithm[J].Journal of China Coal Society,2011,36(2):346-350.
[14]牛晋财,李茂青,张雁鹏.基于人工鱼群算法的列车运行调整方法研究[EB/OL].(2018-06-22)[2018-10-21].http:∥kns.cnki.net/kcms/detail/11.2127.TP.20180620.1631.022.html.
[15]张文辉,林子安,刘彤,等.基于改进人工鱼群算法的机器人路径规划[J].计算机仿真,2016,33(12):374-379,448.