论文部分内容阅读
针对粒子群优化算法(PSO)在优化多维问题时容易陷入局部最优的问题,提高其全局搜索能力和拓展能力,提出了一种基于和声搜索的动态交叉粒子群算法.引入动态交叉操作,使得粒子在更新速度时实现共享有效信息,保证粒子进化过程中的种群多样性,提高全局搜索能力.结合和声搜索(HS)的随机搜索能力提出了HS-DCPSO,利用和声搜索的自适应调整参数音符调节概率PAR和间隔调整带宽bw来提高粒子群的拓展能力.通过多个基准函数对所提出的HS-DCPSO算法进行仿真测试,并与HS、PSO及多种改进的粒子群算法对比,验证所提出的HS-DCPSO算法具有较强的全局搜索能力和局部拓展能力,并且算法时间复杂度相比传统PSO增加不明显.
To solve the problem of Particle Swarm Optimization (PSO), which is easy to fall into the local optimum when it is used to optimize multi-dimensional problems, and to improve its global search ability and expandability, a dynamic crossover particle swarm optimization algorithm based on harmony search is proposed. So that particles can share valid information at the time of updating, to ensure the population diversity during particle evolution and to improve the global search ability.According to the random search ability of harmony search (HS), HS-DCPSO is proposed, which uses adaptive search of harmony Adjust the parameters of note tuning probability PAR and interval adjusting bandwidth bw to improve the ability of particle swarm expansion.The proposed HS-DCPSO algorithm is simulated by multiple benchmark functions and compared with HS, PSO and many improved particle swarm optimization algorithms , Verify that the proposed HS-DCPSO algorithm has strong global search capability and local expansion capability, and the algorithm time complexity is not obvious compared with the traditional PSO increase.