基于动态调整惯性权重的混合粒子群算法

摘要

When solving high dimensional nonlinear problems, Particle Swarm Optimization algorithm is easy to fall into local op-timal solution. In this case, a new nonlinear adaptive weight adjustment strategy based on Sigmod function is proposed. In addi-tion, a Latin Hypercube Sampling method is used to produce a homogeneous initial population, and a niche elimination strategy is used to enhance the global optimization ability of the algorithm. Finally, six standard test functions are used to test the perform-ance of the improved algorithm. The results show that the improved particle swarm optimization algorithm achieves satisfactory re-sults in convergence speed, convergence accuracy and the acquisition of global optimal solution.%标准粒子群算法(Particle Swarm Optimization,PSO)在求解高维非线性问题时容易陷入局部最优解,针对此种情况,提出一种基于Sigmod函数的新的非线性自适应权值调整策略.此外,选用拉丁超立方体抽样的方法产生均匀的初始种群,采用小生境淘汰策略增强算法全局寻优能力.最后选用6个标准测试函数对该改进算法进行性能测试.结果表明,改进的粒子群算法在收敛速度和收敛精度以及全局最优解的获取方面均取得了满意的效果.