一种含最优变异的多微粒群优化算法

针对微粒群优化算法中的固有缺点，提出了带有最优变异算子的多微粒群优化算法，采用多个微粒群对目标函数进行寻优，并在寻优过程中对子群中最优微粒引入了最优变异算子。通过这样的处理，算法可以预防早熟收敛并具有更快的收敛速度和更好的局部开发能力。对一组测试函数的模拟实验结果表明，带最优变异的多微粒群优化算法可以摆脱局部最优解时微粒的吸引，在较少的代数内就能够获得好的优化结果。

A multi-swarm particle swarm optimization algorithm characteristic of optimum mutation

With respect to the inherent deficiency in the particle swarm optimization algorithm, a novel multl-swarm particle swarm optimization algorithm with optimum mutation is presented in this paper. By applying the mutation operator to the best particle in the sub-warm, the objective function can be optimized by the algorithm, which can prevent premature convergence and has better convergence and local exploitation ability. Experiments are conducted on a set of benchmark functions and the results show that it can break away from the attraction of the local optimal solution and thus achieve excellent results in fewer generations.