针对粒子群优化(PSO)算法容易陷入局部极值的不足,引入免疫机制对PSO算法进行优化,实现全局搜索。通过免疫机制的应用,根据亲和度的高低进行粒子克隆、选择、淘汰和高频变异,增强了算法全局搜索的能力,提高了收敛速度和精度。实验表明,改进后的算法完成全局搜索所需的迭代次数明显少于PSO算法,具有优良的自适应调整性能。 In order to overcome the shortcomings of Particle Swarm Optimization (PSO) algorithm such as falling into local extremum easily, an immune mechanism is introduced to optimize the PSO algorithm and achieve global search. Through the application of immune mechanism, particle cloning, selection, elimination and high-frequency mutation are carried out according to the degree of affinity, which enhances the ability of global search algorithm and improves the convergence speed and accuracy. Experiments show that the number of iterations required by the improved algorithm to complete the global search is significantly less than that of the PSO algorithm, and has excellent adaptive adjustment performance.