免疫粒子群优化算法及性能分析

Performance Analysis of Immune Particle Swarm Optimization Algorithm

针对基本粒子群算法的容易陷入局部极小值,搜索精度不高等缺点,将免疫算法和粒子群优化算法(Particle Swarm Optimization,PSO算法)相结合,并加以改进,利用免疫算法能够保持个体多样性的特点,可使粒子群优化算法。达到摆脱局部极值点能力,从而提高算法进化过程中的收敛精度和速度。使用四个经典的测试函数对其进行测试,试验结果显示改进效果良好。

Particle swarm optimization is easy to fall into the local minimum value and the search accuracy is not high. The immune algorithm and particle swarm optimization （Particle Swarm Optimization, PSO algorithm） are combined to make the improvement, the immune algorithm was used to maintain diversity of individuals characteristics, making the PSO algorithm achieve the ability to get rid of local extreme points, improving algorithm convergence precision and speed in the evolutionary process. And the four classical tests function was tested, test results show that the improvements has achieved good results.