Abstract: Clone selection and better diversity of immune learning is introduced into particle swarm optimization algorithm to construct an algorithm immune particle swarm optimization algorithm(IPSO). The modified algorithm can avoid the local optimization and has better performance for multi-peak function optimization problem. The algorithm is applied to four familiar test functions. Experimental results illustrate that the IPSO has the potential to achieve better and faster convergence.

Key words: particle swarm optimization algorithm(PSO), immune mechanism, clone selection, immune memory

摘要： 引入克隆选择操作和借鉴免疫学习中较好的多样性来克服微粒群算法易陷于局部最优以及对多峰值函数搜索效果不佳的缺点，构建了一种免疫微粒群算法。将该算法应用于4个常见的测试函数，实验结果表明，该算法比标准微粒群算法有更好的收敛性和更快的收敛速度。

关键词: 微粒群优化算法, 免疫机制, 克隆选择, 免疫记忆

CLC Number: 

• TP391.9