贾豫葛, 聂茹, 李小凡. Application of Immune Particle Swarm Optimization to Wave Impedance Inversion Problem[J]. 2011, 31(3): 304-310. DOI: 10.13409/j.cnki.jdpme.2011.03.019.
Application of Immune Particle Swarm Optimization to Wave Impedance Inversion Problem
摘要
针对标准粒子群优化(PSO)算法易出现早熟而陷入局部最优以及进化后期收敛速度慢等缺陷
引入免疫系统的免疫记忆和抗体浓度选择机制
构造了基于免疫机制的粒子群优化(IPSO)算法
并将其应用到波阻抗反演问题中。免疫记忆能够保留高适应度个体
抗体浓度选择机制进一步保证了粒子的多样性
从而能较好地避免早熟收敛
提高算法的全局搜索能力。对理论模型试算表明
IPSO算法在进行波阻抗反演时不仅收敛速度快
而且具有较高的精确度和抗噪性能。
Abstract
In the standard particle swarm optimization(PSO)
the premature convergence of particles and slow convergence in the late process decrease the searching ability of the algorithm.By introducing the immune memory idea and the selection strategy based on antibody density
the immunity based PSO(IPSO) algorithm is proposed and is applied to the wave impedance inversion problem.The immune memory idea can reserve particles with full fitness and the selection strategy based on antibody density can maintain the particles diversity
so the defect of premature convergence can be avoided and the global searching ability can be improved.Simulation for wave impedance inversion indicates that IPSO has better efficiency and higher accuracy.