免疫粒子群优化在波阻抗反演中的应用  

Application of Immune Particle Swarm Optimization to Wave Impedance Inversion Problem

作　　者：贾豫葛[1] 聂茹[2] 李小凡[3] 

机构地区：[1]中国矿业大学资源与地球科学学院,江苏徐州221008 [2]中国矿业大学计算机科学与技术学院,江苏徐州221008 [3]中国科学院地质与地球物理研究所,北京100029

出　　处：《防灾减灾工程学报》2011年第3期304-310,共7页Journal of Disaster Prevention and Mitigation Engineering

基　　金：国家自然科学基金重点项目(40437018)资助

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。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.

关 键 词：免疫粒子群 免疫记忆 浓度选择 波阻抗反演 

分 类 号：P315.3[天文地球—地震学]