免疫粒子群算法在混流装配线排序中的应用  

An Immunity Particle Swarm Sequencing Algorithm for Mixed-model Assembly Lines

作　　者：郑永前[1] 王永生[1] 

机构地区：[1]同济大学机械工程学院工业工程系,上海200092

出　　处：《工业工程与管理》2011年第4期16-20,27,共6页Industrial Engineering and Management

基　　金：上海市自然科学基金资助项目(10ZR1431700);"863"高技术研究发展计划资助项目(2008AA04Z105)

摘　　要：混流装配线上的产品投产排序是影响装配线生产效率的重要因素。建立以最小化装配线总闲置-超载成本为优化目标的装配线排序模型,采用粒子群算法来解决混流装配线的投产排序问题。考虑到基本粒子群算法易陷入局部最优解的问题,引入免疫算法思想对其进行改进,根据抗体亲和性与浓度值的计算,及时进行粒子的替换以维持种群的多样性,防止粒子过早收敛于局部极值。利用某汽车零部件制造企业装配线的数据进行试验计算,并与其他方法相比较,仿真结果说明该方法可以有效、快速地解决装配线排序问题。Mixed-model assembly line sequencing problem is crucial for the line efficiency.A sequencing model was built on the basis of minimizing the total cost of idletime and overtime.Particle Swarm Optimization algorithm was applied to optimize the subject.The immunity was used to optimize traditional algorithm to avoid the early convergence of particles.The particle was replaced in time to keep the diversity according to the particle affinity and consistency and avoid sinking into local optimum.An instance was optimized by PSO and Immunity PSO respectively,and the results showed that the algorithm is an effective method for sequencing problem of mixed-model assembly lines.

关 键 词：混流装配线 投产排序 粒子群算法 免疫 

分 类 号：F224[经济管理—国民经济]