带免疫机制的蚁群算法求解几何约束多解  

Combining Immune with Ant Colony Algorithm for Geometric Constraint Multi-Solution Problem

作　　者：赵空[1,2] 袁华[3] 常欣[3] 李文辉[2] 

机构地区：[1]苏州工业园区工业技术学校,江苏苏州215123 [2]吉林大学计算机科学与技术学院,吉林长春130012 [3]长春工业大学计算机科学与工程学院,吉林长春130012

出　　处：《江南大学学报（自然科学版）》2009年第6期649-652,共4页Joural of Jiangnan University (Natural Science Edition)　

基　　金：国家自然科学基金项目(60573182;60873147);教育部高等学校博士点基金项目(20060183042)

摘　　要：针对蚁群优化算法易于陷入早熟收敛和局部求精能力不足的缺点,从人工免疫系统的基本原理出发,设计具有免疫能力的蚂蚁抗体来保持蚁群的多样性,使算法在迭代的后期依然保持进化能力,提高算法的局部求精能力,使蚁群优化算法在局部开采和全局探索间取得更好的平衡。算法具有良好的优化性能和时间性能。The constraint multi-solutions problem can be transformed to an optimization problem. It is proposed to introduce IACOA （Immune Ant Colony Optimization Algorithm） in finding optimal solution. The solution for preventing ACO from premature convergence and improving the precision of local optimization algorithm is to develop ant operators with immunity based on the basic Principles of artificial immune systems. The immune ant operators will create better balance between exploration and exploitation by keeping the diversity of ant colony, maintaining the intensification in the later iteration phase, and improving the precision of local optimization algorithm. The algorithm has good effect in optimization capability and time capability.

关 键 词：几何约束求解 蚂蚁算法 免疫算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]