摘要
用有向图模型描述零件之间的优先关系,构建了装配关系矩阵.基于该矩阵,将蚁群算法用于生成可行、优化的装配序列,并对算法进行了改造:设计了满足优先关系的“可行转移范围”,直接在优先关系的指导下构造序列;提出了信息素惩罚蒸发策略,对不可行解进行惩罚,帮助“蚁群”避开无效序列;根据装配序列规划的特点,对信息素的释放策略进行了改进.最后通过实例验证了算法的实用性.
A directed assembly graph is introduced to represent the precedence relationship between components. After that, an assembly relation matrix is established. Then, an Ant Colony Optimization （ACO） strategy is presented to generate assembly sequence. The ACO algorithm is improved and is suitable to the task： a selectable set is established according to precedence relationship; a penalty-evaporation mechanism is proposed to punish the infeasible assembly sequence, which helps the ants construct valid solutions ; the way of updating pheromones is arranged specially to fit the characteristics of an assembly sequence plan. Finally, an example illustrates the effectiveness of the strategy.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2006年第2期180-183,共4页
Journal of Harbin Institute of Technology
基金
黑龙江留学归国基金资助项目(20010701018)
关键词
蚁群算法
装配序列规划
有向装配图
装配关系矩阵
ant colony optimization
assembly sequence planning
directed assembly graph
assembly relation matrix
