基于改进粒子群算法的多工位装配序列规划

Multi station assembly sequence planning based on improved particle swarm optimization algorithm

针对现有单工位装配序列规划结果难以满足工位需求的问题,提出一种基于改进粒子群算法的多工位装配序列规划方法。建立多工位装配模型来描述零部件的几何信息及其与工位的关系;用装配序列可行性、装配方向一致性、装配聚合性及工位间平衡性4个评价指标构建适应度函数。为解决一般粒子群算法易陷入局部最优解的问题,对惯性权重进行了改进,提出粒子相似度和相似度阈值的概念,并通过相似度阈值控制粒子的变异,提高了算法的全局搜索能力。以某型发动机为装配实例,验证了改进粒子群算法应用于多工位装配序列规划的可行性;同时将该算法和遗传算法、一般粒子群算法进行比较,证明了该算法的优越性。

Aiming at the problem that the existing single station assembly sequence planning was difficult to meet the demand of the station,a multi-station assembly sequence planning method based on improved particle swarm optimization was proposed.A multi-station assembly model was created to describe the geometric information of component and its relationship to the station.The evaluation indexes such as assembly sequence feasibility,assembly direction consistency,assembly polymerizability and inter-station balance were used to construct the fitness function.Aiming at the problem that the general particle swarm algorithm was easy to fall into the local optimal solution,the inertia weight was improved,and the concept of particle similarity and similarity threshold was put forward.The mutation of the particles was controlled with similarity threshold,which improved the global search ability of the algorithm.The feasibility of the improved particle swarm optimization algorithm for multi-station assembly sequence planning was verified by a certain type of engine,and the superiority of the algorithm was proved by comparing with the genetic algorithm and the general particle swarm algorithm.