基于变邻域蚁群算法的自动光学检测路径规划

在确定取像窗口最少数量及其约束移动范围的前提下,为解决蚁群算法用于自动光学检测路径规划存在的问题,提出一种基于变邻域蚁群算法的自动光学检测路径规划方法。针对蚁群算法收敛速度慢、易陷入局部最优解的问题,提出含有3种邻域结构的变邻域路径搜索方法,改进蚁群算法以快速获得质量优异的可优化路径;针对取像窗口位置可调整的问题,提出变邻域窗口位置调整方法,进一步改善可优化路径,获得最短路径。实验结果表明,该算法比基本的蚁群算法具有更高的求解效率和求解质量,有效提升了自动光学检测系统的在线检测效率。

Path planning of automatic optical inspection based on variable neighborhood ant colony algorithm

On the premise of determining the minimum number of image capture windows and the range of constraint movement,to solve the problems existing in the ant colony algorithm for path planning of automatic optical inspection,a path planning me-thod of automatic optical inspection based on variable neighborhood ant colony algorithm was proposed.Aiming at the problem that the ant colony algorithm has slow convergence rate and it is easy to fall into the local optimal solution,a variable neighborhood path search method with three neighborhood structures was proposed to improve the ant colony algorithm to quickly obtain an optimizable path with excellent quality.Aiming at the problem that the image capture window’s position can be adjusted,a variable neighborhood window position adjustment method was proposed to optimize the optimizable path to obtain the shortest path.Experimental results show that the proposed algorithm has higher efficiency and solution quality than the basic ant colony algorithm,which effectively improves the online detection efficiency of the automatic optical inspection system.