应用改进蚁群算法的同心分布喷丝孔检测路径规划

发布时间：2018-04-02 10:32

本文选题：喷丝板检测　切入点：蚁群算法　出处：《纺织学报》2017年11期

【摘要】：为提高微孔同心分布喷丝板的检测效率,提出一种基于改进蚁群算法的微孔检测路径规划方法。该方法针对传统蚁群算法收敛速度慢、易陷入局部最优等缺陷进行优化改进:重新定义微孔间的距离以适应典型喷丝板检测仪运动特点;采用最近邻法设定初始信息素浓度表,使蚁群算法在相同的迭代次数等参数下求得更优的路径结果;通过路径尖端去除处理对蚁群算法的结果进一步优化,得到了优化的微孔检测路径。为验证算法的有效性,以典型的微孔同心分布喷丝板为算例进行检测路径的规划计算。结果表明,所提出的算法具有较快的收敛速度,优化所得路径与传统逐圈检测路径相比缩短路径长度约18%,可显著提高对应喷丝板的检测效率。
[Abstract]:In order to improve the detection efficiency of micropore concentric distribution spinneret, a path planning method based on improved ant colony algorithm is proposed, which aims at the slow convergence speed of traditional ant colony algorithm. In order to adapt to the motion characteristics of a typical spinneret detector, the nearest neighbor method is used to set the initial pheromone concentration table, the distance between the microholes is redefined to fit the motion characteristics of a typical spinneret detector. In order to verify the effectiveness of the algorithm, the ant colony algorithm can obtain better path results under the same iteration times and other parameters, and further optimize the results of the ant colony algorithm through the path tip removal process, and obtain the optimized microhole detection path. A typical micropore concentric distribution spinneret is taken as an example to calculate the detection path planning. The results show that the proposed algorithm has a fast convergence rate. Compared with the traditional loop detection path, the optimized path can shorten the length of the path by about 18%, which can significantly improve the detection efficiency of the corresponding spinneret.
【作者单位】：上海交通大学机械与动力工程学院;
【分类号】：TP18;TQ340.5

【相似文献】