关键词: 喷丝板检测, 蚁群算法, 信息素浓度, 最近邻法, 最优化

Abstract:

In order to improve the inspection efficiency of concentric-distribution spinneret, this essay proposes an inspection route planning method based on improved ant colony algorithm. In order to overcome the shortcomings of traditional algorithm including low convergence speed and sinking into local optimum, this method redefines the distance between micropores to meet the characteristic of typical spinneret inspectors, sets up the initial pheromone concentration table by nearest neighbor method to obtain better results with other parameters unchanged, and further optimizes the results through path peaks removal process. To verify the effectiveness of the proposed algorithm, calculation of the path planning for a typical concentric-distribution spinneret was carried out. The results show that the proposed algorithm has higher convergence speed, and it can shorten the path length by about 18% compared with the conventional inspection route and improve the inspection efficiency of matching spinneret.

Key words: spinneret inspection, ant colont algorithm, pheromone concentration, nearest neighbor, optimization