摘要
为减少船舶涂装缺陷的产生,提早对涂装工艺参数进行干预控制,提出一种基于改进关联规则算法的船舶涂装缺陷知识获取方法,对涂装缺陷成因进行科学性量化分析。首先,在传统Apriori算法模型的基础上,引入哈希算法中的链表结构改变频繁项集的挖掘模式,减少运算过程中遍历整体事务集的次数;其次,对涂装工艺参数和环境参数进行量化,构建涂装缺陷分析模型;最后,选取涂装工艺数据验证文章提出方法的有效性。结果表明,面向冗杂的船舶涂装工艺数据,改进后的Apriori算法可以更好地进行涂装缺陷分析,在有效缩短算法计算时间的同时获得更加直观的缺陷成因知识,算法性能显著提升。
In order to reduce the occurrence of ship coating defects and intervene the coating process parameters in advance, a knowledge acquisition method of ship coating defects based on improved association rule algorithm is proposed, which is used for scientific and quantitative analysis of the causes of coating defects.Firstly, based on the traditional Apriori algorithm model, the linked list structure in hash algorithm is introduced to change the mode of mining frequent itemsets and reduce the number of traversing the whole transaction set in the operation process. Secondly, the coating process parameters and environmental parameters are quantified,and the coating defect analysis model is constructed. Finally, the coating process data are selected to verify the effectiveness of the method proposed. The results show that the improved Apriori algorithm can perform better coating defect analysis for the redundant ship coating process data, shorten the calculation time of the algorithm effectively and obtain more intuitive defect cause knowledges at the same time, and the performance of the algorithm significantly improves.
作者
吕宏宇
卜赫男
袁昕
纪星宇
周宏根
LYU Hongyu;BU Henan;YUAN Xin;JI Xingyu;ZHOU Honggen(School of Mechanical Engineering,Jiangsu University of Science and Technology,Zhenjiang 212003,Jiangsu,China)
出处
《船舶工程》
CSCD
北大核心
2022年第12期30-35,共6页
Ship Engineering
基金
工信部高技术船舶科研项目(MC-202003-Z01-02)。
关键词
船舶涂装
关联规则
缺陷分析
知识获取
ship coating
association rules
defect analysis
knowledge acquisition
