基于图论的飞机典型装配工艺数据挖掘方法  

Typical aircraft assembly process data mining method based on graph theory

作　　者：张森[1] 余剑峰[1] 俞琳[1] 张杰[1] 

机构地区：[1]西北工业大学机电学院,西安710072

出　　处：《计算机工程与应用》2015年第20期116-119,共4页Computer Engineering and Applications

基　　金：国家科技支撑计划课题(No.2011BAF13B03);航天技术支撑基金(No.2013-HT-XGD);国家商用飞机制造工程技术研究中心创新基金(No.SAMC12-15-013);西北工业大学基础研究基金(No.JC201137)

摘　　要：为实现飞机装配指令编制的快速化、智能化,提出基于图论的飞机典型装配工艺数据挖掘方法。该方法将停用词表和分隔数组两个约束引入语义分词法完成装配工艺指令的分词处理,并以装配工艺特征向量结构化地表达分词后的装配工艺指令。将装配工艺特征向量映射为单向有序链,以此构建装配工艺图。通过定义装配工艺图的节点支持度和边支持度,给出了典型装配工艺挖掘方法。以某型飞机的平尾装配工艺为例,在多个支持度下验证了方法的有效性。In answering the need of efficiency and intelligentization in aircraft assembly order planning, this paper pre-sents a data mining method for typical aircraft assembly order based on graph theory. The stop words lists and separator arrays are used as constraints to separate the assembly orders. A concept for Assembly Process Feature Vectors（APFVs） is presented to convey the separated assembly orders. The APFVs are mapped to Unidirectional and Sequential Chains （USCs）, and an Assembly Process Graph（APG）is constructed based on the USCs. An algorithm for the mining of typical assembly orders is proposed through defining the node support and edge support in the APG. The proposed method is vali-dated by the assembly processed of horizontal tail, and the results suggest its feasibility with different support.

关 键 词：装配工艺特征向量 装配工艺图 频繁装配工艺特征链 典型装配工艺 

分 类 号：TP391.73[自动化与计算机技术—计算机应用技术]