基于知识图谱的SMT产线工艺推荐与优化  

The process recommendation and optimizationof SMT production line based on knowledge graph

作　　者：刘潇龙[1] 李鑫[1] 朱孟达 黄文艳 Liu Xiaolong;Li Xin;Zhu Mengda;Huang Wenyan(The 10th Research Institute of China Electronics Technology Group Corporation,Sichuan Chengdu,610036,China;School of Mechano-Electronic Engineering,Xidian University,Shaanxi Xi'an,710126,China)

机构地区：[1]中国电子科技集团公司第十研究所,四川成都610036 [2]西安电子科技大学机电工程学院,陕西西安710126

出　　处：《机械设计与制造工程》2024年第6期122-126,共5页Machine Design and Manufacturing Engineering

基　　金：国家重点研发计划(2021YFB3302100)。

摘　　要：面向复杂电路板组件产品,依赖人工经验设计表面贴装技术(SMT)工艺的传统方法存在准确度与适配度低、设计效率低、实物试错成本高等问题,提出了一种基于知识图谱的SMT产线工艺推荐与优化算法。建立知识图谱系统描述SMT产线工艺参数之间的关系,利用随机森林算法计算各个参数重要度,更新参数权重推荐合适参数,并与完全平均加权法对比,验证了其准确性与稳定性。For complex circuit board component products,the traditional method of relying on manual experience to design SMT process has the problems of low accuracy and adaptability,low design efficiency,and high cost of physical trial and error.This paper proposes a process recommendation and optimization algorithm for SMT production line based on knowledge graph.The knowledge graph system is established to describe the relationship between the process parameters of SMT production line.The importance of each parameter is calculated by random forest,and the parameter weight is updated to recommend the appropriate parameters.Compared with the complete average weighting method,its accuracy and stability are verified.

关 键 词：表面贴装技术 工艺参数 知识图谱 随机森林算法 

分 类 号：TN605[电子电信—电路与系统]