基于机器学习的印制电路板生产投料预大率预测  

Prediction of PCB feeding rate based on machine learning

作　　者：周可杰 吴丰顺[1] 杨卓坪 高团芬 万杨 Zhou Kejie;Wu Fengshun;Yang Zhuoping;Gao Tuanfen;Wan Yang(State Key Laboratory of Materials Processing and Die&Mould Technology,School of Materials Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China;Huayuhuayuan Electronics Co.,Ltd,Shenzhen 518118,China;Hubei Key Laboratory of Micro Nanocrystals Processing Technology,Suizhou 441300,China)

机构地区：[1]华中科技大学材料科学与工程学院材料加工与模具技术国家重点实验室,湖北武汉430074 [2]华宇华源电子科技(深圳)有限公司,广东深圳518118 [3]微纳米晶体加工技术湖北省重点实验室,湖北随州441300

出　　处：《印制电路信息》2021年第10期7-11,共5页Printed Circuit Information

基　　金：国家自然科学基金资助(62074062);湖北省重点研发计划资助“高性能、超高频石英晶体器件(VCXO)制造工艺研发”(2020BAA4)基金资助

摘　　要：印制板生产的精准投料直接影响生产成本。文章采用机器学习的方法对投料预大率问题建模,得到预测模型的基线。再选取合适的特征工程与模型调优方法对基线进行优化,降低预测模型的均方误差。并将算法封装于程序中,编写了投料预大率预测软件。Accurate feeding rate of PCB directly affects the production cost of the manufacturers.In this paper,the machine learning method is used to model the problem of feeding rate,and the baseline of the prediction model is obtained.Then it selects appropriate feature engineering and model optimization methods to optimize the baseline and reduce the mean square error of the model.The algorithm is encapsulated in the program,and the prediction software of feeding rate is written.

关 键 词：印制板生产 投料预大率 特征工程 机器学习 

分 类 号：TN41[电子电信—微电子学与固体电子学]