Sampling via the aggregation value for data-driven manufacturing

作     者：Xu Liu Gengxiang Chen Yingguang Li Lu Chen Qinglu Meng Charyar Mehdi-Souzani Xu Liu;Gengxiang Chen;Yingguang Li;Lu Chen;Qinglu Meng;Charyar Mehdi-Souzani

作者机构：School of Mechanical and Power EngineeringNanjing Tech University College of Mechanical &Electrical EngineeringNanjing University of Aeronautics and Astronautics University Research Laboratory in Automated ProductionEcole normale superieure Paris-SaclayUniversite Paris-SaclayUniversite Sorbonne Paris Nord 

出 版 物：《National Science Review》 (国家科学评论(英文版))

年 卷 期：2022年第9卷第11期

页      面：161-171页

核心收录：

学科分类：08[工学] 082503[工学-航空宇航制造工程] 0825[工学-航空宇航科学与技术] 

基　　金：supported by the National Science Fund for Distinguished Young Scholars (51925505) the Major Program of the National Natural Science Foundation of China (52090052) the Science Fund for Creative Research Groups of the National Natural Science Foundation of China (51921003) 

主　　题：data-driven modelling intelligent manufacturing data sampling data value 

摘      要：Data-driven modelling has shown promising potential in many industrial applications, while the expensive and time-consuming labelling of experimental and simulation data restricts its further development.Preparing a more informative but smaller dataset to reduce labelling efforts has been a vital research problem. Although existing techniques can assess the value of individual data samples, how to represent the value of a sample set remains an open problem. In this research, the aggregation value is defined using a novel representation for the value of a sample set by modelling the invisible redundant information as the overlaps of neighbouring values. The sampling problem is hence converted to the maximisation of the submodular function over the aggregation value. The comprehensive analysis of several manufacturing datasets demonstrates that the proposed method can provide sample sets with superior and stable performance compared with state-of-the-art methods. The research outcome also indicates its appealing potential to reduce labelling efforts for more data-scarcity scenarios.