Performance prediction of magnetorheological fluid‐based liquid gating membrane by kriging machine learning method

作     者：Mengchuang Zhang Yuan Jing Jian Zhang Zhizhi Sheng Yaqi Hou Jiadai Xu Baiyi Chen Jing Liu Miao Wang Xu Hou 

作者机构：Department of PhysicsResearch Institute for Biomimetics and Soft MatterFujian Provincial Key Laboratory for Soft Functional Materials ResearchJiujiang Research InstituteCollege of Physical Science and TechnologyXiamen UniversityXiamenChina Institute of Artificial IntelligenceXiamen UniversityXiamenChina School of Civil AviationNorthwestern Polytechnical UniversityXi'anChina Yangtze River Delta Research Institute of Northwestern Polytechnical UniversityTaicang CityJiangsu ProvinceChina State Key Laboratory of Physical Chemistry of Solid SurfacesCollege of Chemistry and Chemical EngineeringXiamen UniversityXiamenChina Suzhou Institute of Nano-Tech and Nano-BionicsChinese Academy of SciencesSuzhouChina Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province(IKKEM)XiamenChina 

出 版 物：《Interdisciplinary Materials》 (交叉学科材料（英文）)

年 卷 期：2022年第1卷第1期

页      面：157-169页

核心收录：

学科分类：08[工学] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 

基　　金：This study was supported by the National Natural Science Foundation of China(52025132,21975209,and 21621091) the National Key R&D Program of China(2018YFA0209500) 

主　　题：active candidate region techniques artificial intelligence Kriging machine learning method magnetorheological fluid-based liquid gating membrane rheological and mechanical model 

摘      要：Smart liquid gating membrane is a responsive structural material as a pressure-driven system that consists of solid membrane and dynamic liquid,responding to the external *** accurate prediction of rheological and mechanical properties is important for the designs of liquid gating membranes for various ***,high predicted accuracy by the traditional sequential method requires a large amount of experimental data,which is not practical in some *** conquer these problems,artificial intelligence has promoted the rapid development of material science in recent years,bringing hope to solve these *** we propose a Kriging machine learning model with an active candidate region,which can be smartly updated by an expected improvement probability method to increase the local accuracy near the most sensitive search region,to predict the mechanical and rheolo-gical performance of liquid gating system with an active minimal size of ex-perimental *** this,this new machine learning model can instruct our experiments with optimal *** methods are then verified by liquid gating membrane with magnetorheological fluids,which would be of wide interest for the design of potential liquid gating applications in drug release,microfluidic logic,dynamic fluid control,and beyond.