首页|A multiple loops machine learning framework to predict the properties of WC–Co based cemented carbides
A multiple loops machine learning framework to predict the properties of WC–Co based cemented carbides
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
? 2022 Elsevier LtdAlthough of scientific and practical importance, very limited efforts have been made to accurately predict the properties of cemented carbide by machine learning (ML). Herein, we propose a multiple loops ML framework to predict various properties (density, coercive force, hardness, transverse rupture strength, and fracture toughness) of WC–Co based cemented carbides. High fidelity ML models for density and coercive force were firstly built using highly ranked features identified by correlation analyses to augment the training dataset with predicted data. Next, ML models were successfully trained to provide a satisfactory prediction for hardness, transverse rupture strength, and fracture toughness. The current study demonstrated the potential of the ML approach to predict the properties of cemented carbide with various additives and to further guide the design of new materials.
Cemented carbidesMachine learningPropertyWC–Co
Guan Z.、Li N.、Zhang W.、Wang J.、Wang C.、Shen Q.、Peng J.、Xu Z.、Du Y.
展开 >
Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials (Ministry of Education) Shandong University
Engineering Research Center of Environmental Materials and Membrane Technology of Hubei Province School of Materials Science and Engineering Wuhan Institute of Technology
State Key Lab of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology
Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology
State Key Laboratory of Powder Metallurgy Central South University
NSTL
Elsevier
