A generic and extensible model for the martensite start temperature incorporating thermodynamic data mining and deep learning framework

作     者：Chenchong Wang Kaiyu Zhu Peter Hedström Yong Li Wei Xu Chenchong Wang;Kaiyu Zhu;Peter Hedstr?m;Yong Li;Wei Xu

作者机构：State Key Laboratory of Rolling and AutomationNortheastern UniversityShenyang 110819China Department of Materials Science and EngineeringKTH Royal Institute of TechnologyStockholm 10044Sweden 

出 版 物：《Journal of Materials Science & Technology》 (材料科学技术（英文版）)

年 卷 期：2022年第128卷第33期

页      面：31-43页

核心收录：

学科分类：12[管理学] 08[工学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0806[工学-冶金工程] 0817[工学-化学工程与技术] 081104[工学-模式识别与智能系统] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 0703[理学-化学] 0802[工学-机械工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0702[理学-物理学] 0801[工学-力学（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：financially supported by the National Natural Science Foundation of China(Nos.51801019 and U1808208) 

主　　题：Martensite transformation Data mining Deep learning Extensibility Small-sample problem 

摘      要：The martensite start temperature is a critical parameter for steels with metastable *** numerous models have been developed to predict the martensite start(Ms)temperature,the complexity of the martensitic transformation greatly limits their performance and *** this work,we apply deep data mining of thermodynamic calculations and deep learning to develop a generic model for *** data mining was used to establish a hierarchical database with three levels of ***,a convolutional neural network model,which can accurately treat the hierarchical data structure,was used to obtain the final *** integrating thermodynamic calculations,traditional machine learning and deep learning modeling,the final predictor model shows excellent generalizability and extensibility,*** performance both within and beyond the composition range of the original *** effects of 15 alloying elements were considered successfully using the proposed *** work suggests that,with the help of deep data mining considering the physical mechanisms,deep learning methods can partially mitigate the challenge with limited data in materials science and provide a means for solving complex problems with small databases.