基于机器学习设计和制备高熵氮化物陶瓷  

Design and Preparation of High-Entropy Nitride Ceramics via Machine Learning

作　　者：刘娟 田传进 汪长安 LIU Juan;TIAN Chuanjin;WANG Chang′an(School of Materials Science and Engineering,Jingdezhen Ceramic Institute,Jingdezhen 333403,Jiangxi,China;State Key Laboratory of New Ceramics and Fine Processing,School of Materials Science and Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]景德镇陶瓷大学材料科学与工程学院,江西景德镇333403 [2]清华大学材料学院,新型陶瓷与精细工艺国家重点实验室,北京100084

出　　处：《硅酸盐学报》2023年第12期3095-3101,共7页Journal of The Chinese Ceramic Society

基　　金：国家自然科学基金(52173257)。

摘　　要：高熵陶瓷作为一种新兴的陶瓷材料自问世起就成为陶瓷领域的研究热点,然而,其巨大的成分设计空间也为基于实验和“试错法”的组分设计带来了挑战。近年来,通过机器学习与实验探索相结合的方式为这一问题的解决带来新方法。基于此,本研究建立了4个机器学习模型,通过训练评估选出性能最好的梯度提升决策树模型(R~2=0.92)并用于预测,然后通过实验成功合成了单相的(Ti_(0.2)V_(0.2)Zr_(0.2)Nb_(0.2)Hf_(0.2))N高熵氮化物陶瓷,验证了模型的准确性,为高熵氮化物陶瓷的设计提供了新思路,加快了新体系的发现。As one of emerging ceramic materials,high-entropy ceramics become a research hotspot in the field of ceramics.However,their compositional design has some challenges for component design based on experimentation and “trial and error”.In recent years,the combination of machine learning and experiments can provide an effective method to solve this problem.In this paper,four machine learning models were established,the best-performing gradient-boosting decision tree model(R2=0.92) through training and evaluation was selected for prediction.A single-phase(Ti_(0.2)V_(0.2)Zr_(0.2)Nb_(0.2)Hf_(0.2))N high-entropy nitride ceramic was then synthesized based on the predication by the model.This effective approach can provide some ideas for the design of high-entropy nitride ceramic and discover new systems.

关 键 词：高熵陶瓷 氮化物陶瓷 机器学习 材料设计 模型预测 

分 类 号：TQ175[化学工程—硅酸盐工业]