Fast characterization framework for creep microstructure of a nickel-based SX superalloy with high-throughput experiments and deep learning methods

doi:10.1016/j.matchar.2022.111857

CORC > 金属研究所 > 中国科学院金属研究所

	Fast characterization framework for creep microstructure of a nickel-based SX superalloy with high-throughput experiments and deep learning methods
	Xu, Jinghui 2; Li, Longfei 2; Liu, Xingang 1; Li, Hui 1; Feng, Qiang 2
刊名	MATERIALS CHARACTERIZATION
	2022-05-01
卷号	187 页码:9
关键词	Nickel-based SX superalloy Microstructure characterization Integrated method U-net Continuous quantification
ISSN号	1044-5803
DOI	10.1016/j.matchar.2022.111857
通讯作者	Li, Longfei(lilf@skl.ustb.edu.cn)
英文摘要	Nickel-based single crystal (SX) superalloys are the key materials of turbine blades in aircrafts, that the microstructure evolution during high temperature creep has critical effects on the thermo-mechanical properties. Research on microstructure evolution and establishing the quantitative relationship between microstructure evolution and creep conditions are of great significance for service safety assessment of nickel-based SX superalloys. High generation nickel-based SX superalloys generally have high cost on account of precision casting and the addition of Re and Ru which are rare and precious metals. Hence, it is necessary to develop a rapid characterization and analysis approach in terms of microstructure features of nickel-based SX superalloys. In this study, we integrated high-throughput experiment, large-scale high-resolution characterization and highthroughput quantitative analysis techniques to establish an efficient method for investigating the microstructure evolution of nickel-based SX superalloys during high temperature creep. The high temperature interrupted creep tests were carried out on the variable section specimens with arc surface to acquire the microstructures which are changed with creep stress continuously. High-resolution SEM with ALTLAS module was employed to quickly characterize the large-scale microstructure throughout the universal stress scale. Based on U-Net deep learning algorithm, an automatic dendrite identification model was established to segment the dendrite region quickly and accurately. And then, the gamma/gamma' microstructure parameters of dendrite region were continuously quantitated using a logical algorithm. The quantitative correlation between microstructure evolution and creep conditions of nickel-based SX superalloys could be established, which shows tremendous potential and significance in the service safety assessment of nickel-based SX superalloys.
资助项目	National Science and Technology Major Project[:2017-VI0002-0072] ; National Key Research and Development Program of China[:2016YFB0701403] ; National Natural Science Foundation of China[51631008] ; National Natural Science Foundation of China[91860201] ; 111 Project[B170003]
WOS研究方向	Materials Science ; Metallurgy & Metallurgical Engineering
语种	英语
出版者	ELSEVIER SCIENCE INC
WOS记录号	WOS:000793644100004
资助机构	National Science and Technology Major Project ; National Key Research and Development Program of China ; National Natural Science Foundation of China ; 111 Project
内容类型	期刊论文
源URL	[http://ir.imr.ac.cn/handle/321006/173953]
专题	金属研究所_中国科学院金属研究所
通讯作者	Li, Longfei
作者单位	1.Chinese Acad Sci, Inst Met Res, Superalloys Div, Shenyang 110016, Peoples R China 2.Univ Sci & Technol Beijing, Beijing Adv Innovat Ctr Mat Genome Engn, State Key Lab Adv Met & Mat, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Xu, Jinghui,Li, Longfei,Liu, Xingang,et al. Fast characterization framework for creep microstructure of a nickel-based SX superalloy with high-throughput experiments and deep learning methods[J]. MATERIALS CHARACTERIZATION,2022,187:9.
APA	Xu, Jinghui,Li, Longfei,Liu, Xingang,Li, Hui,&Feng, Qiang.(2022).Fast characterization framework for creep microstructure of a nickel-based SX superalloy with high-throughput experiments and deep learning methods.MATERIALS CHARACTERIZATION,187,9.
MLA	Xu, Jinghui,et al."Fast characterization framework for creep microstructure of a nickel-based SX superalloy with high-throughput experiments and deep learning methods".MATERIALS CHARACTERIZATION 187(2022):9.