Data-driven design of Ni-based turbine disc superalloys to improve yield strength
作者机构：Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing 100083 China Collaborative Innovation Center of Steel Technology University of Science and Technology Beijing Beijing 100083 China Beijing Key Laboratory of Materials Genome Engineering University of Science and Technology Beijing Beijing 100083 China Institute for Advanced Materials and Technology University of Science and Technology Beijing Beijing 100083 China School of Mechanical Engineering Chongqing Three Gorges University Chongqing 404000 China School of Mechanical and Equipment Engineering Hebei University of Engineering Handan 056038 China Department of Physics University of Science and Technology Bannu Bannu 28100 Pakistan
出 版 物：《Journal of Materials Science & Technology》 (材料科学技术（英文版）)
年 卷 期：2023年第155卷第24期
页 面：175-191页
核心收录：
学科分类：0806[工学-冶金工程] 0817[工学-化学工程与技术] 08[工学] 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] 0702[理学-物理学] 0801[工学-力学（可授工学、理学学位）]
基 金：financially supported by the Beijing Municipal Natural Science Foundation(Grant No.2212042) the National Natural Science Foundation of China(Grant Nos.U2141205,52271019) the Fundamental Research Funds for the Central Universities(Grant No.FRF-BD-22-03) the Natural Science Foundation of Hebei Province(Grant No.E2022402004) the Natural Science Foundation of Chongqing(Grant No.cstc2021jcyj-msxmX0899) supported by USTB MatCom of Beijing Advanced Innovation Center for Materials Genome Engineering
主 题：Ni-based superalloys Data-driven design Machine learning CALPHAD First-principles calculation
摘 要：Increasing the thrust-weight ratio of aeroengines requires development of high-strength and stable high-temperature materials. A data-driven design of Ni-based turbine disc superalloys is performed to improve the yield strength to reach the target. Through first-principles calculations determining the design superalloy system, the theoretical models and Calculation of Phase Diagram (CALPHAD) screening compositions, and machine learning extrapolating prediction, 14 compositions are selected from 2,865,039 composition combinations. Ni-17Cr-8Co-1Mo-1W-6Al-3Ti-1Nb-1Ta is selected to verify the design accuracy. Experimental tests prove that the designed alloy has trade-offs of microstructure with satisfying design targets, and then, the yield strength is higher in the designed alloy than in commercial superalloys, reaching 728 MPa at 850 ℃. A scheme for increasing the performance of the designed alloy is proposed by discussing the strengthening mechanisms, machine learning process, and alloying chemistry effect. The cross-scale data-driven design is regarded as an accurate and efficient way to design novel high-strength Ni-based turbine disc superalloys, whose significance is the obvious reduction of trial-and-error tests.
维普期刊数据库