PDF
Full
Outline
Data-centric materials informatics has become a transformative paradigm for accelerating the discovery and design of superalloys, particularly by enabling efficient prediction of properties that are experimentally inaccessible or computationally intractable due to constraints in cost, time, or complexity. By harnessing the ability of machine learning (ML) to model complex, nonlinear, and high-dimensional relationships, this approach provides a compelling alternative to traditional trial-and-error and simulation-based strategies. This review presents a comprehensive and critical assessment of recent advances in ML for superalloys. We first delineate the essential workflow for ML-enabled superalloy design, encompassing foundational data resources, quantitative assessments of data quality, feature descriptors and feature-selection strategies, representative algorithms tailored to small and heterogeneous datasets, rigorous model-evaluation protocols, and model interpretation through explainable ML and symbolic regression. We then summarize state-of-the-art ML applications targeting specific high-temperature performance metrics, particularly γ' phase stability, creep behavior, fatigue life, and oxidation resistance, and highlight how approaches such as multi-fidelity learning, data augmentation, transfer learning, and optimization algorithms facilitate efficient exploration of vast composition-processing design spaces. Finally, we discuss persisting challenges and emerging opportunities, including data scarcity and reliability, model confidence and uncertainty quantification, cross-system generalizability across Co-, Ni-, and multi-principal superalloys, high-dimensional multi-objective optimization, and the integration of physics-informed models and large language models into materials-informatics workflows. By synthesizing these developments, this review outlines a strategic roadmap for harnessing ML to accelerate the discovery, performance optimization, and intelligent design of next-generation superalloys.
PDF
2
0
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
