Review: Recent progress in titanium alloys development via machine learning and high-throughput preparation

IF 3.9 3区材料科学 Q2 MATERIALS SCIENCE, MULTIDISCIPLINARY

Journal of Materials Science Pub Date : 2025-09-06 DOI:10.1007/s10853-025-11441-0

Feiyang Gao, Weiwen Zhang, Xiaotao Liu, Xuan Luo, Zhi Wang, Ning Li, Lehua Liu

{"title":"Review: Recent progress in titanium alloys development via machine learning and high-throughput preparation","authors":"Feiyang Gao, Weiwen Zhang, Xiaotao Liu, Xuan Luo, Zhi Wang, Ning Li, Lehua Liu","doi":"10.1007/s10853-025-11441-0","DOIUrl":null,"url":null,"abstract":"<div><p>In the exploration of advanced titanium (Ti) alloys, the huge composition and process space make it impossible to fully consider every possibility through the traditional trial-and-error methods. With the development of high-throughput technologies and the improvement of computer data analysis capabilities, machine learning (ML) methods based on big data have opened up a new paradigm for materials science research, accelerating the development of materials such as Ti alloys and achieving a series of breakthroughs. However, there is still a lack of systematic generalizations and summaries about the applications of ML methods and high-throughput technologies in the field of Ti alloys. This review first introduces the common ML workflow in materials science. Then, advances in high-throughput preparation technology and ML in the prediction and design of the microstructure and properties of Ti alloys are examined. Finally, the main challenges are discussed, and future directions for ML and high-throughput technologies in materials science are proposed. It is hoped that this review offers useful insights into the integration of these emerging technologies, providing some guidance for future research and applications of Ti alloys.</p><h3>Graphical abstract</h3>\n<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":645,"journal":{"name":"Journal of Materials Science","volume":"60 37","pages":"16655 - 16683"},"PeriodicalIF":3.9000,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Materials Science","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s10853-025-11441-0","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

In the exploration of advanced titanium (Ti) alloys, the huge composition and process space make it impossible to fully consider every possibility through the traditional trial-and-error methods. With the development of high-throughput technologies and the improvement of computer data analysis capabilities, machine learning (ML) methods based on big data have opened up a new paradigm for materials science research, accelerating the development of materials such as Ti alloys and achieving a series of breakthroughs. However, there is still a lack of systematic generalizations and summaries about the applications of ML methods and high-throughput technologies in the field of Ti alloys. This review first introduces the common ML workflow in materials science. Then, advances in high-throughput preparation technology and ML in the prediction and design of the microstructure and properties of Ti alloys are examined. Finally, the main challenges are discussed, and future directions for ML and high-throughput technologies in materials science are proposed. It is hoped that this review offers useful insights into the integration of these emerging technologies, providing some guidance for future research and applications of Ti alloys.

Graphical abstract

查看原文本刊更多论文

综述：基于机器学习和高通量制备的钛合金研究进展

在先进钛（Ti）合金的探索中，巨大的成分和工艺空间使得通过传统的试错方法无法充分考虑每一种可能性。随着高通量技术的发展和计算机数据分析能力的提高，基于大数据的机器学习（ML）方法为材料科学研究开辟了新的范式，加速了钛合金等材料的发展，实现了一系列突破。然而，对于机器学习方法和高通量技术在钛合金领域的应用，目前还缺乏系统的归纳和总结。本文首先介绍了材料科学中常见的机器学习工作流程。然后，介绍了高通量制备技术和机器学习在预测和设计钛合金组织和性能方面的进展。最后，讨论了材料科学中机器学习和高通量技术的主要挑战，并提出了未来的发展方向。希望本文的综述能够为这些新兴技术的整合提供有益的见解，为今后钛合金的研究和应用提供一些指导。图形抽象

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Materials Science 工程技术-材料科学：综合

CiteScore

7.90

自引率

4.40%

发文量

1297

审稿时长

2.4 months

期刊介绍： The Journal of Materials Science publishes reviews, full-length papers, and short Communications recording original research results on, or techniques for studying the relationship between structure, properties, and uses of materials. The subjects are seen from international and interdisciplinary perspectives covering areas including metals, ceramics, glasses, polymers, electrical materials, composite materials, fibers, nanostructured materials, nanocomposites, and biological and biomedical materials. The Journal of Materials Science is now firmly established as the leading source of primary communication for scientists investigating the structure and properties of all engineering materials.