Fengyuan Zhao , Zhouran Zhang , Yicong Ye, Yahao Li, Shun Li, Yu Tang, Li’an Zhu, Shuxin Bai
{"title":"机器学习指导下的高熵合金动态能量释放预测","authors":"Fengyuan Zhao , Zhouran Zhang , Yicong Ye, Yahao Li, Shun Li, Yu Tang, Li’an Zhu, Shuxin Bai","doi":"10.1016/j.matdes.2024.113339","DOIUrl":null,"url":null,"abstract":"<div><div>High-entropy alloy (HEA) type energetic structural materials (ESMs) offer exceptional strength, adequate ductility and reactivity upon dynamic loading, thus demonstrating great potentials in pyrotechnic applications. However, the main factors governing their energetic performance remain elusive, primarily attributable to the intricate mechanical-thermal-chemical coupling effects and the inherent challenges of HEA design. To address this, we propose a small-data machine learning framework designed to predict the energetic performance of HEA-type ESMs, employing support vector regression, leave-one-out cross-validation, and principal component analysis (PCA) to effectively manage a small, unevenly distributed, and highly dimensional dataset. Notably, the framework achieved a coefficient of determination (R<sup>2</sup>) of 0.854 while upholding robust performance, interpretability and computational efficiency. Fracture elongation (<em>ε</em><sub>t</sub>) and compressive yield strength (<em>σ</em><sub>cys</sub>) were identified as critical features, with <em>σ</em><sub>cys</sub> positively influencing performance while both <em>ε</em><sub>t</sub> and unit theoretical heat of combustion (UTHC) demonstrated negative effect. Guided by the framework, a series of novel Ti-V-Ta-Zr alloys with the comparable UTHC, velocity (<em>v</em>) and weight (<em>m</em>) but tailored <em>ε</em><sub>t</sub> and <em>σ</em><sub>cys</sub> were designed and tested. Ti<sub>30</sub>V<sub>30</sub>Ta<sub>30</sub>Zr<sub>10</sub> alloy exhibited a commendable balance of mechanical properties and the smallest mean particle size, aligning with the model predictions and suggesting more thorough energy release during ballistic experiments.</div></div>","PeriodicalId":383,"journal":{"name":"Materials & Design","volume":"246 ","pages":"Article 113339"},"PeriodicalIF":7.6000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning guided prediction of dynamic energy release in high-entropy alloys\",\"authors\":\"Fengyuan Zhao , Zhouran Zhang , Yicong Ye, Yahao Li, Shun Li, Yu Tang, Li’an Zhu, Shuxin Bai\",\"doi\":\"10.1016/j.matdes.2024.113339\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>High-entropy alloy (HEA) type energetic structural materials (ESMs) offer exceptional strength, adequate ductility and reactivity upon dynamic loading, thus demonstrating great potentials in pyrotechnic applications. However, the main factors governing their energetic performance remain elusive, primarily attributable to the intricate mechanical-thermal-chemical coupling effects and the inherent challenges of HEA design. To address this, we propose a small-data machine learning framework designed to predict the energetic performance of HEA-type ESMs, employing support vector regression, leave-one-out cross-validation, and principal component analysis (PCA) to effectively manage a small, unevenly distributed, and highly dimensional dataset. Notably, the framework achieved a coefficient of determination (R<sup>2</sup>) of 0.854 while upholding robust performance, interpretability and computational efficiency. Fracture elongation (<em>ε</em><sub>t</sub>) and compressive yield strength (<em>σ</em><sub>cys</sub>) were identified as critical features, with <em>σ</em><sub>cys</sub> positively influencing performance while both <em>ε</em><sub>t</sub> and unit theoretical heat of combustion (UTHC) demonstrated negative effect. Guided by the framework, a series of novel Ti-V-Ta-Zr alloys with the comparable UTHC, velocity (<em>v</em>) and weight (<em>m</em>) but tailored <em>ε</em><sub>t</sub> and <em>σ</em><sub>cys</sub> were designed and tested. Ti<sub>30</sub>V<sub>30</sub>Ta<sub>30</sub>Zr<sub>10</sub> alloy exhibited a commendable balance of mechanical properties and the smallest mean particle size, aligning with the model predictions and suggesting more thorough energy release during ballistic experiments.</div></div>\",\"PeriodicalId\":383,\"journal\":{\"name\":\"Materials & Design\",\"volume\":\"246 \",\"pages\":\"Article 113339\"},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Materials & Design\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0264127524007147\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Materials & Design","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0264127524007147","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
高熵合金(HEA)型高能效结构材料(ESMs)具有超强的强度、足够的延展性和动态加载时的反应性,因此在烟火应用中展现出巨大的潜力。然而,制约其能量性能的主要因素仍然难以捉摸,这主要归因于错综复杂的机械-热-化学耦合效应以及 HEA 设计所固有的挑战。为了解决这个问题,我们提出了一个小数据机器学习框架,旨在预测 HEA 型 ESM 的能量性能,该框架采用了支持向量回归、留空交叉验证和主成分分析 (PCA) 等方法,有效地管理了一个小型、分布不均和高维的数据集。值得注意的是,该框架的判定系数(R2)达到了 0.854,同时保持了强大的性能、可解释性和计算效率。断裂伸长率(εt)和抗压屈服强度(σcys)被确定为关键特征,其中σcys对性能有积极影响,而εt和单位理论燃烧热(UTHC)则表现出负面影响。在该框架的指导下,设计并测试了一系列新型 Ti-V-Ta-Zr 合金,它们具有可比的 UTHC、速度 (v) 和重量 (m),但εt 和 σcys 却经过了定制。Ti30V30Ta30Zr10 合金表现出了值得称赞的机械性能平衡和最小的平均粒度,与模型预测一致,表明在弹道实验中能量释放更彻底。
Machine learning guided prediction of dynamic energy release in high-entropy alloys
High-entropy alloy (HEA) type energetic structural materials (ESMs) offer exceptional strength, adequate ductility and reactivity upon dynamic loading, thus demonstrating great potentials in pyrotechnic applications. However, the main factors governing their energetic performance remain elusive, primarily attributable to the intricate mechanical-thermal-chemical coupling effects and the inherent challenges of HEA design. To address this, we propose a small-data machine learning framework designed to predict the energetic performance of HEA-type ESMs, employing support vector regression, leave-one-out cross-validation, and principal component analysis (PCA) to effectively manage a small, unevenly distributed, and highly dimensional dataset. Notably, the framework achieved a coefficient of determination (R2) of 0.854 while upholding robust performance, interpretability and computational efficiency. Fracture elongation (εt) and compressive yield strength (σcys) were identified as critical features, with σcys positively influencing performance while both εt and unit theoretical heat of combustion (UTHC) demonstrated negative effect. Guided by the framework, a series of novel Ti-V-Ta-Zr alloys with the comparable UTHC, velocity (v) and weight (m) but tailored εt and σcys were designed and tested. Ti30V30Ta30Zr10 alloy exhibited a commendable balance of mechanical properties and the smallest mean particle size, aligning with the model predictions and suggesting more thorough energy release during ballistic experiments.
期刊介绍:
Materials and Design is a multi-disciplinary journal that publishes original research reports, review articles, and express communications. The journal focuses on studying the structure and properties of inorganic and organic materials, advancements in synthesis, processing, characterization, and testing, the design of materials and engineering systems, and their applications in technology. It aims to bring together various aspects of materials science, engineering, physics, and chemistry.
The journal explores themes ranging from materials to design and aims to reveal the connections between natural and artificial materials, as well as experiment and modeling. Manuscripts submitted to Materials and Design should contain elements of discovery and surprise, as they often contribute new insights into the architecture and function of matter.