机器学习辅助莫来石刚玉陶瓷多性能预测及烧结机理探讨。

IF 3.1 3区 材料科学 Q3 CHEMISTRY, PHYSICAL
Materials Pub Date : 2025-03-20 DOI:10.3390/ma18061384
Qingyue Chen, Weijin Zhang, Xiaocheng Liang, Hao Feng, Weibin Xu, Pengrui Wang, Jian Pan, Benjun Cheng
{"title":"机器学习辅助莫来石刚玉陶瓷多性能预测及烧结机理探讨。","authors":"Qingyue Chen, Weijin Zhang, Xiaocheng Liang, Hao Feng, Weibin Xu, Pengrui Wang, Jian Pan, Benjun Cheng","doi":"10.3390/ma18061384","DOIUrl":null,"url":null,"abstract":"<p><p>Mullite-corundum ceramics are pivotal in heat transfer pipelines and thermal energy storage systems due to their excellent mechanical properties, thermal stability, and chemical resistance. Establishing relationships and mechanisms through traditional experiments is time-consuming and labor-intensive. In this study, gradient boosting regression (GBR), random forest (RF), and artificial neural network (ANN) models were developed to predict essential properties such as apparent porosity, bulk density, water absorption, and flexural strength of mullite-corundum ceramics. The GBR model (<i>R</i><sup>2</sup> 0.91-0.95) outperformed the RF and ANN models (<i>R</i><sup>2</sup> 0.83-0.89 and 0.88-0.91, respectively) in accuracy. Feature importance and partial dependence analyses revealed that sintering temperature and K<sub>2</sub>O (~0.25%) positively affected bulk density while negatively influencing apparent porosity and water absorption. Additionally, sintering temperature, additives, and Fe<sub>2</sub>O<sub>3</sub> (optimal content ~5% and 1%, respectively) were positively related to flexural strength. This approach provided new insight into the relationships between feedstock compositions and sintering process parameters and ceramic properties, and it explored the possible mechanisms involved.</p>","PeriodicalId":18281,"journal":{"name":"Materials","volume":"18 6","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11943972/pdf/","citationCount":"0","resultStr":"{\"title\":\"Machine Learning-Assisted Multi-Property Prediction and Sintering Mechanism Exploration of Mullite-Corundum Ceramics.\",\"authors\":\"Qingyue Chen, Weijin Zhang, Xiaocheng Liang, Hao Feng, Weibin Xu, Pengrui Wang, Jian Pan, Benjun Cheng\",\"doi\":\"10.3390/ma18061384\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Mullite-corundum ceramics are pivotal in heat transfer pipelines and thermal energy storage systems due to their excellent mechanical properties, thermal stability, and chemical resistance. Establishing relationships and mechanisms through traditional experiments is time-consuming and labor-intensive. In this study, gradient boosting regression (GBR), random forest (RF), and artificial neural network (ANN) models were developed to predict essential properties such as apparent porosity, bulk density, water absorption, and flexural strength of mullite-corundum ceramics. The GBR model (<i>R</i><sup>2</sup> 0.91-0.95) outperformed the RF and ANN models (<i>R</i><sup>2</sup> 0.83-0.89 and 0.88-0.91, respectively) in accuracy. Feature importance and partial dependence analyses revealed that sintering temperature and K<sub>2</sub>O (~0.25%) positively affected bulk density while negatively influencing apparent porosity and water absorption. Additionally, sintering temperature, additives, and Fe<sub>2</sub>O<sub>3</sub> (optimal content ~5% and 1%, respectively) were positively related to flexural strength. This approach provided new insight into the relationships between feedstock compositions and sintering process parameters and ceramic properties, and it explored the possible mechanisms involved.</p>\",\"PeriodicalId\":18281,\"journal\":{\"name\":\"Materials\",\"volume\":\"18 6\",\"pages\":\"\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2025-03-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11943972/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Materials\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.3390/ma18061384\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.3390/ma18061384","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

莫来石刚玉陶瓷由于其优异的机械性能、热稳定性和耐化学性,在传热管道和热能储存系统中发挥着关键作用。通过传统的实验建立关系和机制是费时费力的。本研究采用梯度增强回归(GBR)、随机森林(RF)和人工神经网络(ANN)模型来预测莫来石刚玉陶瓷的基本性能,如表观孔隙率、体积密度、吸水率和抗弯强度。GBR模型(R2 0.91-0.95)的准确率优于RF和ANN模型(R2分别为0.83-0.89和0.88-0.91)。特征重要性和部分依赖性分析表明,烧结温度和K2O(~0.25%)对容重有积极影响,对表观孔隙率和吸水率有消极影响。此外,烧结温度、添加剂和Fe2O3(最佳含量分别为5%和1%)与抗弯强度呈正相关。该方法为原料成分与烧结工艺参数和陶瓷性能之间的关系提供了新的见解,并探讨了可能涉及的机制。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Machine Learning-Assisted Multi-Property Prediction and Sintering Mechanism Exploration of Mullite-Corundum Ceramics.

Mullite-corundum ceramics are pivotal in heat transfer pipelines and thermal energy storage systems due to their excellent mechanical properties, thermal stability, and chemical resistance. Establishing relationships and mechanisms through traditional experiments is time-consuming and labor-intensive. In this study, gradient boosting regression (GBR), random forest (RF), and artificial neural network (ANN) models were developed to predict essential properties such as apparent porosity, bulk density, water absorption, and flexural strength of mullite-corundum ceramics. The GBR model (R2 0.91-0.95) outperformed the RF and ANN models (R2 0.83-0.89 and 0.88-0.91, respectively) in accuracy. Feature importance and partial dependence analyses revealed that sintering temperature and K2O (~0.25%) positively affected bulk density while negatively influencing apparent porosity and water absorption. Additionally, sintering temperature, additives, and Fe2O3 (optimal content ~5% and 1%, respectively) were positively related to flexural strength. This approach provided new insight into the relationships between feedstock compositions and sintering process parameters and ceramic properties, and it explored the possible mechanisms involved.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Materials
Materials MATERIALS SCIENCE, MULTIDISCIPLINARY-
CiteScore
5.80
自引率
14.70%
发文量
7753
审稿时长
1.2 months
期刊介绍: Materials (ISSN 1996-1944) is an open access journal of related scientific research and technology development. It publishes reviews, regular research papers (articles) and short communications. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. Therefore, there is no restriction on the length of the papers. The full experimental details must be provided so that the results can be reproduced. Materials provides a forum for publishing papers which advance the in-depth understanding of the relationship between the structure, the properties or the functions of all kinds of materials. Chemical syntheses, chemical structures and mechanical, chemical, electronic, magnetic and optical properties and various applications will be considered.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信