Transformer-Based Mechanical Property Prediction for Polymer Matrix Composites

IF 2.9 4区 工程技术 Q2 CHEMISTRY, MULTIDISCIPLINARY Korean Journal of Chemical Engineering Pub Date : 2024-08-07 DOI:10.1007/s11814-024-00247-6
Jaewook Lee, Jinkyung Son, Juri Lim, In Kim, Seonwoo Kim, Namjung Cho, Woojin Choi, Dongil Shin
{"title":"Transformer-Based Mechanical Property Prediction for Polymer Matrix Composites","authors":"Jaewook Lee,&nbsp;Jinkyung Son,&nbsp;Juri Lim,&nbsp;In Kim,&nbsp;Seonwoo Kim,&nbsp;Namjung Cho,&nbsp;Woojin Choi,&nbsp;Dongil Shin","doi":"10.1007/s11814-024-00247-6","DOIUrl":null,"url":null,"abstract":"<div><p>Combinatorial nature of polymer matrix composites design requires a robust predictive model to accurately predict the mechanical properties of polymer composites, thereby reducing the need for extensive and costly trial-and-error approaches in their manufacturing. However, traditional prediction models have been either lacking in accuracy or too resource-intensive for practical use. This study proposes an advanced Transformer-based predictive model simultaneously considering various variables that can influence mechanical properties, while utilizing only a minimal amount of training data. In developing this model, we utilize an extensive dataset across 294 types of polymer composites, using a diverse range of polymers and reinforcements, providing a comprehensive basis for the model’s predictions. The model employs a Transformer-based transfer learning technique, known for its efficiency with small datasets, to predict essential mechanical properties such as tensile strength, tensile modulus, flexural strength, flexural modulus and density. It shows high predictive accuracy (<i>R</i><sup>2</sup> = 92%) and makes reliable predictions for combinations of polymer composites that have not been trained on (<i>R</i><sup>2</sup> = 82%). Additionally, the model’s effectiveness and learning process are validated through Explainable Artificial Intelligence analysis and latent space visualization.</p></div>","PeriodicalId":684,"journal":{"name":"Korean Journal of Chemical Engineering","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Korean Journal of Chemical Engineering","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s11814-024-00247-6","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Combinatorial nature of polymer matrix composites design requires a robust predictive model to accurately predict the mechanical properties of polymer composites, thereby reducing the need for extensive and costly trial-and-error approaches in their manufacturing. However, traditional prediction models have been either lacking in accuracy or too resource-intensive for practical use. This study proposes an advanced Transformer-based predictive model simultaneously considering various variables that can influence mechanical properties, while utilizing only a minimal amount of training data. In developing this model, we utilize an extensive dataset across 294 types of polymer composites, using a diverse range of polymers and reinforcements, providing a comprehensive basis for the model’s predictions. The model employs a Transformer-based transfer learning technique, known for its efficiency with small datasets, to predict essential mechanical properties such as tensile strength, tensile modulus, flexural strength, flexural modulus and density. It shows high predictive accuracy (R2 = 92%) and makes reliable predictions for combinations of polymer composites that have not been trained on (R2 = 82%). Additionally, the model’s effectiveness and learning process are validated through Explainable Artificial Intelligence analysis and latent space visualization.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于变压器的聚合物基复合材料机械性能预测
聚合物基复合材料设计的组合性质需要一个强大的预测模型来准确预测聚合物复合材料的机械性能,从而减少在其制造过程中大量昂贵的试错方法。然而,传统的预测模型要么缺乏准确性,要么过于耗费资源而无法实际使用。本研究提出了一种基于变压器的先进预测模型,该模型同时考虑了可能影响机械性能的各种变量,同时只需利用极少量的训练数据。在开发该模型的过程中,我们利用了涉及 294 种聚合物复合材料的大量数据集,使用了多种聚合物和增强材料,为模型的预测提供了全面的基础。该模型采用了基于 Transformer 的迁移学习技术(该技术以高效处理小型数据集而著称)来预测拉伸强度、拉伸模量、弯曲强度、弯曲模量和密度等基本机械性能。该模型显示出较高的预测准确性(R2 = 92%),并能对未经训练的聚合物复合材料组合做出可靠的预测(R2 = 82%)。此外,还通过可解释人工智能分析和潜空间可视化验证了模型的有效性和学习过程。
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 去求助
来源期刊
Korean Journal of Chemical Engineering
Korean Journal of Chemical Engineering 工程技术-工程:化工
CiteScore
4.60
自引率
11.10%
发文量
310
审稿时长
4.7 months
期刊介绍: The Korean Journal of Chemical Engineering provides a global forum for the dissemination of research in chemical engineering. The Journal publishes significant research results obtained in the Asia-Pacific region, and simultaneously introduces recent technical progress made in other areas of the world to this region. Submitted research papers must be of potential industrial significance and specifically concerned with chemical engineering. The editors will give preference to papers having a clearly stated practical scope and applicability in the areas of chemical engineering, and to those where new theoretical concepts are supported by new experimental details. The Journal also regularly publishes featured reviews on emerging and industrially important subjects of chemical engineering as well as selected papers presented at international conferences on the subjects.
期刊最新文献
Dynamic Maintenance of Underground Pipelines via a Systematic Approach for Conservative Estimation of Pipeline Defect Probability Density Under Data Scarcity Highly Electrocatalytic Activity of Micro and Nanocomposite Phase Engineering of MoO3−x@K3PW12O40 Decorated on Graphite Felt for High-Performance VRFB Time-Lapse Traces of Transformation of CdTe Nanoparticles into Nanowires via Self-Assembly GPT Prompt Engineering for a Large Language Model-Based Process Improvement Generation System Identification of Representative Wind Power Fluctuation Patterns for Water Electrolysis Device Stress Testing: A Data Mining Approach
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1