预测聚合物熔体粘度的物理强化神经网络

IF 9.4 1区 材料科学 Q1 CHEMISTRY, PHYSICAL
Ayush Jain, Rishi Gurnani, Arunkumar Rajan, H.Jerry Qi, Rampi Ramprasad
{"title":"预测聚合物熔体粘度的物理强化神经网络","authors":"Ayush Jain, Rishi Gurnani, Arunkumar Rajan, H.Jerry Qi, Rampi Ramprasad","doi":"10.1038/s41524-025-01532-6","DOIUrl":null,"url":null,"abstract":"<p>Achieving superior polymeric components through additive manufacturing (AM) relies on precise control of rheology. One rheological property particularly relevant to AM is melt viscosity (<i>η</i>). <i>η</i> is influenced by polymer chemistry, molecular weight (<i>M</i><sub><i>w</i></sub>), polydispersity, shear rate (<span>\\({\\dot{\\gamma}}\\)</span>), and temperature (<i>T</i>). The relationship of <i>η</i> with <i>M</i><sub><i>w</i></sub>, <span>\\({\\dot{\\gamma }}\\)</span>, and <i>T</i> is captured by parameterized equations. Several physical experiments are required to fit the parameters, so predicting <i>η</i> of new polymer materials in unexplored physical domains is laborious. Here, we develop a Physics-Enforced Neural Network (PENN) model that predicts the empirical parameters and encodes the parametrized equations to calculate <i>η</i> as a function of polymer chemistry, <i>M</i><sub><i>w</i></sub>, polydispersity, <span>\\({\\dot{\\gamma }}\\)</span>, and <i>T</i>. We benchmark our PENN against physics-unaware Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) models. We demonstrate that the PENN offers superior values of <i>η</i> when extrapolating to unseen values of <i>M</i><sub><i>w</i></sub>, <span>\\({\\dot{\\gamma }}\\)</span>, and <i>T</i> for sparsely seen polymers.</p>","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"52 1","pages":""},"PeriodicalIF":9.4000,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A physics-enforced neural network to predict polymer melt viscosity\",\"authors\":\"Ayush Jain, Rishi Gurnani, Arunkumar Rajan, H.Jerry Qi, Rampi Ramprasad\",\"doi\":\"10.1038/s41524-025-01532-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Achieving superior polymeric components through additive manufacturing (AM) relies on precise control of rheology. One rheological property particularly relevant to AM is melt viscosity (<i>η</i>). <i>η</i> is influenced by polymer chemistry, molecular weight (<i>M</i><sub><i>w</i></sub>), polydispersity, shear rate (<span>\\\\({\\\\dot{\\\\gamma}}\\\\)</span>), and temperature (<i>T</i>). The relationship of <i>η</i> with <i>M</i><sub><i>w</i></sub>, <span>\\\\({\\\\dot{\\\\gamma }}\\\\)</span>, and <i>T</i> is captured by parameterized equations. Several physical experiments are required to fit the parameters, so predicting <i>η</i> of new polymer materials in unexplored physical domains is laborious. Here, we develop a Physics-Enforced Neural Network (PENN) model that predicts the empirical parameters and encodes the parametrized equations to calculate <i>η</i> as a function of polymer chemistry, <i>M</i><sub><i>w</i></sub>, polydispersity, <span>\\\\({\\\\dot{\\\\gamma }}\\\\)</span>, and <i>T</i>. We benchmark our PENN against physics-unaware Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) models. We demonstrate that the PENN offers superior values of <i>η</i> when extrapolating to unseen values of <i>M</i><sub><i>w</i></sub>, <span>\\\\({\\\\dot{\\\\gamma }}\\\\)</span>, and <i>T</i> for sparsely seen polymers.</p>\",\"PeriodicalId\":19342,\"journal\":{\"name\":\"npj Computational Materials\",\"volume\":\"52 1\",\"pages\":\"\"},\"PeriodicalIF\":9.4000,\"publicationDate\":\"2025-02-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"npj Computational Materials\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1038/s41524-025-01532-6\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"npj Computational Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1038/s41524-025-01532-6","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

通过增材制造(AM)实现优异的聚合物组件依赖于流变学的精确控制。与增材制造特别相关的一个流变性能是熔体粘度(η)。η受聚合物化学性质、分子量(Mw)、多分散性、剪切速率(\({\dot{\gamma}}\))和温度(T)的影响,η与Mw、\({\dot{\gamma }}\)和T的关系通过参数化方程得到。为了拟合这些参数,需要进行多次物理实验,因此在未开发的物理领域预测新聚合物材料的η是非常困难的。在这里,我们开发了一个物理强制神经网络(PENN)模型,该模型预测经验参数并对参数化方程进行编码,以计算η作为聚合物化学,Mw,多分散性,\({\dot{\gamma }}\)和t的函数。我们将PENN与物理不敏感的人工神经网络(ANN)和高斯过程回归(GPR)模型进行了基准测试。我们证明,当外推到未见的Mw, \({\dot{\gamma }}\)和T值时,PENN提供了优越的η值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

A physics-enforced neural network to predict polymer melt viscosity

A physics-enforced neural network to predict polymer melt viscosity

Achieving superior polymeric components through additive manufacturing (AM) relies on precise control of rheology. One rheological property particularly relevant to AM is melt viscosity (η). η is influenced by polymer chemistry, molecular weight (Mw), polydispersity, shear rate (\({\dot{\gamma}}\)), and temperature (T). The relationship of η with Mw, \({\dot{\gamma }}\), and T is captured by parameterized equations. Several physical experiments are required to fit the parameters, so predicting η of new polymer materials in unexplored physical domains is laborious. Here, we develop a Physics-Enforced Neural Network (PENN) model that predicts the empirical parameters and encodes the parametrized equations to calculate η as a function of polymer chemistry, Mw, polydispersity, \({\dot{\gamma }}\), and T. We benchmark our PENN against physics-unaware Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) models. We demonstrate that the PENN offers superior values of η when extrapolating to unseen values of Mw, \({\dot{\gamma }}\), and T for sparsely seen polymers.

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
npj Computational Materials
npj Computational Materials Mathematics-Modeling and Simulation
CiteScore
15.30
自引率
5.20%
发文量
229
审稿时长
6 weeks
期刊介绍: npj Computational Materials is a high-quality open access journal from Nature Research that publishes research papers applying computational approaches for the design of new materials and enhancing our understanding of existing ones. The journal also welcomes papers on new computational techniques and the refinement of current approaches that support these aims, as well as experimental papers that complement computational findings. Some key features of npj Computational Materials include a 2-year impact factor of 12.241 (2021), article downloads of 1,138,590 (2021), and a fast turnaround time of 11 days from submission to the first editorial decision. The journal is indexed in various databases and services, including Chemical Abstracts Service (ACS), Astrophysics Data System (ADS), Current Contents/Physical, Chemical and Earth Sciences, Journal Citation Reports/Science Edition, SCOPUS, EI Compendex, INSPEC, Google Scholar, SCImago, DOAJ, CNKI, and Science Citation Index Expanded (SCIE), among others.
×
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