Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.6
5.0
Journals
Polymers
Special Issues
Scientific Machine Learning for Polymeric Materials
share announcement

Scientific Machine Learning for Polymeric Materials

A special issue of Polymers (ISSN 2073-4360). This special issue belongs to the section "Smart and Functional Polymers".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 5077

Special Issue Editors

Dr. Salah A. Faroughi

E-Mail Website
Guest Editor
Geo-Intelligence Laboratory, Ingram School of Engineering, Texas State University, San Marcos, TX 78666, USA
Interests: data intelligence; rheology; viscoelastic fluids; complex fluids; physics-based deep learning
Special Issues, Collections and Topics in MDPI journals
Dr. Célio Bruno Pinto Fernandes

E-Mail Website
Guest Editor
Institute for Polymers and Composites, University of Minho, Campus de Azurém, 4800-058 Guimarães, Portugal
Interests: rheology; swelling; viscosity and viscoelasticity; polymers at interfaces and in confined spaces; numerical simulation; constitutive and multiscale modeling
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Polymeric materials play a key role in supporting the ever-increasing demand for electronics, medicines, plastics, sensors, and the transition to renewable energy sources. This is achieved through polymers’ distinct features at different structural and temporal scales (i.e., a subtle change in their atomic or mesoscopic structures leads to a totally emergent functionality). However, the design of new polymeric materials is still a lengthy process. This grand challenge is related to the lack of capability to comprehensively bridge phenomena that occur at temporal scales from tens of nanoseconds to seconds or spatial scales from nanometers to meters. Indeed, scientific datasets in this field are sparse, and include only directly observable quantities, while the underlying processes are either too complex to observe directly or are completely unknown. To move towards an accelerated on-demand design for polymeric materials, recent breakthroughs in scientific machine learning (SciML) can be leveraged to explore the interactions of physics at different spatial and temporal scales. In pursuit of this objective, we designed this Special Issue to bring together researchers working on SciML (e.g., physics-guided neural networks, physics-informed neural networks, physics-encoded neural networks, and neural operators) to exchange ideas, identify and address grand challenges, and possibly reveal multi-scale multi-temporal structures and mechanisms in polymer behaviors (rheology, self-assembly, phase transition, etc.) that can better serve the community to design polymeric materials in shorter time-frames—that is, accelerated on-demand material design.

Dr. Salah A. Faroughi
Dr. Célio Bruno Pinto Fernandes
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Polymers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • scientific machine learning
  • physics-based deep learning
  • physics-guided neural networks
  • physics-informed neural networks
  • polymer simulation
  • viscoelastic fluids

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 9115 KiB  
Article
Predicting Diffusion Coefficients in Nafion Membranes during the Soaking Process Using a Machine Learning Approach
by Ivan Malashin, Daniil Daibagya, Vadim Tynchenko, Andrei Gantimurov, Vladimir Nelyub and Aleksei Borodulin
Polymers 2024, 16(9), 1204; https://doi.org/10.3390/polym16091204 - 25 Apr 2024
Viewed by 370
Abstract
Nafion, a versatile polymer used in electrochemistry and membrane technologies, exhibits complex behaviors in saline environments. This study explores Nafion membrane’s IR spectra during soaking and subsequent drying processes in salt solutions at various concentrations. Utilizing the principles of Fick’s second law, diffusion [...] Read more.
Nafion, a versatile polymer used in electrochemistry and membrane technologies, exhibits complex behaviors in saline environments. This study explores Nafion membrane’s IR spectra during soaking and subsequent drying processes in salt solutions at various concentrations. Utilizing the principles of Fick’s second law, diffusion coefficients for these processes are derived via exponential approximation. By harnessing machine learning (ML) techniques, including the optimization of neural network hyperparameters via a genetic algorithm (GA) and leveraging various regressors, we effectively pinpointed the optimal model for predicting diffusion coefficients. Notably, for the prediction of soaking coefficients, our model is composed of layers with 64, 64, 32, and 16 neurons, employing ReLU, ELU, sigmoid, and ELU activation functions, respectively. Conversely, for drying coefficients, our model features two hidden layers with 16 and 12 neurons, utilizing sigmoid and ELU activation functions, respectively. Full article
(This article belongs to the Special Issue Scientific Machine Learning for Polymeric Materials)
►▼ Show Figures

Figure 1

27 pages, 763 KiB  
Article
Estimation and Prediction of the Polymers’ Physical Characteristics Using the Machine Learning Models
by Ivan Pavlovich Malashin, Vadim Sergeevich Tynchenko, Vladimir Aleksandrovich Nelyub, Aleksei Sergeevich Borodulin and Andrei Pavlovich Gantimurov
Polymers 2024, 16(1), 115; https://doi.org/10.3390/polym16010115 - 29 Dec 2023
Cited by 4 | Viewed by 1794
Abstract
This article investigates the utility of machine learning (ML) methods for predicting and analyzing the diverse physical characteristics of polymers. Leveraging a rich dataset of polymers’ characteristics, the study encompasses an extensive range of polymer properties, spanning compressive and tensile strength to thermal [...] Read more.
This article investigates the utility of machine learning (ML) methods for predicting and analyzing the diverse physical characteristics of polymers. Leveraging a rich dataset of polymers’ characteristics, the study encompasses an extensive range of polymer properties, spanning compressive and tensile strength to thermal and electrical behaviors. Using various regression methods like Ensemble, Tree-based, Regularization, and Distance-based, the research undergoes thorough evaluation using the most common quality metrics. As a result of a series of experimental studies on the selection of effective model parameters, those that provide a high-quality solution to the stated problem were found. The best results were achieved by Random Forest with the highest R2 scores of 0.71, 0.73, and 0.88 for glass transition, thermal decomposition, and melting temperatures, respectively. The outcomes are intricately compared, providing valuable insights into the efficiency of distinct ML approaches in predicting polymer properties. Unknown values for each characteristic were predicted, and a method validation was performed by training on the predicted values, comparing the results with the specified variance values of each characteristic. The research not only advances our comprehension of polymer physics but also contributes to informed model selection and optimization for materials science applications. Full article
(This article belongs to the Special Issue Scientific Machine Learning for Polymeric Materials)
►▼ Show Figures

Figure 1

13 pages, 2058 KiB  
Article
Predicting the Performance of Functional Materials Composed of Polymeric Multicomponent Systems Using Artificial Intelligence—Formulations of Cleansing Foams as an Example
by Masugu Hamaguchi, Hideki Miwake, Ryoichi Nakatake and Noriyoshi Arai
Polymers 2023, 15(21), 4216; https://doi.org/10.3390/polym15214216 - 25 Oct 2023
Cited by 1 | Viewed by 1087
Abstract
Cleansing foam is a common multicomponent polymeric functional material. It contains ingredients in innumerable combinations, which makes formulation optimization challenging. In this study, we used artificial intelligence (AI) with machine learning to develop a cleansing capability prediction system that considers the effects of [...] Read more.
Cleansing foam is a common multicomponent polymeric functional material. It contains ingredients in innumerable combinations, which makes formulation optimization challenging. In this study, we used artificial intelligence (AI) with machine learning to develop a cleansing capability prediction system that considers the effects of self-assembled structures and chemical properties of ingredients. Over 500 cleansing foam samples were prepared and tested. Molecular descriptors and Hansen solubility index were used to estimate the cleansing capabilities of each formulation set. We used five machine-learning models to predict the cleansing capability. In addition, we employed an in silico formulation by generating virtual formulations and predicting their cleansing capabilities using an established AI model. The achieved accuracy was R2 = 0.770. Our observations revealed that mixtures of cosmetic ingredients exhibit complex interactions, resulting in nonlinear behavior, which adds to the complexity of predicting cleansing performance. Nevertheless, accurate chemical property descriptors, along with the aid of in silico formulations, enabled the identification of potential ingredients. We anticipate that our system will efficiently predict the chemical properties of polymer-containing blends. Full article
(This article belongs to the Special Issue Scientific Machine Learning for Polymeric Materials)
►▼ Show Figures

Figure 1

15 pages, 4611 KiB  
Article
Hysteresis Behavior Modeling of Magnetorheological Elastomers under Impact Loading Using a Multilayer Exponential-Based Preisach Model Enhanced with Particle Swarm Optimization
by Alawiyah Hasanah Mohd. Alawi, Khisbullah Hudha, Zulkiffli Abd. Kadir and Noor Hafizah Amer
Polymers 2023, 15(9), 2145; https://doi.org/10.3390/polym15092145 - 30 Apr 2023
Cited by 2 | Viewed by 1174
Abstract
Magnetorheological elastomers (MREs) are a type of smart material that can change their mechanical properties in response to external magnetic fields. These unique properties make them ideal for various applications, including vibration control, noise reduction, and shock absorption. This paper presents an approach [...] Read more.
Magnetorheological elastomers (MREs) are a type of smart material that can change their mechanical properties in response to external magnetic fields. These unique properties make them ideal for various applications, including vibration control, noise reduction, and shock absorption. This paper presents an approach for modeling the impact behavior of MREs. The proposed model uses a combination of exponential functions arranged in a multi-layer Preisach model to capture the nonlinear behavior of MREs under impact loads. The model is trained using particle swarm optimization (PSO) and validated using experimental data from drop impact tests conducted on MRE samples under various magnetic field strengths. The results demonstrate that the proposed model can accurately predict the impact behavior of MREs, making it a useful tool for designing MRE-based devices that require precise control of their impact response. The model’s response closely matches the experimental data with a maximum prediction error of 10% or less. Furthermore, the interpolated model’s response is in agreement with the experimental data with a maximum percentage error of less than 8.5%. Full article
(This article belongs to the Special Issue Scientific Machine Learning for Polymeric Materials)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop