Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations
Epoxy resin is an of the most widely used adhesives for various applications owing to its outstanding properties. The performance of epoxy systems varies significantly depending on the composition of the base resin and curing agent. However, there are limitations in exploring numerous formulations o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Nanomaterials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-4991/12/14/2353 |
| _version_ | 1797433269390671872 |
|---|---|
| author | Joohee Choi Haisu Kang Ji Hee Lee Sung Hyun Kwon Seung Geol Lee |
| author_facet | Joohee Choi Haisu Kang Ji Hee Lee Sung Hyun Kwon Seung Geol Lee |
| author_sort | Joohee Choi |
| collection | DOAJ |
| description | Epoxy resin is an of the most widely used adhesives for various applications owing to its outstanding properties. The performance of epoxy systems varies significantly depending on the composition of the base resin and curing agent. However, there are limitations in exploring numerous formulations of epoxy resins to optimize adhesive properties because of the expense and time-consuming nature of the trial-and-error process. Herein, molecular dynamics (MD) simulations and machine learning (ML) methods were used to overcome these challenges and predict the adhesive properties of epoxy resin. Datasets for diverse epoxy adhesive formulations were constructed by considering the degree of crosslinking, density, free volume, cohesive energy density, modulus, and glass transition temperature. A linear correlation analysis demonstrated that the content of the curing agents, especially dicyandiamide (DICY), had the greatest correlation with the cohesive energy density. Moreover, the content of tetraglycidyl methylene dianiline (TGMDA) had the highest correlation with the modulus, and the content of diglycidyl ether of bisphenol A (DGEBA) had the highest correlation with the glass transition temperature. An optimized artificial neural network (ANN) model was constructed using test sets divided from MD datasets through error and linear regression analyses. The root mean square error (RMSE) and correlation coefficient (<i>R</i><sup>2</sup>) showed the potential of each model in predicting epoxy properties, with high linear correlations (0.835–0.986). This technique can be extended for optimizing the composition of other epoxy resin systems. |
| first_indexed | 2024-03-09T10:14:37Z |
| format | Article |
| id | doaj.art-a6534d3190a24ca18441fc9c226cb692 |
| institution | Directory Open Access Journal |
| issn | 2079-4991 |
| language | English |
| last_indexed | 2024-03-09T10:14:37Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Nanomaterials |
| spelling | doaj.art-a6534d3190a24ca18441fc9c226cb6922023-12-01T22:30:56ZengMDPI AGNanomaterials2079-49912022-07-011214235310.3390/nano12142353Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics SimulationsJoohee Choi0Haisu Kang1Ji Hee Lee2Sung Hyun Kwon3Seung Geol Lee4School of Chemical Engineering, Pusan National University, Busan 46241, KoreaDepartment of Chemical and Biomolecular Engineering, University of Illinois at Urbana Champaign, Urbana, IL 61801, USASchool of Chemical Engineering, Pusan National University, Busan 46241, KoreaSchool of Chemical Engineering, Pusan National University, Busan 46241, KoreaSchool of Chemical Engineering, Pusan National University, Busan 46241, KoreaEpoxy resin is an of the most widely used adhesives for various applications owing to its outstanding properties. The performance of epoxy systems varies significantly depending on the composition of the base resin and curing agent. However, there are limitations in exploring numerous formulations of epoxy resins to optimize adhesive properties because of the expense and time-consuming nature of the trial-and-error process. Herein, molecular dynamics (MD) simulations and machine learning (ML) methods were used to overcome these challenges and predict the adhesive properties of epoxy resin. Datasets for diverse epoxy adhesive formulations were constructed by considering the degree of crosslinking, density, free volume, cohesive energy density, modulus, and glass transition temperature. A linear correlation analysis demonstrated that the content of the curing agents, especially dicyandiamide (DICY), had the greatest correlation with the cohesive energy density. Moreover, the content of tetraglycidyl methylene dianiline (TGMDA) had the highest correlation with the modulus, and the content of diglycidyl ether of bisphenol A (DGEBA) had the highest correlation with the glass transition temperature. An optimized artificial neural network (ANN) model was constructed using test sets divided from MD datasets through error and linear regression analyses. The root mean square error (RMSE) and correlation coefficient (<i>R</i><sup>2</sup>) showed the potential of each model in predicting epoxy properties, with high linear correlations (0.835–0.986). This technique can be extended for optimizing the composition of other epoxy resin systems.https://www.mdpi.com/2079-4991/12/14/2353epoxy resinmolecular dynamicsmachine learningartificial neural networkadhesive strength |
| spellingShingle | Joohee Choi Haisu Kang Ji Hee Lee Sung Hyun Kwon Seung Geol Lee Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations Nanomaterials epoxy resin molecular dynamics machine learning artificial neural network adhesive strength |
| title | Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations |
| title_full | Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations |
| title_fullStr | Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations |
| title_full_unstemmed | Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations |
| title_short | Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations |
| title_sort | predicting the properties of high performance epoxy resin by machine learning using molecular dynamics simulations |
| topic | epoxy resin molecular dynamics machine learning artificial neural network adhesive strength |
| url | https://www.mdpi.com/2079-4991/12/14/2353 |
| work_keys_str_mv | AT jooheechoi predictingthepropertiesofhighperformanceepoxyresinbymachinelearningusingmoleculardynamicssimulations AT haisukang predictingthepropertiesofhighperformanceepoxyresinbymachinelearningusingmoleculardynamicssimulations AT jiheelee predictingthepropertiesofhighperformanceepoxyresinbymachinelearningusingmoleculardynamicssimulations AT sunghyunkwon predictingthepropertiesofhighperformanceepoxyresinbymachinelearningusingmoleculardynamicssimulations AT seunggeollee predictingthepropertiesofhighperformanceepoxyresinbymachinelearningusingmoleculardynamicssimulations |