iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: http://pubmed.ncbi.nlm.nih.gov/35889577/
Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jul 9;12(14):2353.
doi: 10.3390/nano12142353.

Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations

Joohee Choi  1 , Haisu Kang  2 , Ji Hee Lee  1 , Sung Hyun Kwon  1 , Seung Geol Lee  1   3
Affiliations

Predicting the Properties of High-Performance Epoxy Resin by Machine Learning Using Molecular Dynamics Simulations

Joohee Choi et al. Nanomaterials (Basel). .

Abstract

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 (R2) 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.

Keywords: adhesive strength; artificial neural network; epoxy resin; machine learning; molecular dynamics.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Molecular structures of (a) base resins (DGEBA, DGEBF, TGAP, TGMDA) and (b) curing agents (33DDS, 44DDS, DICY) that compose epoxy resin systems.
Scheme 1
Scheme 1
Schematic view of a strategy for crosslinking in MD simulations.
Figure 2
Figure 2
Example of the equilibrated structures of the epoxy resin system.
Figure 3
Figure 3
Pearson correlation coefficients for relationships (a) between input variables and cohesive energy density, (b) between input variables and modulus, and (c) between input variables and glass transition temperature.
Figure 4
Figure 4
Artificial neural network (ANN) models for predicting (a) cohesive energy density, (b) modulus, and (c) glass transition temperature. The cyan circles of ANN models indicate neurons of input layer, and the blue, red and green circles show neurons of hidden layers. The yellow circles indicate neurons of output layer.
Figure 5
Figure 5
(a) Correlation of cohesive energy density predicted by ANN with actual cohesive energy density, (b) correlation of modulus predicted by ANN with actual modulus, and (c) correlation of glass transition temperature predicted by ANN with actual glass transition temperature.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Ma H., Zhang X., Ju F., Tsai S.-B. A study on curing kinetics of nano-phase modified epoxy resin. Sci. Rep. 2018;8:3045. doi: 10.1038/s41598-018-21208-0. - DOI - PMC - PubMed
    1. Wang Z., Liang Z., Wang B., Zhang C., Kramer L. Processing and property investigation of single-walled carbon nanotube (SWNT) buckypaper/epoxy resin matrix nanocomposites. Compos. Part A Appl. Sci. Manuf. 2004;35:1225–1232. doi: 10.1016/j.compositesa.2003.09.029. - DOI
    1. Robertson I.D., Yourdkhani M., Centellas P.J., Aw J.E., Ivanoff D.G., Goli E., Lloyd E.M., Dean L.M., Sottos N.R., Geubelle P.H. Rapid energy-efficient manufacturing of polymers and composites via frontal polymerization. Nature. 2018;557:223–227. doi: 10.1038/s41586-018-0054-x. - DOI - PubMed
    1. Zheng P., Wang R., Wang D., Peng X., Zhao Y., Liu Q. A phosphorus-containing hyperbranched phthalocyanine flame retardant for epoxy resins. Sci. Rep. 2021;11:17731. doi: 10.1038/s41598-021-96927-y. - DOI - PMC - PubMed
    1. Hartshorn S.R. Structural Adhesives: Chemistry and Technology. Springer Science & Business Media; Berlin/Heidelberg, Germany: 2012.

LinkOut - more resources