Finite Element-Based Machine Learning Model for Predicting the Mechanical Properties of Composite Hydrogels
Source abstract
Abstract
In this study, a finite element (FE)-based machine learning model was developed to predict the mechanical properties of bioglass (BG)-collagen (COL) composite hydrogels. Based on the experimental observation of BG-COL composite hydrogels with scanning electron microscope, 2000 microstructural images with randomly distributed BG particles were created. The BG particles have diameters ranging from 0.5 µm to 1.5 µm and a volume fraction from 17% to 59%. FE simulations of tensile testing were performed for calculating the Young’s modulus and Poisson’s ratio of 2000 microstructures. The microstructural images and the calculated Young’s modulus and Poisson’s ratio by FE simulation were used for training and testing a convolutional neural network regression model. Results showed that the network developed in this work can effectively predict the mechanical properties of the composite hydrogels. The R-squared values were 95% and 83% for Young’s modulus and Poisson’s ratio, respectively. This work provides a surrogate model of finite element analysis to predict mechanical properties of BG-COL hydrogel using microstructure images, which could be further utilized for characterizing heterogeneous materials in big data-driven material designs.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Collagen: Extraction and Characterization · Advanced machining processes and optimization · Infrared Thermography in Medicine
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Biomedical and Chemical Engineering and Sciences, Florida Institute of Technology, Melbourne, FL 32901, USA
Department of Mechanical and Materials Engineering, University of Nebraska, Lincoln, NE 68588, USA
References (40)
Show source-provided references
1. In vitro apatite forming ability of type I collagen hydrogels containing bioactive glass and silica sol-gel particles10.1007/s10856-006-6820-6 ↗
2. Combining collagen and bioactive glasses for bone tissue engineering: A review10.1002/adhm.201400302 ↗
3. Bioglass incorporated methacrylated collagen bioactive ink for 3D printing of bone tissue10.1088/1748-605X/abc744 ↗
4. Improvements in mechanical properties of collagen-based scaffolds for tissue engineering10.1016/j.cobme.2020.100253 ↗
5. Optimization of Freeze-FRESH Methodology for 3D Printing of Microporous Collagen Constructs10.1089/3dp.2020.0311 ↗
6. Effective properties of a fly ash geopolymer: Synergistic application of X-ray synchrotron tomography, nanoindentation, and homogenization models10.1016/j.cemconres.2015.08.004 ↗
7. Double-inclusion model and overall moduli of multi-phase composites10.1016/0167-6636(93)90066-Z ↗
8. Double inclusion model for approximate elastic moduli of concrete material10.1016/0008-8846(95)00196-4 ↗
9. Prediction of the thermomechanical behavior of particle-reinforced metal matrix composites10.1016/j.compositesb.2012.09.056 ↗
10. Perturbation-based stochastic multi-scale computational homogenization method for woven textile composites10.1016/j.ijsolstr.2015.09.008 ↗
11. Novel implementation of homogenization method to predict effective properties of periodic materials10.1007/s10409-013-0043-0 ↗
12. Development of an ABAQUS plugin tool for periodic RVE homogenisation10.1007/s00366-018-0616-4 ↗
13. Statistically equivalent representative volume elements for unidirectional composite microstructures: Part I-Without damage10.1177/0021998305055273 ↗
14. Artificial intelligence and machine learning in design of mechanical materials10.1039/D0MH01451F ↗
15. Shokrollahi, Y., Dong, P., Kaya, M., Suh, D.W., and Gu, L. (2022). Rapid Prediction of Retina Stress and Strain Patterns in Soccer-Related Ocular Injury: Integrating Finite Element Analysis with Machine Learning Approach. Diagnostics, 12.10.3390/diagnostics12071530 ↗
16. Dong, P., Ye, G., Kaya, M., and Gu, L. (2020). Simulation-Driven Machine Learning for Predicting Stent Expansion in Calcified Coronary Artery. Appl. Sci., 10.10.3390/app10175820 ↗
17. Predicting elemental stiffness matrix of FG nanoplates using Gaussian Process Regression based surrogate model in framework of layerwise model10.1016/j.enganabound.2022.08.001 ↗
18. Insightful classification of crystal structures using deep learning10.1038/s41467-018-05169-6 ↗
19. Machine learning plastic deformation of crystals10.1038/s41467-018-07737-2 ↗
20. Deep neural network method for predicting the mechanical properties of composites10.1063/1.5124529 ↗
21. Deep learning method for determining the surface elastic moduli of microstructured solids10.1016/j.eml.2021.101226 ↗
22. Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis10.1016/j.commatsci.2021.110328 ↗
23. Prediction of composite microstructure stress-strain curves using convolutional neural networks10.1016/j.matdes.2020.108509 ↗
24. Machine-learning based design of active composite structures for 4D printing10.1088/1361-665X/ab1439 ↗
25. Ponnusami, S.A. (2021). From Microstructural Images to Properties—An Interpretable Deep Learning Approach to Predict Elastic-Plastic Properties of Fiber Composites.10.31224/osf.io/w6mgv ↗
26. Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods10.1016/j.ijheatmasstransfer.2018.08.082 ↗
27. Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods10.1016/j.compscitech.2019.107861 ↗
28. Prediction and validation of the transverse mechanical behavior of unidirectional composites considering interfacial debonding through convolutional neural networks10.1016/j.compositesb.2021.109314 ↗
29. In vitro bioactivity and physical–mechanical properties of MnO2 substituted 45S5 bioactive glasses and glass-ceramics10.1166/jbt.2012.1043 ↗
30. Wang, Y., Xue, Y., Wang, J., Zhu, Y., Zhu, Y., Zhang, X., Liao, J., Li, X., Wu, X., and Qin, Y.-X. (2019). A composite hydrogel with high mechanical strength, fluorescence, and degradable behavior for bone tissue engineering. Polymers, 11.10.3390/polym11071112 ↗
31. Prediction of composite properties from a representative volume element10.1016/0266-3538(95)00141-7 ↗
32. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2–4). {TensorFlow}: A system for {Large-Scale} machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA.
33. Agarap, A.F. (2018). Deep learning using rectified linear units (relu). arXiv.
34. Dropout: A simple way to prevent neural networks from overfitting
35. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
36. Experimental characterization of composites to support an orthotropic plasticity material model10.1177/0021998317733319 ↗
37. Material design of economical ultra-high performance concrete (UHPC) and evaluation of their properties10.1016/j.cemconcomp.2019.103346 ↗
38. Mobasher, B., Arora, A., Aguayo, M., Kianmofrad, F., Yao, Y., and Neithalath, N. (2019). Developing Ultra-High–Performance Concrete Mix Designs for Arizona Bridge Element Connections, Department of Transportation, Research Center.
39. Crack propagation and strain localization in metallic particulate-reinforced cementitious mortars10.1016/j.matdes.2015.04.038 ↗
40. Measurements and predictions of the viscoelastic properties of a composite lamina and their sensitivity to temperature and frequency10.1016/j.compscitech.2017.06.005 ↗