Page 10 - IJAMD-2-3

International Journal of AI for
Materials and Design AI applications in composite materials

A

B D

C

E

Figure 3. DNNs for composite materials prediction. (A) Structure of ANN and DNN; (B) A schematic illustrating the use of a DNN to predict ground
force by applying capacitance-based self-sensing of the foam core in a sandwich composite. Reprinted with permission from Hong et al. Copyright ©
29
29
2022 Elsevier; (C) Prediction results (peak force, mean crushing force, displacement corresponding to peak force, and effective compression stroke) and
errors for braided-textile reinforced tubular structures. Reprinted with permission from Wang et al. Copyright © 2021 Elsevier; (D) Prediction results
30
30
of macroscopic stiffness and yield strength of unidirectional fiber composites using DNN; (E) Training process of transfer learning for predicting the
31
behavior of composite pressure vessels and comparison with conventional finite element analysis methods. Reprinted with permission from Hong et al.
32
32
Copyright © 2024 Elsevier.
Abbreviations: ANN: Artificial neural network; DEM: Discrete element method; DNN: Deep neural network; FEA: Finite element analysis;
GRF: Generalized random forests; MAE: Mean absolute error; NN: Neural network; RMSE: Root mean squared error.
Volume 2 Issue 3 (2025) 4 doi: 10.36922/IJAMD025210016