Details
Original language | English |
---|---|
Article number | 2556 |
Journal | Applied Sciences (Switzerland) |
Volume | 10 |
Issue number | 7 |
Publication status | Published - 8 Apr 2020 |
Abstract
This manuscript introduces a computational approach to micro-damage problems using deep learning for the prediction of loading deflection curves. The location of applied forces, dimensions of the specimen and material parameters are used as inputs of the process. The micro-damage is modelled with a gradient-enhanced damage model which ensures the well-posedness of the boundary value and yields mesh-independent results in computational methods such as FEM. We employ the Adam optimizer and Rectified linear unit activation function for training processes and research into the deep neural network architecture. The performance of our approach is demonstrated through some numerical examples including the three-point bending specimen, shear bending on L-shaped specimen and different failure mechanisms.
Keywords
- Deep learning, Deep neural network, Gradient enhanced damage, Stress-level dependent damage model
ASJC Scopus subject areas
- Materials Science(all)
- Physics and Astronomy(all)
- Instrumentation
- Engineering(all)
- Chemical Engineering(all)
- Process Chemistry and Technology
- Computer Science(all)
- Computer Science Applications
- Chemical Engineering(all)
- Fluid Flow and Transfer Processes
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Applied Sciences (Switzerland), Vol. 10, No. 7, 2556, 08.04.2020.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Efficient Deep Learning for Gradient-Enhanced Stress Dependent Damage Model
AU - Zhuang, Xiaoying
AU - Nguyen, L. C.
AU - Nguyen-Xuan, Hung
AU - Alajlan, Naif
AU - Rabczuk, Timon
N1 - Funding information: The authors extend their appreciation to the Distinguished Scientist Fellowship Program (DSFP) at King Saud University for funding this work. The authors extend their appreciation to the Distinguished Scientist Fellowship Program (DSFP) at King Saud University for funding this work.
PY - 2020/4/8
Y1 - 2020/4/8
N2 - This manuscript introduces a computational approach to micro-damage problems using deep learning for the prediction of loading deflection curves. The location of applied forces, dimensions of the specimen and material parameters are used as inputs of the process. The micro-damage is modelled with a gradient-enhanced damage model which ensures the well-posedness of the boundary value and yields mesh-independent results in computational methods such as FEM. We employ the Adam optimizer and Rectified linear unit activation function for training processes and research into the deep neural network architecture. The performance of our approach is demonstrated through some numerical examples including the three-point bending specimen, shear bending on L-shaped specimen and different failure mechanisms.
AB - This manuscript introduces a computational approach to micro-damage problems using deep learning for the prediction of loading deflection curves. The location of applied forces, dimensions of the specimen and material parameters are used as inputs of the process. The micro-damage is modelled with a gradient-enhanced damage model which ensures the well-posedness of the boundary value and yields mesh-independent results in computational methods such as FEM. We employ the Adam optimizer and Rectified linear unit activation function for training processes and research into the deep neural network architecture. The performance of our approach is demonstrated through some numerical examples including the three-point bending specimen, shear bending on L-shaped specimen and different failure mechanisms.
KW - Deep learning
KW - Deep neural network
KW - Gradient enhanced damage
KW - Stress-level dependent damage model
UR - http://www.scopus.com/inward/record.url?scp=85083441337&partnerID=8YFLogxK
U2 - 10.3390/app10072556
DO - 10.3390/app10072556
M3 - Article
AN - SCOPUS:85083441337
VL - 10
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
SN - 2076-3417
IS - 7
M1 - 2556
ER -