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 -