Open Access

Forecasting Damage Mechanics By Deep Learning

Duyen Le Hien Nguyen¹, Dieu Thi Thanh Do², Jaehong Lee², Timon Rabczuk³, Hung Nguyen-Xuan^{1, 4,*}
1 CIRTech Institute, Ho Chi Minh City University of Technology (HUTECH), Ho Chi Minh City, Vietnam.
2 Department of Architectural Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul, Korea.
3 Institute of Structural Mechanics, Bauhaus-Universit\u00e4t Weimar, 99423, Weimar, Germany.
4 Department of Physical Therapy, Graduate Institute of Rehabilitation Science, China Medical University, Taichung, 40402, Taiwan.

* Corresponding Author: Hung Nguyen-Xuan. Email: .

Journal of Advanced Optics and Photonics https://doi.org/10.32604/cmc.2019.08001

Abstract

We in this paper exploit time series algorithm based deep learning in forecasting damage mechanics problems. The methodologies that are able to work accurately for less computational and resolving attempts are a significant demand nowadays. Relied on learning an amount of information from given data, the long short-term memory (LSTM) method and multi-layer neural networks (MNN) method are applied to predict solutions. Numerical examples are implemented for predicting fracture growth rates of L-shape concrete specimen under load ratio, single-edge-notched beam forced by 4-point shear and hydraulic fracturing in permeable porous media problems such as storage-toughness fracture regime and fracture-height growth in Marcellus shale. The predicted results by deep learning algorithms are well-agreed with experimental data.

---

Keywords

Damage mechanics, time series forecasting, deep learning, long short-term memory, multi-layer neural networks, hydraulic fracturing

---