A physics-guided deep learning-based framework for computational mechanics

Overview

Computational mechanics is an essential discipline that uses numerical schemes to approximately solve mechanics problems. It provides engineers with precious knowledge about the structures to identify the at-risk area and further guide the structural design and optimisation process.

Deep learning (DL) is an important branch of machine learning (ML). The great success of the DL techniques has been witnessed in the past decade. Now, various fields have benefited from the DL techniques, including computer vision, financial prediction, and bioinformatics. Therefore, it is of great interest to find what will the traditional computational mechanics benefit from the DL techniques.

Research activities

The research activities in this project include:

• review the recent development of related research fields
• implement DL models in Python through the TensorFlow library
• establish a PGDL-based computational mechanics framework
• validate the proposed framework through well-known benchmark problems and conduct academic discussions.

Outcomes

In this project, the possibility of the combination of DL techniques and computational mechanics will be explored. The state-of-the-art physics-guided deep learning (PGDL) technique will be leveraged to deal with mechanics problems. The mechanics information in terms of displacement and stress will be predicted by the proposed PGDL-based computational mechanics framework.

Skills and experience

To be considered for this project you should:

• have basic knowledge of solid mechanics
• be skilled in coding (Python and MATLAB).

Keywords

• mechanics
• machine learning

Contact

Contact the supervisor for more information.