Description
Large Composite parts are often joined together using bolted joints and accurate Finite element simulation of such joints is essential for designing composite structures. The computational effort required to simulate a single composite joint is extremely high because of which it becomes impossible to simulate large structures with field of bolts. The project aims to address this problem by using shell-beam models, supplemented with Machine learning algorithms to reduce the computational time substantially without compromising on accuracy. The aim of the current task is to develop training data for the machine learning algorithm from Abaqus models. The tasks can be tailored to some extent according to the knowledge and skills of the student.
Tasks
- Python Scripting in Abaqus
- Stress Analysis in Abaqus
- Machine Learning (ML) with Python
Prerequisites
- Basic programming skills in Python
- Experience with Abaqus or other FEM solver
- Basic Knowledge of FEM and ML is a plus
- Motivated and Independent way of working
- Enrollment at a German University
Working hours
The paid student assistant position is initially limited to 3 months with 20 hours monthly, and an extension to 9 months with monthly 45 hours is possible.
Contact Person
Aditya Bansod, M. Sc.
Institut für Statik und Dynamik Appelstr. 9A, 30167 Hannover Tel.: 0511-762-17426
E-Mail : a.bansod@isd.uni-hannover.de
