Copy of Role of engineering in preventing future pandemic: biosensor design and numerical analysis tools.
Using Machine Learning Techniques in Predictive Modelling of Magnetorheological Fluids
Research Group Activity
| Machine Learning, Material Modelling |
Project Description
| The demand for magnetorheological fluid (MRF) is increasing due to the adoption of smart suspension systems in robotic surgery and the automotive and aerospace industry. Constitutive modelling of MRFs is a crucial step in modelling MR devices, like MR dampers, MR brakes, MR clutches, and MR medical haptic devices. Due to the number of parameters that play role in the magneto-mechanical behaviour of MRFs, machine learning techniques could be promising tools to improve the predictive capabilities of material models. The prospective researcher will be provided with some experimental data on a few MRFs to run the analysis by MATLAB machine learning toolbox in order to generate predictive models for the MRFs under study. The material model is expected to predict the magneto-mechanical behaviour of these MRFs as a function of role-playing parameters like shear rate, magnetic field intensity, and magnetic particles particle concentration. This can potentially reduce the effort being done for the preparation, testing, and optimisation of commercial MRFs. |
Student Level
Open to both undergraduate and postgraduate students
Location
This project can be completed remotely.
Skills you can learn from this project
| The prospective researcher will receive training/tutorials on fundamental knowledge of MRFs, constitutive material modelling, and machine learning techniques. They will also learn the literature review, and scientific report writing techniques. |
Required Skills
| Elementary knowledge of MATLAB. |
If you wish to apply for this project, fill in the form below including uploading your CV and personal statement, explaining why you want to do this particular internship project. Attachments must be in PDF format.
This form is closed and is no longer accepting any submissions. Thank you for your time.
