University of Twente Student Theses
Machine learning in the calibration process of discrete particle model
Nguyen, Q.H. (2022) Machine learning in the calibration process of discrete particle model.
|
PDF
4MB |
| Abstract: | This research presents a comprehensive study on the use of machine learning in the calibration prob- lem of the Discrete Particle Model, with a particular focus on one bulk parameter: the static angle of repose. Three machine learning algorithms have been tested, including GrainLearning - the unsuper- vised algorithm explicitly developed for DPM calibration, and two other popular supervised learning algorithms: Neural Network and Random Forest regressor. With GrainLearning, multiple attempts have been made to analyze its ability to find the correct combinations of microparameters that can reproduce the experimental static angle of repose in DEM simulations. Meanwhile, after a training period consisting of hundreds of DEM simulations, the NN and RF are capable of providing a database that can be used to find the microparameters that correspond to the experimental static angle of re- pose. Subsequent validations of those combinations using DEM simulations indicate that multiple combinations are correct, paving the way for future research on adapting more supervised machine learning algorithms in the calibration problem with different contact laws and bulk parameters. |
| Item Type: | Essay (Bachelor) |
| Faculty: | TNW: Science and Technology |
| Subject: | 31 mathematics, 33 physics, 35 chemistry |
| Programme: | Chemical Engineering BSc (56960) |
| Link to this item: | https://purl.utwente.nl/essays/91991 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page