Developing Drag Models for Non-Spherical Particles through Machine Learning
- Johns Hopkins Univ., Baltimore, MD (United States)
The overarching goal of this project is to produce comprehensive experimental and numerical datasets for gas-solid flows in well-controlled settings to understand the aerodynamic drag of non-spherical particles in the dense regime. The datasets and the gained knowledge will be utilized to train deep neural networks in TensorFlow to formulate a general drag model for use directly in NETL MFiX-DEM module in order to help to advance the accuracy and prediction fidelity of the computational tools that will be used in designing and optimizing fluidized beds and chemical looping reactors.
- Research Organization:
- Johns Hopkins Univ., Baltimore, MD (United States)
- Sponsoring Organization:
- USDOE Office of Fossil Energy and Carbon Management (FECM)
- DOE Contract Number:
- FE0031897
- OSTI ID:
- 2503555
- Country of Publication:
- United States
- Language:
- English
Similar Records
Development and Evaluation of a General Drag Model for Gas-Solid Flows via Deep Learning
Machine learning accelerated discrete element modeling of granular flows
Development of a Deep Learning Model for Predicting the Drag Coefficients of Spherical and Non-Spherical Particles,
Technical Report
·
Tue Sep 30 00:00:00 EDT 2025
·
OSTI ID:2997049
Machine learning accelerated discrete element modeling of granular flows
Journal Article
·
Wed Jun 02 00:00:00 EDT 2021
· Chemical Engineering Science
·
OSTI ID:1869680
Development of a Deep Learning Model for Predicting the Drag Coefficients of Spherical and Non-Spherical Particles,
Conference
·
Wed Apr 21 00:00:00 EDT 2021
·
OSTI ID:1811210