Machine learning accelerated discrete element modeling of granular flows
| Autor: | William A. Rogers, Liqiang Lu, Xi Gao, Jean-François Dietiker, Mehrdad Shahnam |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
business.industry Computer science Applied Mathematics General Chemical Engineering Computation 02 engineering and technology General Chemistry Function (mathematics) Troubleshooting 021001 nanoscience & nanotechnology Granular material Machine learning computer.software_genre Convolutional neural network Industrial and Manufacturing Engineering Discrete element method Software 020401 chemical engineering Artificial intelligence 0204 chemical engineering 0210 nano-technology business computer |
| Zdroj: | Chemical Engineering Science. 245:116832 |
| ISSN: | 0009-2509 |
| DOI: | 10.1016/j.ces.2021.116832 |
| Popis: | Granular flows are widely encountered in many industrial processes and natural phenomena. Discrete Element Modeling (DEM) is a useful tool for understanding and troubleshooting devices processing granular materials. However, its applicability is significantly limited by the huge computational cost associated with detecting and computing collisions. In this research, the computation speed of DEM was accelerated by orders of magnitude using a convolutional neural network to replace the direct calculation of particle–particle and particle-boundary collisions. The MFiX software was used to generate the training and testing dataset. A GPU accelerated TensorFlow model was used to train the neural network and test the results. The model fluctuations caused by different training steps were reduced with a multi-scale loss function. The accuracy was improved with more frames within one training step. The modeling of a rotating drum and a hopper demonstrated the accuracy and efficiency of this machine learning accelerated DEM in the simulation of granular flows. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect