Deep Learning for Drag Coefficient Predictions of Spherical and Non-Spherical Particles

The drag model for non-spherical particles required in a particle-laden flow is not fully established, which could cover a wide range of sphericities. This study focuses on developing an artificial neural network model by using a large number of available experimental data for a wide range of sphericities (0.034–1), density ratios (0.0005–0.491), and Reynold numbers (0.002–79432). Available experimental and DNS data for particles of various sizes and materials tested against liquid and gas are identified to correlate the drag coefficient. Three different neural network algorithms, Random Forest, Gradient Boosting, and a Deep Neural Network (DNN), are trained and evaluated. The neural network results were compared to the experimental results and to select numerical correlations. It was found that the DNN model outperforms all the other methods and algorithms for most of the studied sphericities (0.36–1).