A GPU-based coupled SPH-DEM method for particle-fluid flow with free surfaces

Particle-fluid flows with free-surfaces are commonly encountered in many industrial processes, such as wet ball milling, slurry transport and mixing. Accurate prediction of particle behaviors in these systems is critical to establish fundamental understandings of the processes, however the presence of the free-surface makes modelling them a challenge for most traditional, continuum, multi-phase methodologies. Coupling of smoothed particle hydrodynamics and discrete element method (SPH-DEM) has the potential to be an effective numerical method to achieve this goal. However, practical application of this method remains challenging due to high computational demands. In this work, a general purposed SPH-DEM model that runs entirely on a Graphic Processing Unit (GPU) is developed to accelerate the simulation. Fluid-solid coupling is based on local averaging techniques and, to accelerate neighbor searching, a dual-grid searching approach is adapted to a GPU architecture to tackle the size difference in the searching area between SPH and DEM. Simulation results compare well with experimental results on dam-breaking of a free-surface flow and particle-fluid flow both qualitatively and quantitatively, confirming the validity of the developed model. More than 10 million fluid particles can be simulated on a single GPU using double-precision floating point operations. A linear scalability of calculation time with the number of particles is obtained for both single-phase and two-phase flows. Practical application of the developed model is demonstrated by simulations of an agitated tubular reactor and a rotating drum, showing its capability in handling complex engineering problems involving both free-surfaces and particle-fluid interactions. (C) 2018 The Authors. Published by Elsevier B.V.