(715a) Combining Simulation and Machine Learning for the Optimization of Powder Handling Processes with Altair Solutions

The rapid virtual optimization of industrial processes is at the core of the Industry 4.0 paradigm, but it requires the development of computationally efficient methodologies that go beyond a purely simulation driven approach to include machine learning based reduced-order modelling. This is particularly true in the context of industrial bulk solids handling processes, where the computational expense of high-fidelity simulations is significant. This workshop discusses an efficient virtual optimization methodology for industrial bulk handling processes, which combines high-fidelity numerical modelling in Altair EDEM with statistical and machine learning methods in Altair HyperStudy, Activate and romAI, to significantly reduce the computational expense of optimization relative to a purely simulation driven approach.

The challenge of quickly and accurately representing powder in a virtual environment has been addressed with the industry’s first powder material model database. The database allows researchers to quickly represent a powder in a virtual environment based on the poured bulk density, degree of compressibility, cohesion, and either the static angle of repose or steady-state shear response. Not all powders have been included in the database, and in this case leveraging the combination of EDEM and HyperStudy is advantageous to accelerate the calibration process and arrive at an acceptably accurate virtual representation of the powder. The creation of the powder material database and the execution of EDEM-HyperStudy powder calibration will be reviewed.

Pneumatic conveyance of powder is commonly used due to its safety, versatility, and ease of automation. Overcoming the challenges of plug flow, agglomeration and blockages has been investigated with two-way coupled CFD-DEM simulation, whereby the bulk solid flow was resolved in Altair EDEM and the air flow was resolved in Altair AcuSolve. The outcome of this industry-partnered study will be highlighted.