Optimizing a Continuous Mixing Process with Discrete Element Modeling and Machine Learning

Achieving reliability in continuous bulk solids mixing processes is key to meeting product quality requirements in a wide range of industries but physical trial-and-error optimization is time consuming and expensive. This webinar demonstrates an efficient virtual optimization methodology that combines high-fidelity physics-based simulation in Altair EDEM, High Performance Computing (HPC) in Altair Unlimited and machine learning and automation in Altair HyperStudy to rapidly identify the optimal mixer design and operation in-silico. 

The presented methodology will cover parameterizing the equipment geometry, automatically generating and running EDEM simulations with well distributed sample set to drive machine learning. A multi-objective genetic algorithm, MOGA, is then utilized to rapidly estimate the optimal parameter set from a fitted response surface. All of this is achieved through an automated, easy to use, GUI-based workflow that combines all of the Altair tools together.

For further details check the following blog in Altair Community: