B1: Physics-informed deep learning models for the simulation of granular flow

Term: 2/2019 - 1/2022 (36 Monate)

Partner: DCS Computing GmbH

Granular flows are of significant importance across a wide variety of industries, including amongst others oil and gas, pharmaceutical, mining, food production and metallurgy. There are huge energetic and monetary losses due to poorly understood granular flow processes which are starting to be addressed by the advent of Industry 4.0. The project aims for an interdisciplinary collaboration between the two partners in order to develop a machine learning algorithm that is capable of reproducing and predicting granular flows with high computational efficiency.