Development of a CFD-Suitable Deep Neural Network Model for Laminar Burning Velocity

Hydrogen is a valued resource for today’s industry. As fuel, it produces large amounts of energy and creates water during the process, unlike most other polluting sources. However, safe use hydrogen requires reliable tools able to accurately predict combustion. This study presents implementation deep neural network laminar burning velocity into an open-source CFD solver flameFoam. DNN was developed based on previously created larger DNN, which too applications since calculations took around 40 times longer compared Malet correlation. Therefore, original model, faster, but still accurate, implemented flameFoam starting with version 0.10. The paper adaptation CFD-applicable initial test results CFD–DNN simulation.