Progressive, extrapolative machine learning for near-wall turbulence modeling

Abstract

Training/retraining a model against new data often breaks its good behavior. This left machine learning models open to criticism: machine-learned models do not fully preserve, e.g., the law of the wall (among other empirical facts), and they do not generalize to, e.g., high Reynolds numbers (among other conditions). This paper establishes a paradigm for machine learning, namely, progressive machine learning, allowing one to preserve the good behavior of an existing model in retraining. This paradigm is applied to progressively model flows in the constant stress layer, the wake layer, and with system rotation, with success.

Topics & Concepts