Construction method for general phenomenological RANS turbulence model

TL;DR

This paper introduces a phenomenological RANS turbulence model enhanced with deep learning and coordinate technology, significantly reducing simulation errors and improving adaptability in complex flow regimes.

Contribution

It presents a novel RANS turbulence model integrating deep learning with physical constraints and coordinate technology for better accuracy in complex flows.

Findings

Achieved 51.7% error reduction over standard k-e model.

Reduced simulation error by 6.2% using coordinate technology.

Enhanced model adaptability in abnormal flow regimes.

Abstract

This paper proposes a phenomenological Reynolds Averaged Navier-Stokes (RANS) calculation model based on physical constraints. In this model part of the source terms in the e equation was replaced with the deep learning model, using the standard k-e model as a template. The simulation results of this model achieved a high error reduction of 51.7 % compared to the standard k-e model. To improve the adaptability and accuracy compared to the convergence of the abnormal flow regime, the coordinate technology proposed in this study was used in the modelling process. For the training data, the k-field and e-field were automatically corrected using this approach when the flow state deviated from the theoretical assumption. Based on the coordinate technology, a deep learning model for the source term of the equation was built, and the simulation error was reduced by 6.2 % compared to the uncoordinated one. From the results, the proposed coordinate technology can effectively be adapted to the underdeveloped flow state and assist in the more accurately modelling of the phenomenological RANS calculation model under a complex flow state.