Adjoint-Based Model Tuning and Machine Learning Strategy for Turbulence Model Improvement
2022-01-1079
03/29/2022
- Content
- As turbulence modeling has become an indispensable approach to perform flow simulation in a wide range of industrial applications, how to improve the prediction accuracy has gained increasing attention during the past years. Of all the turbulence models, RANS is the most common choice for many OEMs due to its short turn-around time and strong robustness, however, the default setting of RANS is usually benchmarked through classical and well-studied engineering examples, not always suitable for resolving complex flows in specific applications. Many previous researches have suggested a small tuning in turbulence model coefficients could achieve higher accuracy on a variety of flow scenarios. Instead of adjusting parameters by trial and error from experience, this paper introduced a new data-driven approach of turbulence model recalibration using adjoint solver, based on Generalized k-ω (GEKO) model, one variant of RANS. In this approach, the model coefficients are tuned locally to match the measured drag force and surface pressure as closely as possible on two production cars, one is sedan, and the other is SUV. After well-tuned process, neural network strategy was utilized with a training dataset to learn the correlation between calibrated coefficients and certain flow features. Once trained, the improved model can be employed in similar applications, like geometrical modifications and varying flow conditions. Results show that through tuning and machine learning, prediction of drag and surface pressure presented better agreement with test data for both cars, compared with the original model. Adjoint-based GEKO tuning, validated by various cases of this paper and benchmarked with wind tunnel test, proved to be very helpful in turbulence model optimization. Hence, this work indicated the promising potential of applying model tuning and machine learning to assist turbulence model development in vehicle aerodynamic application.
- Citation
- Zhou, H., and Ren, C., "Adjoint-Based Model Tuning and Machine Learning Strategy for Turbulence Model Improvement," SAE Technical Paper 2022-01-1079, 2022, .