This work proposes a physics-constrained machine learning approach to enhance the generalisability of neural-network-represented turbulence models across different flow regimes with a physics-constrained learning approach based on the regularised ensemble Kalman method.
Abstract
Abstract Content of image described in text. In this work we propose a physics-constrained machine learning approach to enhance the generalisability of neural-network-represented turbulence models across different flow regimes. Machine learning-augmented turbulence modelling has emerged to improve the predictive accuracy of the Reynolds-averaged Navier–Stokes method based on high-fidelity data. However, such data-driven models face difficulties in generalising well in different flow scenarios outside training datasets. Here we show that this issue can be alleviated by incorporating physical constraints of the Reynolds stress during the learning process. It is achieved with a physics-constrained learning approach based on the regularised ensemble Kalman method, which allows for model learning from limited velocity data and is flexible in imposing physical constraints. The method is used to learn a nonlinear eddy viscosity model, represented by a tensor-basis neural network, from velocity data in separated flows over periodic hills. Two physical constraints are incorporated during the model learning, i.e. the baseline coefficients to capture the log law of the wall and the algebraic Reynolds stress equation to inform the Reynolds stress anisotropy. Moreover, an adaptive penalty method is developed to enforce physical constraints in the feature space associated with canonical flows, avoiding the incompatibility with the training data from separated flows. Our results show that the proposed method can learn a generalisable turbulence model across different flow scenarios, including similar separated flows, canonical wall-bounded flows and complex flow configurations. Finally, the learned neural-network-based model function is discussed, demonstrating its consistency with the imposed physical constraints.
This work presents the development and assessment of a hybrid framework coupling numerical simulation, experimental samples, data assimilation (DA) and machine learning (ML) to investigate the flow within an axial compressor stage. The methodology first implements a Multi-Fidelity Ensemble Kalman Filter (MFEnKF) which...
Tom Moussie, Pierric Joseph, M. Meldi· 0 citations
This work proposes a goal-oriented method to select and weight Reynolds-stress training data for complex flows, and suggests a broader strategy for aligning supervised learning with downstream prediction goals while preserving training efficiency.
Zhuo-Lin Zhao, Hao-Chen Wang, Youngwoo Kim et al.· 0 citations
Abstract Data-driven methods have demonstrated strong predictive capabilities in fluid mechanics, yet most current applications still focus on simplified configurations, often characterized by statistical stationarity or limited temporal variability. This work proposes a methodology that combines data assimilation (DA)...
Miguel Martínez Valero, M. Meldi· Data-Centric Engineering· 0 citations
Magnetohydrodynamics (MHD) is central to plasma modeling in astrophysics, space science, fusion, and engineering, but resolving multiscale MHD dynamics is computationally expensive. Machine-learning surrogates enable fast inference by learning reusable solution operators, yet existing models require separate training f...
Radhika Achikanath Chirakkara, Rajdeep Haldar, Zezheng Song et al.· arXiv.org· 0 citations
A reduced-order physics-constrained deep learning framework, SupersonicNet, is developed for the rapid prediction of two-dimensional supersonic flow fields (Ma 2.5–5.0) in confined channels with variable forward-facing step geometries. The framework is built upon a modified U-Net architecture. The continuity equation a...
Yu-De Yan, Jian Dai· The Physics of Fluids· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.