Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling

Abstract

Developing Reynolds-averaged Navier-Stokes (RANS) turbulence models that remain accurate across diverse flow regimes is a long-standing challenge. In this work, we propose a novel framework, termed the progressive mixture-of-experts (PMoE), designed to enable continual learning for RANS turbulence modelling. The framework employs a modular autoencoder-based router to associate each flow scenario with a specialised turbulence model, referred to as an expert. When a new flow regime cannot be adequately represented by the existing router and expert set, a new expert together with its routing component can be introduced at low cost, without modifying or degrading previously trained ones, thereby naturally avoiding catastrophic forgetting. The framework is applied to a range of flows with distinct physical characteristics, including airfoil wake, channel, periodic hill, and square duct flows. The resulting PMoE model effectively integrates multiple experts and achieves improved predictive accuracy across both seen and unseen test cases that differ in operating conditions or configurations. Owing to sparse activation, model expansion does not incur additional computational cost during inference. The proposed framework therefore provides a scalable pathway towards lifelong-learning turbulence models for industrial computational fluid dynamics.

References in corpus (13)

• Overcoming catastrophic forgetting in neural networks
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Direct numerical simulation of turbulent channel flow up to $R{e}_{\tau }\approx 5200$
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach
• RANS Turbulence Model Development using CFD-Driven Machine Learning
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Feature selection and processing of turbulence modeling based on an artificial neural network
• Machine learning building-block-flow wall model for large-eddy simulation
• Enhancing the SST Turbulence Model with Symbolic Regression: A Generalizable and Interpretable Data-Driven Approach
• Space-dependent Aggregation of Stochastic Data-driven Turbulence Models