September 11, 2025

Deep reinforcement learning control unlocks enhanced heat transfer in turbulent convection.

Key Points

Heat transfer improved by up to 38.5%, showing the effectiveness of deep reinforcement learning techniques.
The deep reinforcement learning agent outperformed traditional methods, which max out at 20 to 25% enhancement.
Analysis of turbulent Rayleigh-Bénard convection using a novel machine learning framework demonstrates significant performance improvements.
The findings support future applications of machine learning for optimizing heat transfer in various settings.

Abstract

Turbulent convection governs heat transport in both natural and industrial settings, yet optimizing it under extreme conditions remains a significant challenge. Traditional control strategies, such as predefined temperature modulation, struggle to achieve substantial enhancement. Here, we introduce a deep reinforcement learning (DRL) framework that autonomously discovers optimal control policies to maximize heat transfer in turbulent Rayleigh-Bénard convection. By dynamically adjusting wall temperature fluctuations, the DRL agent achieves a heat transfer enhancement of up to 38.5%, exceeding the 20 to 25% limit of conventional methods. The learned strategy reveals a nonlinear state-action relationship, inducing a fully modulated boundary layer regime. Furthermore, we distill the DRL insights into a simplified bang-bang control model, which retains comparable performance (up to 40.0% enhancement) and, crucially, generalizes to unseen, higher Rayleigh number cases without additional training. Our results demonstrate the power of machine learning in turbulence control and reveal a framework with potential for intelligent heat transfer optimization in real-world applications.

Bookmark

Deep reinforcement learning control unlocks enhanced heat transfer in turbulent convection.

Key Points

Abstract

Cite This Study