Hypersonic Flow Control: Generalized Deep Reinforcement Learning for Hypersonic Intake Unstart Control under Uncertainty

TL;DR

This paper presents a deep reinforcement learning-based control strategy for stabilizing hypersonic inlets at Mach 5, demonstrating robustness, generalization to unseen conditions, and potential for real-time application under uncertainty.

Contribution

The study introduces a generalized DRL approach for hypersonic inlet unstart control, capable of handling uncertainties and noisy measurements, with high-fidelity CFD simulations supporting its development.

Findings

Robust stabilization of hypersonic inlet across various back pressures.

Strong zero-shot generalization to unseen scenarios.

Effective control with minimal sensor configurations.

Abstract

The hypersonic unstart phenomenon poses a major challenge to reliable air-breathing propulsion at Mach 5 and above, where strong shock-boundary-layer interactions and rapid pressure fluctuations can destabilize inlet operation. Here, we demonstrate a deep reinforcement learning (DRL)- based active flow control strategy to control unstart in a canonical two-dimensional hypersonic inlet at Mach 5 and Reynolds number $5\times 10^6$. The in-house CFD solver enables high-fidelity simulations with adaptive mesh refinement, resolving key flow features, including shock motion, boundary-layer dynamics, and flow separation, that are essential for learning physically consistent control policies suitable for real-time deployment. The DRL controller robustly stabilizes the inlet over a wide range of back pressures representative of varying combustion chamber conditions. It further generalizes to previously unseen scenarios, including different back-pressure levels, Reynolds numbers, and sensor configurations, while operating with noisy measurements, thereby demonstrating strong zero-shot generalization. Control remains robust in the presence of noisy sensor measurements, and a minimal, optimally selected sensor set achieves comparable performance, enabling practical implementation. These results establish a data-driven approach for real-time hypersonic flow control under realistic operational uncertainties.