Adjoint-based machine learning for active flow control

TL;DR

This paper introduces a neural-network-based active flow control method using adjoint sensitivities for optimization, demonstrating superior efficiency and effectiveness over reinforcement learning in various flow scenarios, including drag reduction and vortex stabilization.

Contribution

The paper presents a novel adjoint-based deep learning approach for active flow control that outperforms deep reinforcement learning in efficiency and effectiveness, and offers flexible optimization over control laws.

Findings

DPM-based control is comparable to supervised learning for in-sample solutions.

DPM control is more effective and less computationally intensive than DRL for 2D cylinder flow.

Both controllers achieve 99% drag reduction and stabilize vortex shedding in unconfined flows.

Abstract

We develop neural-network active flow controllers using a deep learning PDE augmentation method (DPM). The sensitivities for optimization are computed using adjoints of the governing equations without restriction on the terms that may appear in the objective function. In 1D Burgers' examples with analytic control functions, DPM-based control is comparably effective to supervised learning for in-sample solutions and more effective for out-of-sample solutions. The influence of the optimization time interval is analyzed, the results of which influence algorithm design and hyperparameter choice, balancing control efficacy with computational cost. We later develop adjoint-based controllers for two flows. First, we compare the drag-reduction performance and optimization cost of adjoint controllers and deep reinforcement learning (DRL) controllers for 2D, incompressible, confined cylinder flow at Re=100, with synthetic body forces along the cylinder boundary. The required model complexity for the DRL controller is 4k times that required for the DPM controller. In these tests, the DPM controller is 4.85 times more effective and 63.2 times less computationally intensive to train than the DRL controller. Second, we test DPM control for compressible, unconfined cylinder flow and extrapolate the controller to out-of-sample Reynolds numbers. We also train a simplified, steady controller based on the DPM control law. Both controllers stabilize the vortex shedding with a 99% drag reduction, demonstrating the robustness of the learning approach. For out-of-sample flows, both controllers successfully reduce drag and stabilize vortex shedding, indicating that the DPM-based approach results in a stable model. A key attractive feature is the flexibility of adjoint-based optimization, which permits optimization over arbitrarily defined control laws without the need to match a priori known functions.