Machine learning frameworks such as Genetic Programming (GP) and Reinforcement Learning (RL) are gaining popularity in flow control. This work presents a comparative analysis of the two, bench-marking some of their most representative algorithms against global optimization techniques such as Bayesian Optimization (BO) and Lipschitz global optimization (LIPO). First, we review the general framework of the flow control problem, linking optimal control theory with model-free machine learning methods. Then, we test the control algorithms on three test cases. These are (1) the stabilization of a nonlinear dynamical system featuring frequency cross-talk, (2) the wave cancellation from a Burgers' flow and (3) the drag reduction in a cylinder wake flow. Although the control of these problems has been tackled in the recent literature with one method or the other, we present a comprehensive comparison to illustrate their differences in exploration versus exploitation and their balance between `model capacity' in the control law definition versus `required complexity'. We believe that such a comparison opens the path towards hybridization of the various methods, and we offer some perspective on their future development in the literature of flow control problems.
翻译:首先,我们审查了流动控制问题的总体框架,将最佳控制理论与无模型的机器学习方法联系起来。然后,我们测试了三个测试案例的控制算法。这些案例是:(1) 非线性动态系统的稳定,以频率为主,(2) 汉堡的潮流取消,(3) 气瓶后流的拖动减少。虽然最近文献用一种或另一种方法处理了这些问题的控制,但我们用一种或另一种方法来说明这些问题的勘探与开发之间的差别,以及控制法定义中的“示范能力”与“必要的复杂性”之间的平衡。我们认为,这种比较为各种方法的混合开辟了道路,我们从流动控制问题的文献中对它们的未来发展提出一些看法。