论文标题
控制双向耦合流体系统和可区分求解器
Control of Two-way Coupled Fluid Systems with Differentiable Solvers
论文作者
论文摘要
我们研究了深层神经网络来控制复杂的非线性动力学系统，特别是浸入液体中的刚体的运动。我们以两种方式耦合求解Navier Stokes方程，这会引起非线性扰动，从而使控制任务非常具有挑战性。通过从可区分的模拟器中学习的过程，以一种无监督的方式对神经网络进行培训，以充当具有期望特征的控制器。在这里，我们介绍了一组可解释的损失术语，以使网络学习强大而稳定的互动。我们证明，在规范环境中训练有静止初始条件的控制器可靠地概括为各种和具有挑战性的环境，例如以前看不见的流入条件和强迫，尽管它们没有任何流体信息作为输入。此外，我们表明，在评估指标和概括功能方面，接受我们方法训练的控制器优于各种古典和学习的替代方案。
We investigate the use of deep neural networks to control complex nonlinear dynamical systems, specifically the movement of a rigid body immersed in a fluid. We solve the Navier Stokes equations with two way coupling, which gives rise to nonlinear perturbations that make the control task very challenging. Neural networks are trained in an unsupervised way to act as controllers with desired characteristics through a process of learning from a differentiable simulator. Here we introduce a set of physically interpretable loss terms to let the networks learn robust and stable interactions. We demonstrate that controllers trained in a canonical setting with quiescent initial conditions reliably generalize to varied and challenging environments such as previously unseen inflow conditions and forcing, although they do not have any fluid information as input. Further, we show that controllers trained with our approach outperform a variety of classical and learned alternatives in terms of evaluation metrics and generalization capabilities.
