论文标题
使用梯度来提高深度学习模型的概括性能，以进行流体动力学
Using Gradient to Boost the Generalization Performance of Deep Learning Models for Fluid Dynamics
论文作者
论文摘要
如今，计算流体动力学（CFD）是工业设计的基本工具。但是，进行此类模拟的计算成本很昂贵，对于需要许多仿真的现实情况，例如形状优化的任务，可能会有害。最近，深度学习（DL）在广泛的应用方面取得了重大飞跃，并成为了物理系统的良好候选者，并开辟了CFD的观点。为了避免CFD的计算瓶颈，DL模型已被用于学习欧几里得数据，最近，在非欧盟数据（如未张开的网格和歧管）上，允许更快，更有效（内存，硬件）代理模型。然而，DL提出了外推（概括）训练数据分布（设计空间）的内在限制。在这项研究中，我们提出了一项新的工作，以提高深度学习的概括能力。为此，我们将物理梯度（输出w.r.t.输入的导数）结合到了DL模型。我们的策略已经在更好地概括DL网络的情况下显示出良好的结果，我们的方法论/理论研究通过经验验证（包括消融研究）证实。
Nowadays, Computational Fluid Dynamics (CFD) is a fundamental tool for industrial design. However, the computational cost of doing such simulations is expensive and can be detrimental for real-world use cases where many simulations are necessary, such as the task of shape optimization. Recently, Deep Learning (DL) has achieved a significant leap in a wide spectrum of applications and became a good candidate for physical systems, opening perspectives to CFD. To circumvent the computational bottleneck of CFD, DL models have been used to learn on Euclidean data, and more recently, on non-Euclidean data such as unstuctured grids and manifolds, allowing much faster and more efficient (memory, hardware) surrogate models. Nevertheless, DL presents the intrinsic limitation of extrapolating (generalizing) out of training data distribution (design space). In this study, we present a novel work to increase the generalization capabilities of Deep Learning. To do so, we incorporate the physical gradients (derivatives of the outputs w.r.t. the inputs) to the DL models. Our strategy has shown good results towards a better generalization of DL networks and our methodological/ theoretical study is corroborated with empirical validation, including an ablation study.
