Data-driven modelling in fluid mechanics is a promising alternative given the continuous increase of computational power and data-storage capabilities. Highly non-linear flows which include turbulence and reaction are challenging to model, and accurate algebraic closures for the unresolved terms in large eddy simulations of such flows are difficult to obtain. In this study, an artificial neural network is developed in order to directly model an important unclosed term namely the unresolved stress tensor. The performance of this approach is evaluated a priori using direct numerical simulation data of a highly demanding flow configuration, a turbulent premixed V-flame, and compared against the predictions of eight other classic models in the literature which include both static and dynamic formulations.

中文翻译：

---

对湍流预混 V 型火焰中未解决应力的基于神经网络的封闭评估

鉴于计算能力和数据存储能力的不断增加，流体力学中的数据驱动建模是一种很有前途的替代方案。包括湍流和反应在内的高度非线性流动难以建模，并且难以获得此类流动的大涡模拟中未解析项的准确代数闭包。在这项研究中，开发了一个人工神经网络，以直接模拟一个重要的未封闭项，即未解析的应力张量。这种方法的性能使用要求很高的流动配置、湍流预混 V 型火焰的直接数值模拟数据进行了先验评估，并与文献中包括静态和动态公式的其他八种经典模型的预测进行了比较。