Velocity reconstruction in puffing pool fires with physics-informed neural networks
Velocity reconstruction in puffing pool fires with physics-informed neural networks
复制标题
利用物理信息神经网络重建喷水池火灾的速度
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
N. Doan
中科院分区：
文献类型：
--
作者：
M. Sitte;N. Doan
池火是许多意外火灾的典型代表，这些火灾可能表现出不稳定的不稳定行为，称为喷发，涉及温度场和速度场之间的强耦合。尽管它们与火灾研究具有实际相关性，但由于并行测量相关量的复杂性，它们的实验研究可能受到限制。在这项工作中，我们分析了一种最新的基于物理的机器学习方法（称为隐藏流体力学（HFM））的使用，以根据测量的量重建喷水池火灾中未测量的量。 HFM 框架依靠物理信息神经网络 (PINN) 来完成此任务。 PINN 是一种神经网络，它使用可用数据（此处为测量量）和控制系统的物理方程（此处为反应纳维-斯托克斯方程）来推断完整的流体动力学状态。该框架用于根据密度、压力和温度的测量来推断膨胀池火灾中的速度场。在这项工作中，用于该测试的数据集是通过数值模拟生成的。结果表明，PINN 能够准确地重建速度场并推断出速度场的大部分特征。此外，结果表明，重建精度对于噪声数据具有鲁棒性，并且探索和讨论了测量量数量的减少。这项研究开辟了使用 PINN 从测量的数量重建未测量的数量的可能性，为其在火灾研究实验中的使用提供了潜在的基础。
Pool fires are canonical representations of many accidental fires which can exhibit an unstable unsteady behavior, known as puffing, which involves a strong coupling between the temperature and velocity fields. Despite their practical relevance to fire research, their experimental study can be limited due to the complexity of measuring relevant quantities in parallel. In this work, we analyze the use of a recent physics-informed machine learning approach, called hidden fluid mechanics (HFM), to reconstruct unmeasured quantities in a puffing pool fire from measured quantities. The HFM framework relies on a physics-informed neural network (PINN) for this task. A PINN is a neural network that uses both the available data, here the measured quantities, and the physical equations governing the system, here the reacting Navier–Stokes equations, to infer the full fluid dynamic state. This framework is used to infer the velocity field in a puffing pool fire from measurements of density, pressure, and temperature. In this work, the dataset used for this test was generated from numerical simulations. It is shown that the PINN is able to reconstruct the velocity field accurately and to infer most features of the velocity field. In addition, it is shown that the reconstruction accuracy is robust with respect to noisy data, and a reduction in the number of measured quantities is explored and discussed. This study opens up the possibility of using PINNs for the reconstruction of unmeasured quantities from measured ones, providing the potential groundwork for their use in experiments for fire research.
DOI：
10.1017/dce.2021.5
发表时间：
2021-01-01
期刊：
DATA-CENTRIC ENGINEERING
影响因子：
--
作者：
Carter, Douglas W.;De Voogt, Francis;Ganapathisubramani, Bharathram
通讯作者：
Ganapathisubramani, Bharathram
影响因子：
3.7
作者：
Nair, Nirmal J.;Goza, Andres
通讯作者：
Goza, Andres