当前位置: X-MOL 学术Big Data › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Physics-Guided Deep Learning for Drag Force Prediction in Dense Fluid-Particulate Systems
Big Data ( IF 4.6 ) Pub Date : 2020-10-19 , DOI: 10.1089/big.2020.0071
Nikhil Muralidhar 1, 2 , Jie Bu 1, 2 , Ze Cao 3 , Long He 3 , Naren Ramakrishnan 1, 2 , Danesh Tafti 3 , Anuj Karpatne 1, 2
Affiliation  

Physics-based simulations are often used to model and understand complex physical systems in domains such as fluid dynamics. Such simulations, although used frequently, often suffer from inaccurate or incomplete representations either due to their high computational costs or due to lack of complete physical knowledge of the system. In such situations, it is useful to employ machine learning (ML) to fill the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models being cognizant of data paucity issues. In such scenarios, it is helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of ML models. We can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this article, we propose PhyNet, a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a computational fluid dynamics–discrete element method. We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation. PhyNet has been compared with several state-of-the-art models and achieves a significant performance improvement of 7.09% on average. The source code has been made available*.

中文翻译:

用于稠密流体颗粒系统阻力预测的物理引导深度学习

基于物理的模拟通常用于建模和理解流体动力学等领域中的复杂物理系统。这种模拟虽然经常使用,但由于其高计算成本或由于缺乏系统的完整物理知识而经常遭受不准确或不完整的表示。在这种情况下,通过直接从模拟数据中学习复杂物理过程的模型,使用机器学习 (ML) 来填补空白是很有用的。然而,由于通过模拟生成数据的成本很高,我们需要开发能够意识到数据缺乏问题的模型。在这种情况下,如果将应用领域的丰富物理知识纳入 ML 模型的架构设计中,将会很有帮助。我们还可以使用来自基于物理的模拟的信息来指导学习过程,使用聚合监督来有利地约束学习过程。在本文中,我们提出了 PhyNet,这是一种深度学习模型,它使用物理引导的结构先验和物理引导的聚合监督来模拟计算流体动力学离散元方法中作用在每个粒子上的阻力。我们在阻力预测的背景下进行了广泛的实验,并展示了在我们的深度学习公式中包含物理知识的有用性。PhyNet 已经与几个最先进的模型进行了比较,平均实现了 7.09% 的显着性能提升。源代码已提供 一个深度学习模型,使用物理引导的结构先验和物理引导的聚合监督来模拟计算流体动力学 - 离散元方法中作用在每个粒子上的阻力。我们在阻力预测的背景下进行了广泛的实验,并展示了在我们的深度学习公式中包含物理知识的有用性。PhyNet 已经与几个最先进的模型进行了比较,平均实现了 7.09% 的显着性能提升。源代码已提供 一个深度学习模型,使用物理引导的结构先验和物理引导的聚合监督来模拟计算流体动力学 - 离散元方法中作用在每个粒子上的阻力。我们在阻力预测的背景下进行了广泛的实验,并展示了在我们的深度学习公式中包含物理知识的有用性。PhyNet 已经与几个最先进的模型进行了比较,平均实现了 7.09% 的显着性能提升。源代码已提供 我们在阻力预测的背景下进行了广泛的实验,并展示了在我们的深度学习公式中包含物理知识的有用性。PhyNet 已经与几个最先进的模型进行了比较,平均实现了 7.09% 的显着性能提升。源代码已提供 我们在阻力预测的背景下进行了广泛的实验,并展示了在我们的深度学习公式中包含物理知识的有用性。PhyNet 已经与几个最先进的模型进行了比较,平均实现了 7.09% 的显着性能提升。源代码已提供* .
更新日期:2020-10-30
down
wechat
bug