一种新的混合深度学习方法,用于预测仿生飞翼的流场
Fujia Hu1,2, Weebeng Tay3, Yilun Zhou2
1Department of Energy and Power Engineering, North University of China, Taiyuan 030051, China.
Biomimetics (Basel, Switzerland)
|February 23, 2024
概括
一个新的混合深度学习模型 (HCDD-PINN) 准确地预测了生物灵感飞翼的流体动力学. 这种方法使用更粗的数据,与传统方法相比,加速解决方案.
科学领域:
- 流体动力学 流体动力学
- 计算科学 计算科学
- 人工智能的人工智能
背景情况:
- 生物灵感的飞翼涉及由部分微分方程 (PDEs) 规范的复杂流体动力学.
- 传统的基于PDE的计算是资源密集型的,并受到复杂的流动模式和众多参数的限制.
- 对非线性PDEs的准确和快速解决方案对于分析生物波结构至关重要.
研究的目的:
- 提出一个混合粗数据驱动的物理信息神经网络 (HCDD-PINN) 模型.
- 为了提高预测翼非线性PDE解决方案的准确性和可靠性.
- 为传统的计算流体动力学 (CFD) 提供更快的替代方案.
主要方法:
- 开发了一个HCDD-PINN模型,包括初始/边界条件和控制方程.
- 利用大小顺序曲线的网格数据作为神经网络损失函数内的内部训练数据.
- 分析了训练/预测动态,并对2D不稳定的飞翼问题进行了超参数研究.
主要成果:
- HCDD-PINN 显示出足够的稳定性和准确性,用于生物模拟的飞翼问题.
- 该模型可以在任何时刻快速提供流域数据,与传统的CFD不同,需要重复运行.
- 对粗略的内部数据分辨率和快照分数进行了性能分析.
结论:
- HCDD-PINN模型提供了一个有前途的替代方案,可以加速或取代传统的CFD解决方案.
- 该方法显示了在飞翼研究中的3D和优化问题的巨大潜力.
- 这种深度学习方法有助于快速分析生物飞结构.
相关概念视频
01:30Typical Model Studies
359
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
359
01:22Eulerian and Lagrangian Flow Descriptions
1.4K
Fluid flow analysis is critical in many scientific and engineering disciplines, and two principal approaches are used to describe this flow: the Eulerian and Lagrangian methods. These methods offer different perspectives on monitoring and analyzing the motion of fluids, each with distinct advantages depending on the scenario.
The Eulerian method focuses on fixed points in space where fluid properties, such as velocity, pressure, and temperature, are observed as the fluid moves between these...
The Eulerian method focuses on fixed points in space where fluid properties, such as velocity, pressure, and temperature, are observed as the fluid moves between these...
1.4K
01:23Plane Potential Flows
386
Plane potential flows simplify fluid motion by assuming the fluid to be irrotational and incompressible. These characteristics allow these flows to be described by a velocity potential function, ϕ, representing the flow speed in a given direction, and a stream function, ψ, that visualizes the flow path, both governed by Laplace's equation. These parameters help in estimating flow patterns, velocity distributions, and pressure fields around various hydraulic structures.
Uniform...
Uniform...
386
01:07Laminar and Turbulent Flow
8.5K
Fluid dynamics is the study of fluids in motion. Velocity vectors are often used to illustrate fluid motion in applications like meteorology. For example, wind—the fluid motion of air in the atmosphere—can be represented by vectors indicating the speed and direction of the wind at any given point on a map. Another method for representing fluid motion is a streamline. A streamline represents the path of a small volume of fluid as it flows. When the flow pattern changes with time, the...
8.5K
01:23Lift
124
Lift is a fundamental aerodynamic force that acts perpendicular to the direction of airflow. It plays a central role in achieving and sustaining flight and in stabilizing various vehicles. Lift primarily originates from pressure differences created across surfaces, such as an airfoil. A lower pressure region forms above the wing, while a higher pressure region forms below it, generating an upward force. This differential results from the shape and orientation of the airfoil, enabling the wing...
124
01:27Laminar Flow
1.1K
Laminar flow represents a smooth, orderly fluid motion where particles move along parallel paths, resulting in minimal mixing between layers. Streamlined particle paths characterize this flow regime and occur under conditions where viscous forces dominate over inertial forces. The distinction between laminar, transitional, and turbulent flow is primarily determined by the Reynolds number, a dimensionless quantity calculated as:
1.1K