一个具有注意力机制的深度神经网络,用于对压缩机叶片的流量预测
Guanyu Gao1,2, Gang Wang3,4,5
1State Key Lab of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin, 300130, People's Republic of China.
Scientific reports
|May 10, 2025
概括
一个具有注意力机制的新型卷积神经网络 (CNN) 预测了复杂的流体流场,大大降低了压缩机叶片设计优化的计算成本. 这种人工智能方法加快了设计周期,同时保持了高精度.
科学领域:
- 航空航天工程 航空航天工程
- 计算科学 计算科学
- 人工智能的人工智能
背景情况:
- 计算流体动力学 (CFD) 对于设计优化至关重要,但在计算上昂贵.
- 由于CFD模拟的高成本,设计探索机会有限.
- 加快压缩机叶片等组件的设计周期是一个关键的工业挑战.
研究的目的:
- 开发一种高效的深度学习模型,用于预测空气动力学设计中的流场.
- 为了减少与传统的CFD方法相关的计算时间.
- 提高压缩机叶片开发中的设计探索能力.
主要方法:
- 使用基于U-Net的卷积神经网络 (CNN) 与注意力机制 (AM).
- 输入形状和流量条件被转换为灰度图像,用于直接流量场预测.
- 开发了两种新的注意力机制,以确保身体的一致性,特别是在冲击波时.
- 进行了广泛的超参数调整,以优化模型的性能.
主要成果:
- CNN模型准确地预测了马赫数分布和复杂的流量场,与CFD结果一致.
- 与传统的CFD方法相比,实现了超过三倍的加快速度.
- 在各种工作条件和批量大小中保持低预测误差.
- 开发出的注意力机制有效地保护了冲击波现象的物理完整性.
结论:
- 拟议的CNN模型为流场预测提供了一个高效和准确的替代传统CFD.
- 这种方法通过减少计算成本,显著缩短了压缩机叶片设计周期.
- 注意力机制的整合增强了模型处理复杂物理现象的能力,确保可靠的预测.
相关概念视频
01:27Uniform Depth Channel Flow
48
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
48
01:24Fast Decoupled and DC Powerflow
139
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
139
01:27Laminar Flow
421
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:
421
01:24Turbulent Flow
80
Turbulent flow is characterized by unpredictable fluctuations in velocity and pressure, which result in a chaotic fluid movement distinct from the orderly patterns of laminar flow. While laminar flow is governed by smooth, parallel layers with minimal mixing, turbulent flow exhibits highly irregular, three-dimensional patterns. This behavior arises due to instabilities in the fluid's velocity profile, and amplifies as the flow velocity increases. Minor disturbances, known as turbulent...
80
01:26General External Flow Characteristics
56
The study of external flow is essential for creating structures and objects that interact efficiently and safely with moving fluids, such as air or water. When a body is immersed in a flowing fluid, it experiences two primary forces: drag, which opposes motion along the flow direction, and lift, which acts perpendicular to the flow. The shape, size, and orientation of the object influence these forces.Streamlined and Blunt Bodies in External FlowObjects in fluid flow are classified as...
56
01:24Rapidly Varying Flow
36
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
36