arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.00183physics.flu-dyn
收藏

基于物理信息CNN的涡轮机械PIV数据建模中重建精度与物理有效性之间的权衡

Trade-off between reconstruction accuracy and physical validity in modeling turbomachinery PIV data by Physics-Informed CNN

Maryam Soltani, Ghasem Akbari, Nader Montazerin

AI总结:

本文提出卷积物理信息自编码器,在填补PIV缺失区域时兼顾质量守恒,通过湍流尺度设定损失权重,在DNS和PIV数据上验证,实现残差和速度统计精度提升约28%和29%,仅以最多5%的误差超限向量增加为代价。

摘要:

粒子图像测速(PIV)数据是流体力学中的宝贵资产。即使在复杂物理场景下,例如离心风机转子出口处的流动,它也能够可视化流动结构。机器学习也是PIV的成功伙伴,用于提高数据分辨率或填补实验空白。虽然经典算法仅侧重于使用统计指标复现数据,但物理信息神经网络(PINN)的应用同时有助于数据重建和遵循控制方程。本研究利用卷积物理信息自编码器在缺失区域重现平面PIV场,同时满足质量守恒方程。它提出了一种新方法,在实验数据重建与遵守物理约束之间进行折中。同时,旨在确保重建误差不会显著偏离测试数据的不确定度带。采用湍流尺度近似来设定损失函数中物理项和非物理项的相对权重,以确保两个目标都能实现。所有步骤首先在一组DNS数据上进行评估,以证明网络的通用能力。最后,对PIV数据的检验表明,所提出的PINN自编码器可以将重建精度在质量守恒残差和速度统计方面分别提高约28%和29%,代价是重建误差高于PIV测试数据不确定度带的向量数量最多增加5%。

英文摘要:

Particle Image Velocimetry (PIV) data is a valuable asset in fluid mechanics. It is capable of visualizing flow structures even in complex physics scenarios, such as the flow at the exit of the rotor of a centrifugal fan. Machine learning is also a successful companion to PIV in order to increase data resolution or impute experimental gaps. While classical algorithms focus solely on replicating data using statistical metrics, the application of Physics Informed Neural Networks (PINN) contributes to both data reconstruction and adherence to governing equations. The present study utilizes a convolutional physics-informed auto-encoder to reproduce planar PIV fields in the gappy regions while also satisfying the mass conservation equation. It proposes a novel approach, which compromises experimental data reconstruction for compliance with physical restrictions. Simultaneously, it is aimed to ensure that the reconstruction error does not considerably deviate from the uncertainty band of the test data. Turbulence scale approximation is employed to set the relative weighting of the physical and non-physical terms in the loss function to ensure that both objectives are achieved. All steps are initially evaluated on a set of DNS data to demonstrate the general capability of the network. Finally, examination of the PIV data indicates that the proposed PINN auto-encoder can enhance reconstruction accuracy by about 28% and 29% in terms of mass conservation residual and velocity statistics, respectively, in expense of up to 5% increase in the number of vectors with reconstruction error higher than the uncertainty band of the PIV test data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑