arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.07568physics.flu-dyn
收藏

用于单色激光诱导荧光多场可视化的物理信息神经网络

Physics-informed neural networks for multi-field visualization with single-color laser induced fluorescence

Nagahiro Ohashi, Leslie K. Hwang, Beomjin Kwon

AI总结:

本研究针对稀疏实验数据场重建的不适定问题,提出用物理信息神经网络结合单色激光诱导荧光数据重建多场,引入迁移学习提效,经验证精度较高且可实现近实时重建。

摘要:

从稀疏观测数据中重建场是一个不适定问题,存在于诸多工程与科学应用场景中。本文研究利用物理信息神经网络(PINNs,Physics-informed neural networks),从通过单色激光诱导荧光(LIF,laser-induced fluorescence)获取的稀疏含噪实验温度数据中,重建完整的温度、速度与压力场。研究将PINNs应用于层流混合对流系统——这是一种复杂但具有基础重要性的现象,其特征是瞬态强制对流与自然对流行为同时存在。为提升计算效率,本研究还探索了迁移学习(TL,transfer learning)作为大幅缩短场重建耗时的手段。研究结果表明,PINNs效果显著,能够消除大部分不符合控制物理定律的实验噪声。此外,研究显示TL方法与常规训练方案相比误差在5%以内,同时将计算时间缩短了9.9倍。研究采用非同步粒子图像测速法(PIV,particle image velocimetry)和有限体积法(FVM,finite volume method)模拟对PINN重建结果进行验证:PINN重建的速度场与PIV测得的结果高度吻合;以FVM数据为参考时,平均温度误差低于1%,压力与速度误差低于10%。本研究揭示了利用PINNs结合实验数据求解不适定问题的可行性,同时凸显了TL实现近实时场重建的潜力。

英文摘要:

Reconstructing fields from sparsely observed data is an ill-posed problem that arises in many engineering and science applications. Here, we investigate the use of physics-informed neural networks (PINNs) to reconstruct complete temperature, velocity and pressure fields from sparse and noisy experimental temperature data obtained through single-color laser-induced fluorescence (LIF). The PINNs are applied to the laminar mixed convection system, a complex but fundamentally important phenomenon characterized by the simultaneous presence of transient forced and natural convection behaviors. To enhance computation efficiency, this study also explores transfer learning (TL) as a mean of significantly reducing the time required for field reconstruction. Our findings demonstrate that PINNs are effective, capable of eliminating most experimental noise that does not conform to governing physics laws. Additionally, we show that the TL method achieves errors within 5% compared to the regular training scheme while reducing computation time by a factor of 9.9. We validate the PINN reconstruction results using non-simultaneous particle image velocimetry (PIV) and finite volume method (FVM) simulations. The reconstructed velocity fields from the PINN closely match those obtained from PIV. When using FVM data as a reference, the average temperature errors are below 1%, while the pressure and velocity errors are below 10%. This research provides insights into the feasibility of using PINNs for solving ill-posed problems with experimental data and highlights the potential of TL to enable near real-time field reconstruction.

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。

↑