LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mapping

2025-08-19

AI Summary

Particle image velocimetry (PIV) struggles to simultaneously achieve high temporal frequency and high spatial resolution in turbulent wake flows, whereas wall-pressure measurements—though spatially sparse—are readily acquired at high sampling rates. Method: We propose LatentFlow, a novel framework that reconstructs high spatiotemporal-resolution turbulent wake fields directly from sparse, high-frequency wall-pressure signals. It employs a physics-constrained β-VAE (pC-β-VAE) to learn a compact, disentangled latent space separating flow spatial structure from pressure-driven temporal dynamics; a two-stage network maps pressure time series to latent variables, which are then decoded into 512-Hz velocity fields. Contribution/Results: Trained solely on low-frequency (15 Hz) PIV data synchronized with high-frequency pressure measurements, LatentFlow achieves high-fidelity wake reconstruction. It eliminates the conventional requirement for dense, high-resolution flow-field annotations, markedly advancing data-driven turbulence modeling under sparse sensing and enhancing practical applicability in engineering settings.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Time-Series/Data Streams
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Large-scale security measurements

Abstract

Acquiring temporally high-frequency and spatially high-resolution turbulent wake flow fields in particle image velocimetry (PIV) experiments remains a significant challenge due to hardware limitations and measurement noise. In contrast, temporal high-frequency measurements of spatially sparse wall pressure are more readily accessible in wind tunnel experiments. In this study, we propose a novel cross-modal temporal upscaling framework, LatentFlow, which reconstructs high-frequency (512 Hz) turbulent wake flow fields by fusing synchronized low-frequency (15 Hz) flow field and pressure data during training, and high-frequency wall pressure signals during inference. The first stage involves training a pressure-conditioned $β$-variation autoencoder ($p$C-$β$-VAE) to learn a compact latent representation that captures the intrinsic dynamics of the wake flow. A secondary network maps synchronized low-frequency wall pressure signals into the latent space, enabling reconstruction of the wake flow field solely from sparse wall pressure. Once trained, the model utilizes high-frequency, spatially sparse wall pressure inputs to generate corresponding high-frequency flow fields via the $p$C-$β$-VAE decoder. By decoupling the spatial encoding of flow dynamics from temporal pressure measurements, LatentFlow provides a scalable and robust solution for reconstructing high-frequency turbulent wake flows in data-constrained experimental settings.

Problem

• Reconstructing high-frequency turbulent wake flow fields
• Overcoming hardware limitations in PIV experiments
• Mapping sparse pressure data to flow dynamics

Innovation

• Pressure-conditioned autoencoder for latent representation
• Mapping low-frequency pressure to latent space
• High-frequency flow reconstruction from pressure signals