Automated real-time tuning improves fluid flow measurement accuracy
ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control
Artificial IntelligenceComputer Vision and Pattern Recognition
Summary
Measuring how fluids move using cameras can be tricky because the method involves many settings that experts usually adjust by hand. The authors created a system called ART of PIV that automatically chooses the best settings for each pair of images based on current conditions. This makes the measurements faster and more accurate, especially when the fluid conditions change or when the measurements are used to control fluid flow in real time. They tested their system in simulations and a water tank with spinning cylinders, showing it works better than fixed settings.
What this means in practice
- •For industrial process control teams: Use automated tuner to improve real-time fluid velocity measurements for efficient flow control in manufacturing systems.
- •For civil engineering maintenance teams: Deploy real-time adaptive flow measurement systems to monitor and adjust water flows in infrastructure like flood control channels.
Authors
Antonio Terpin, Francesco Banelli, Alan Bonomi, Raffaello D'Andrea
Abstract
Particle image velocimetry (PIV) measures fluid motion from images of tracer particles, but its accuracy depends on choices throughout the estimation pipeline, including image preprocessing, flow estimation, and postprocessing. These choices are typically left to expert tuning, and a fixed configuration can become less accurate as conditions change. This matters especially when PIV supplies feedback for real-time control, where measurements must be both accurate and fast, and flow conditions vary. We introduce ART of PIV -- short for Agentic Real-Time and also a nod to the art of tuning a PIV pipeline -- which automates pipeline choice for each image pair. A learned agent selects a configuration according to a chosen measurement objective from a library assembled for a specified speed budget. Across cross-correlation, classical optical-flow, and learning-based estimators, ART of PIV reduces average end-point error (AEPE) by 12.2-22.4 % relative to the best single estimator at matched speed, with gains extending to 1000-4000 image pair/s. In a simulated local velocity regulation task, it reduces mean normalized closed-loop cost by 13.24-13.59 percentage points relative to a tuned fixed estimator, with the same classical controller in both cases. In a tabletop water channel, we illustrate two ways to tune ART of PIV for a fluidic pinball of three rotating cylinders: selecting between complementary optical-flow tunings for accuracy, and selecting regions of interest with coherent rotation or shear using a common flow estimator. For the first variant, we train a DreamerV3 reinforcement learning controller directly in the physical world and demonstrate tracking of a prescribed flow field in the wake of a fluidic pinball.