Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning

TL;DR

This paper introduces a non-invasive deep learning approach using piezoelectric sensor data to accurately estimate vehicle velocity and angle of attack from structural vibrations, validated in hypersonic wind tunnel experiments.

Contribution

It presents a novel method combining piezoelectric sensors and CNNs for estimating aerodynamic variables without flow instrumentation, demonstrated in controlled hypersonic wind tunnel tests.

Findings

Mean velocity error below 2.27 m/s (0.21%)

Mean AoA error of 0.44 degrees (8.25%)

Effective post-processing improves robustness

Abstract

Accurate estimation of aerodynamic state variables such as freestream velocity and angle of attack (AoA) is important for aerodynamic load prediction, flight control, and model validation. This work presents a non-intrusive method for estimating vehicle velocity and AoA from structural vibration measurements rather than direct flow instrumentation such as pitot tubes. A dense array of piezoelectric sensors mounted on the interior skin of an aeroshell capture vibrations induced by turbulent boundary layer pressure fluctuations, and a convolutional neural network (CNN) is trained to invert these structural responses to recover velocity and AoA. Proof-of-concept is demonstrated through controlled experiments in Sandia's hypersonic wind tunnel spanning zero and nonzero AoA configurations, Mach~5 and Mach~8 conditions, and both constant and continuously varying tunnel operations. The CNN is trained and evaluated using data from 16 wind tunnel runs, with a temporally centered held-out interval within each run used to form training, validation, and test datasets and assess intra-run temporal generalization. Raw CNN predictions exhibit increased variance during continuously varying conditions; a short-window moving-median post-processing step suppresses this variance and improves robustness. After post-processing, the method achieves a mean velocity error relative to the low-pass filtered reference velocity below 2.27~m/s (0.21\%) and a mean AoA error of $0.44^{\circ} (8.25\%)$ on held-out test data from the same experimental campaign, demonstrating feasibility of vibration-based velocity and AoA estimation in a controlled laboratory environment.