Romeo: Fault Detection of Rotating Machinery via Fine-Grained mmWave Velocity Signature

Real-time velocity monitoring is pivotal for fault detection of rotating machinery. However, existing methods rely on either troublesome deployments of optical encoders and IMU sensors or various tachometers delivering coarse-grained velocity measurements insufficient for fault detection. To overcome these limitations, we propose Romeo as the first work to exploit the mmWave radar for rotating machinery fault detection by extracting a fine-grained velocity signature. Though mmWave radars should capture instant rotation information with their claimed high sensitivity and sampling rate, direct adoption entails significant efforts for high-precision velocity measurement per radar to handle; particularly, exhausted system calibration and noise interference. To this end, we first develop a phase-velocity model to characterize the relationship between the mmWave signal phase and the fine-grained angular velocity. We then explore the geometric properties of specific positions in the rotation trajectory to precisely calibrate the rotation sensing model, leading to an iterative algorithm for accurate angular velocity measurement. Finally, we propose a simple yet effective fault detection algorithm by extracting a unique velocity signature. Our extensive experiments show Romeo achieves a median error of 0.4°/s for fine-grained angular speed measurement, outperforming SOTA solutions with over ×16 angular speed granularity and ×7 measurement precision.