mmVibFlow: Gauging the Airflow of Air Conditioning Using mmWave Signal

Effective heating, ventilation, and air conditioning (HVAC) systems are increasingly vital for public health, safeguarding indoor air quality and occupant safety across residential, occupational, and educational settings. Accurate, real-time monitoring of airflow speed is essential for optimizing HVAC performance and ensuring healthy environments. However, existing solutions face significant limitations: traditional anemometers are intrusive and incur high deployment costs, acoustic methods raise severe privacy concerns and are highly susceptible to environmental noise, and contact-based vibration sensors struggle to isolate blade micro-vibrations from overwhelming chassis noise. Millimeter-wave (mmWave) radar emerges as a compelling alternative, offering non-contact, privacy-preserving, and noise-robust sensing. Furthermore, it significantly reduces the Total Cost of Ownership (TCO) by multiplexing existing smart building sensors for a zero-marginal-cost deployment. Yet, the core challenge of reliably distinguishing and extracting fan blade micro-vibrations from dominant structural vibrations using commodity mmWave radar in noisy HVAC environments remains largely unaddressed. Motivated by this gap and the potential of mmWave sensing, we propose mmVibFlow, a mmWave radar-based method for airflow speed estimation by capturing the micro-vibrations of fan blades. mmVibFlow identifies the operating gear (speed level) of an air conditioner and predicts real-time airflow speed from the machine’s vibrations. To effectively distinguish mechanical chassis vibrations from the target fan blade micro-vibrations, we develop an interference-resistant vibration sensing framework. This framework first utilizes beamforming to decorrelate vibrations from the blade region and the chassis, then employs phase-based subtraction to isolate the fan blade vibrations. To extract informative features for airflow speed estimation from RF signals, we develop a signal representation method that captures multi-domain frequency features at different airflow speeds. We validate mmVibFlow, achieving 99% accuracy in gear classification and a mean squared error (MSE) of 0.05 in airflow speed estimation when the radar is placed within 1.5 meters of the air conditioner outlet. Experimental results demonstrate that mmVibFlow accurately measures airflow speed in real-world environments.