GrainSense: A Wireless Grain Moisture Sensing System Based on Wi-Fi Signals

Abstract

Grain moisture sensing plays a critical role in ensuring grain quality and reducing grain losses. However, existing commercial off-the-shelf (COTS) grain moisture sensing systems are either expensive, inconvenient or inaccurate, which greatly limit their widespread deployment in real-world scenarios. To fill this gap, we develop a system called GrainSense which leverages COTS Wi-Fi devices to detect the grain moisture without the need for dedicated sensors. Specifically, we propose a wireless grain moisture detection model based on the refraction phenomenon of Wi-Fi signals and the Multiple-Input-Multiple-Output (MIMO) technology. On one hand, we correlate the grain moisture with the phase difference between two refracted Wi-Fi signals that propagate along different paths, based on which grain moisture can be deduced accordingly. On the other hand, to reduce the multi-path interference in indoor environments (e.g., the granary), we adopt Wi-Fi beamforming to enhance the refracted signal. In particular, a new signal feature (i.e., the Wi-Fi CSI beamforming ratio) is designed to eliminate the effect of sub-carrier frequency bias and cumulative phase bias. To validate the effectiveness of the developed system, we conduct extensive experiments with different types of grains in both the laboratory and the granary. Results show that the system can accurately estimate the grain moisture with an mean absolute error smaller than 5%, which meets the requirements for commercial usage. To the best of our knowledge, this is the first model-based work that achieves accurate grain moisture detection based on wireless sensing.