Multi-Mems Differential Pressure Sensor Elements-Based Airflow Sensor with Neural Network Model

This paper reports a compact spherical airflow sensor using multi-MEMS differential pressure (DP) sensor elements. Three built-in MEMS sensors simultaneously measure the DP around the spherical housing structure so that the measured DPs are converted into 2D wind direction and speed. The sensor outputs are converted into wind direction and speed by neural network. We attached the calibrated sensor to a toy drone as a demonstration. Then, it was confirmed that the output corresponding to wind direction and speed was measured when a crosswind was applied during flight.