Pulse-driven MEMS gas sensor combined with machine learning for selective gas identification.

Abstract

The sensing and identification of trace gases are essential for ensuring chemical safety and protecting human health. This study introduces a low-power electronic nose system that utilizes a single sensor driven by repeated pulsed power inputs, offering a viable alternative to conventional sensor array-based methods. The sensor's compact design and suspended architecture facilitate a rapid thermal response, effectively decoupling the influences of temperature, physisorption, and charge exchange on the conductivity of the sensing material. This mechanism generates distinct gas sensing responses, characterized by alternating dual responses within a single time period. The unique dynamics of the dual signals, which vary with gas type and concentration, enable precise identification of multiple gas species using machine learning (ML) algorithms. Microfabricated through wafer-level batch processing, our innovative electronic nose system holds significant potential for battery-powered mobile devices and IoT-based monitoring applications.