Dual-sensory fusion self-powered triboelectric taste-sensing system towards effective and low-cost liquid identification

Abstract

Infusing human taste perception into smart sensing devices to mimic the processing ability of gustatory organs to perceive liquid substances remains challenging. Here we developed a self-powered droplet-tasting sensor system based on the dynamic morphological changes of droplets and liquid–solid contact electrification. The sensor system has achieved accuracies of liquid recognition higher than 90% in five different applications by combining triboelectric fingerprint signals and deep learning. Furthermore, an image sensor is integrated to extract the visual features of liquids, and the recognition capability of the liquid-sensing system is improved to up to 96.0%. The design of this dual-sensory fusion self-powered liquid-sensing system, along with the droplet-tasting sensor that can autonomously generate triboelectric signals, provides a promising technological approach for the development of effective and low-cost liquid sensing for liquid food safety identification and management. The sense of taste plays a major role in the identification and analysis of liquid food types. This study reports a droplet-based, self-powered triboelectric taste-sensing system that integrates two taste-sensing units. Combined with deep-learning data analytics and image recognition, the systems can achieve liquid recognition accuracy of up to 96.0%.