Fluid Classification via the Dual Functionality of Moisture-Enabled Electricity Generation Enhanced by Deep Learning.

Abstract

Classifications of fluids using miniaturized sensors are of substantial importance for various fields of application. Modified with functional nanomaterials, a moisture-enabled electricity generation (MEG) device can execute a dual-purpose operation as both a self-powered framework and a fluid detection platform. In this study, a novel intelligent self-sustained sensing approach was implemented by integrating MEG with deep learning in microfluidics. Following a multilayer design, the MEG device including three individual units for power generation/fluid classification was fabricated in this study by using nonwoven fabrics, hydroxylated carbon nanotubes, poly(vinyl alcohol)-mixed gels, and indium tin bismuth liquid alloy. A composite configuration utilizing hydrophobic microfluidic channels and hydrophilic porous substrates was conducive to self-regulation of the on-chip flow. As a generator, the MEG device was capable of maintaining a continuous and stable power output for at least 6 h. As a sensor, the on-chip units synchronously measured the voltage (V), current (C), and resistance (R) signals as functions of time, whose transitions were completed using relays. These signals can serve as straightforward indicators of a fluid presence, such as the distinctive "fingerprint". After normalization and Fourier transform of raw V/C/R signals, a lightweight deep learning model (wide-kernel deep convolutional neural network, WDCNN) was employed for classifying pure water, kiwifruit, clementine, and lemon juices. In particular, the accuracy of the sample distinction using the WDCNN model was 100% within 15 s. The proposed integration of MEG, microfluidics, and deep learning provides a novel paradigm for the development of sustainable intelligent environmental perception, as well as new prospects for innovations in analytical science and smart instruments.