Intelligently detecting and identifying liquids leakage combining triboelectric nanogenerator based self-powered sensor with machine learning

Self-powered, rapidly-responding and cost-effective sensor is greatly needed in liquids leakage detection. Here, a single electrode liquid-solid (SELS) triboelectric nanogenerator (TENG) with a triboelectric layer of p-type silicon was designed and its performances for liquids leakage detecting and identifying were studied. The results demonstrated that the designed SELS TENG was sensitive to very small liquids leakage and could qualitatively characterize the leakage rate of liquid. The difference between the short-circuit output currents of the SELS TENG responding to several liquids was mainly considered as from their different conductivity and wettability. In addition, the short-circuit output currents of SELS TENG responding to different liquids were considered as their fingerprint and used to identify liquids. A great deal of sensors in practical application generated a great of data and an intelligent detecting and identifying system was designed to identify different liquids based on big data and machine learning technologies. High classification accuracies over 90% were obtained for each two liquids in most of cases. These findings shed light on the application of TENG based self-powered sensors in liquid leakage detecting and environment monitoring fields. Most importantly, the great potential application of TENG combined with big data and machine learning technologies was successfully explored and exhibited.