Search

Abstract Human–robot interface (HRI) electronics are critical for realizing robotic intelligence. Here, we report graphene‐based dual‐function acoustic transducers for machine learning‐assisted human–robot interfaces (GHRI). The GHRI functions both an artificial ear through the triboelectric acoustic sensing mechanism and an artificial mouth through the thermoacoustic sound emission mechanism. The success of the integrated device is also attributed to the multifunctional laser‐induced graphene, as either triboelectric materials, electrodes, or thermoacoustic sources. By systematically optimizing the structure parameters, the GHRI achieves high sensitivity (4500 mV Pa–1) and operating durability (1 000 000 cycles and 60 days), capable of recognizing speech identities, emotions, content, and other information in the human speech. With the assistance of machine learning, 30 speech categories are trained by a convolutional neural network, and the accuracy reaches 99.66% and 96.63% in training datasets and test datasets. Furthermore, GHRI is used for artificial intelligence communication based on recognized speech features. Our work shows broad prospects for the development of robotic intelligence.

In a transformer, the insulation materials will produce different dissolved gases due to various faults in the operation of the transformer, in which C2H2, CH4, and H2 are the main dissolved gases. In this study, the adsorption characteristics of the above three gases on the SnO2–GeSe monolayer surface were discussed and analyzed based on the density functional theory. The adsorption energy, transfer charge, geometric structure parameters, electronic density of states, electronic local function, charge difference density, and recovery time were calculated and compared to characterize the gas-sensing adsorption mechanism. The results showed that the SnO2–GeSe monolayer exhibited good adsorption capacity, selectivity, and repeatability for the three characteristic dissolved gases. After adsorbing CH4 gas molecules, the conductivity of the SnO2–GeSe monolayer decreased. After adsorbing C2H2 and H2 gas molecules, the conductivity of the SnO2–GeSe monolayer increased. Therefore, the SnO2–GeSe monolayer has great application potential in the real-time monitoring of dissolved gases in insulating materials, which may become a new type of resistive gas sensor.

SF6 is a common insulating medium of gas-insulated switchgear (GIS). However, it is inevitable that SF6 will be decomposed due to partial discharge (PD) in GIS, which will cause hidden dangers to the safe and stable operation of equipment. Based on the DFT method, the two-dimensional nano-composite As-doped h-BN (As-BN) monolayer was proposed. By modeling and calculating, the ability of an As-BN monolayer as a specific sensor for SO2F2 (compared with an H2O adsorption system and CO2 adsorption system) was evaluated by parameters such as the binding energy (Eb), adsorption energy (Eads), transfer charge (ΔQ), geometric structure parameters, the total density of states (TDOS), band structure, charge difference density (CDD), electron localization function (ELF), sensitivity (S), and recovery time (τ). The results showed that an As-BN monolayer showed strong adsorption specificity, high sensitivity, and short recovery time for SO2F2 gas molecules. Therefore, the As-BN monolayer sensor has great application potential in the detection of SF6 decomposition gases.

In the post-epidemic era, industrial production has gradually recovered, and the attendant air pollution problem has attracted much attention. In this study, the Zr-doped h-BN monolayer (Zr-BN) is proposed as a new gas sensor for air pollution. Based on density functional theory (DFT), we calculated and compared the adsorption energies (Eads), geometric parameters, the shortest distance between gas and substrate (dsub/gas), density of states (DOS), electron localization function (ELF), charge density difference (CDD), band structure, band gap energy change rate (ΔEg), and sensitivity (S) of Zr-BN adsorption systems (SO2F2, SOF2, SO2, NO, and CO2 adsorption systems). The results show that Zr-BN had strong adsorption and high sensitivity to the above-mentioned polluted gases, and the sensitivity was in the order of SOF2 > SO2F2 > CO2 > SO2 > NO. Therefore, this study provides a theoretical basis for the preparation of Zr-BN gas sensors and provides new ideas and methods for the development of other gas sensors.