The leakage of HCHO gas has direct and irreversible damage on both human health and the environment. However, the current commercial electronic nose (E-nose) has low accuracy in predicting the concentration of HCHO. In this work, a sensor array consisting of 6 gas sensors was fabricated and combined with advanced deep learning algorithms to achieve accurate prediction of HCHO concentration. High-performance SnO 2 sensing material with high specific surface area was synthesized by applying the Metal-Organic Frameworks (MOFs) sacrificial template, and the response of the SnO 2 gas sensor was as high as 15.098, which is much higher than that of commonly used commercial sensors. In addition, the sensing performance of the SnO 2 sensor, including response, selectivity and repeatability etc., were investigated. Afterward, a Formaldehyde Prediction Network (FPNet) model was proposed for processing the HCHO gas dataset and cosine annealing was added to gradually reduce the learning rate during training to help the model converge to the optimal solution. Furthermore, the residual structures with different number of layers were compared, and the 3-layer residual structure expressed the most accurate results of concentration prediction of the HCHO gas, with an MSE of 9.003, MAPE of 0.015, and R 2 of 0.998. This study provides a new idea from sensor preparation to pattern recognition algorithm research, effectively solving the problems of the low response of commercial sensors to HCHO and the low accuracy of pattern recognition algorithms for E-nose datasets.
Graphical In this article, a Sm−Pd bimetal doped SnO 2 -based MEMS C 2 H 2 sensor was prepared for detecting dissolved acetylene gas in transformer oil. It has the unique advantages of high sensitivity, high selectivity and low power consumption. Acetylene (C 2 H 2 ), as an important characteristic gas in transformer fault diagnosis, should be accurately detected and effectively distinguished from other dissolved gases (H 2 , CH 4 , C 2 H 6 , C 2 H 4 , CO, CO 2 ), which is crucial to determine whether the fault occurs and the fault type, but also faces challenges now. The rational design and employment of rare earth and noble metals are expected to address this issue. In this work, SnO 2 -3 at% Sm 2 O 3 -1 at% PdO based MEMS gas sensor was prepared to achieve high performance detection of C 2 H 2 which has a response value of 56 to 50 ppm C 2 H 2 , response/recovery time of 2 s/136 s, lower detection limit of 1 ppm, power consumption of 15.5 mW, and weak cross sensitivity to other transformer fault characteristic gases. Lewis acids and bases theory was used to explain the reason why rare earth Sm is a benefit element to improve selectivity to C 2 H 2 . The formation of oxygen vacancies and hetero junctions was used to explain the increased sensitivity of the material. This study proved the feasibility of rare earth and noble metals as potential additives to enable advanced gas-sensitive materials for highly selective transformer fault characteristic gas C 2 H 2 detection.
危险品化学品经营许可证（带存储）