Optimization of the Mixed Gas Detection Method Based on Neural Network Algorithm

Abstract

Real-time mixed gas detection has attracted significant interest for being a key factor for applications of the electronic nose (E-nose). However, mixed gas detection still faces the challenge of long detection time and a large amount of training data. Therefore, in this work, we propose a feasible way to realize low-cost fast detection of mixed gases, which uses only the part response data of the adsorption process as the training set. Our results indicated that the proposed method significantly reduced the number of training sets and the prediction time of mixed gas. Moreover, it can achieve new concentration prediction of mixed gas using only the response data of the first 10 s, and the training set proportion can reduce to 60%. In addition, the convolutional neural network model can realize both the smaller training set but also the higher accuracy of mixed gas. Our findings provide an effective way to improve the detection efficiency and accuracy of E-noses for the experimental measurement.

Intelligent Detection and Odor Recognition of Cigarette Packaging Paper Boxes Based on a Homemade Electronic Nose

“…Given that the resistance values captured by each sensor span a broad range, proper normalization of gas sensor data is essential for enhancing the reliability of predictions for future test data, including those that may extend beyond the range of the training dataset. Several normalization methods exist, such as z-score normalization [17], min-max normalization [18], and baseline normalization [19]. While z-score normalization is widely used, it may not effectively handle non-stationary time-series data.…”

Ultrasensitive Online NO Sensor Based on a Distributed Parallel Self-Regulating Neural Network and Ultraviolet Differential Optical Absorption Spectroscopy for Exhaled Breath Diagnosis

“…Gas sensors using neural network analysis have been widely used to detect gases at the ppb level. − The convolutional neural network (CNN) is a widely used deep learning model, and its special hierarchical structure can be well adapted to the problem of spectral drift in gas spectral data compared with the artificial neural network (ANN). Meanwhile, it can effectively improve the efficiency and accuracy of detection. − Some researchers in their studies have trained the preprocessed absorption spectra as a whole through CNN models. Meanwhile, different absorption characteristic regions of the spectrum contributing differently to the concentration prediction are not considered. − To better combine deep learning technology and spectroscopy technology, in this paper, we construct a distributed parallel self-regulating neural network (DPSRNN) model structure based on the absorption characteristics of UV absorption spectroscopy.…”

Gas Graph Convolutional Transformer for Robust Generalization in Adaptive Gas Mixture Concentration Estimation

“…The experiments' results demonstrate the proposed approach's effectiveness, but the performance varies on different data batches. 28 However, the scope of their data set was confined to only two gas types, raising questions about the model's performance with a broader range of gases. Cheng et al employed a method based on graph convolutional networks (GCNs) to analyze the signals collected from their sensor network across both temporal and spatial dimensions, achieving estimation of gas concentrations.…”

“…Their model demonstrated high adaptability across various scenarios, signaling strong potential in gas analysis but showed variability in recognizing different gas mixtures. Further, Li et al in 2023 optimized a convolutional neural network for mixed gas analysis that excelled in accuracy with a smaller training data set . However, the scope of their data set was confined to only two gas types, raising questions about the model’s performance with a broader range of gases.…”