A comprehensive gas recognition algorithm with label-free drift compensation based on domain adversarial network

• Published in: Sensors and actuators. B, Chemical Vol. 387; p. 133709
• Main Authors: Pan, Xiaofang, Chen, Jiebin, Wen, Xiaolin, Hao, Jiacheng, Xu, Wei, Ye, Wenbin, Zhao, Xiaojin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.07.2023
• Subjects: Concentration measurement; Drift compensation; Electronic nose; Mixture gases; Transfer calibration; Mixture gases; Concentration measurement; Transfer calibration; Drift compensation; Electronic nose
• ISSN: 0925-4005; 1873-3077
• DOI: 10.1016/j.snb.2023.133709

For most applications, the sensor system needs to identify/measure target gases in mixture conditions simultaneously, while countering the performance degradation caused by the drift deviation and batch to batch discrepancy. To solve these problems, we propose a comprehensive algorithm, hybrid attention-based transformer network with domain adversarial learning (HATN-DA). Inside it, multi-head transformer and channel-wise attention mechanism serving as main blocks of the feature extractor effectively capture temporal dependencies and lays emphasis on the diversities of sensors. Then, the capsule vector is applied in the predictor to encode gas species into the concentration information. Besides, the domain discriminator calculates Wasserstein distance of gas features between source and target domains, which is optimized through the back propagation by the feature extractor during the training process. Based on this, label-free drift compensation and transfer calibration effects are achieved: for public dataset, HATN-DA achieves 97.50∼100% accuracies for drift compensation experiment; for dataset of mixture gases, in the batch transfer tasks, HATN-DA achieves an accuracy of 98.79%, significantly improved compared to 90.16% (before transfer). Besides, in the cross-domain real-time concentration prediction tasks, HATN-DA achieves a normalized root mean squared error of 3.32%, 3.25%, 6.62% and 3.01% for ethanol, methane, carbon monoxide and ethylene. •Accurate and robust mixture gases identification and concentration detection.•Label-free domain adaptation based on Wasserstein distance for transfer calibration and drift compensation.•Transformer and channel-wise attention mechanism for dynamical feature extraction.•Capsule vector to encode the gas concentration information into the category information.