A Hybrid MTL-CNN Architecture for Simultaneous Mixed Gas Identification and Concentration Estimation

The detection of hazardous gases and the localization of gas leaks heavily rely on electronic nose (E-nose) systems. However, most existing robotic detection and localization approaches rely on a single gas sensor and assume a single-gas leakage scenario, neglecting the potential interference from other gas components in complex environments. Moreover, conventional machine learning algorithms, constrained by the sequential process of data preprocessing, feature extraction, and training-validation, fail to meet the real-time concentration prediction. To address these limitations, this paper proposes a novel multi-task learning convolutional neural network (MTL-CNN) algorithm capable of simultaneous gas classification and concentration prediction. Compared to traditional methods, the proposed MTL-CNN achieves significant improvements in both classification and regression tasks, while enabling real-time prediction by eliminating manual feature extraction. Experiments were conducted using methane (CH<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</inf>), carbon dioxide (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>), and their mixtures. The results demonstrate a classification accuracy of 97.7778%, with mean absolute errors (MAE) for concentration regression of 2.2825 ppm (CH<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</inf>), 26.242 ppm (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>), and 2.8191 ppm (CH<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</inf> in mixtures), respectively.