<p>This study develops a portable tea aroma detection stick system based on the Arduino Uno R3 microcontroller, equipped with six metal oxide gas sensors: MQ2, MQ3, MQ4, MQ5, MQ7, and MQ9. The system can quickly and conveniently collect aroma data from different quality grades of tea, and subsequently utilizes deep learning algorithms to classify the tea aromas, thus verifying the functionality of the system. Additionally, in response to the data characteristics of the gas sensor array, this paper proposes a Grouped Convolutional Hybrid Attention Mechanism (GCHAM) that combines channel information and spatial information. By focusing attention on the key information that affects classification performance, GCHAM suppresses noise and irrelevant information, enhancing the model’s feature representation capability. We introduce a high-performance tea gas classification network that combines GCHAM with depthwise separable convolution and elastic net regularization. By comparing with multiple attention mechanisms, machine learning, and deep learning models, the results show that the proposed method has superior recognition performance, with recognition accuracy, precision, recall, and F1 score of 95.33%, 95.47%, 95.92%, and 95.52%, respectively. The integration of the portable tea aroma detection stick system with the tea gas classification network can serve as a convenient and efficient detection technology for tea quality evaluation.</p>