Real-Time Gas Composition Identification and Concentration Estimation Model for Artificial Olfaction

Accurately and quickly identifying the gas composition and estimating the concentration are critical for ensuring industrial gas safety. However, conventional gas discrimination and concentration estimation models are unable to directly employ the raw dynamic response signal of the sensor array to accurately identify gases and estimate their concentrations online. To overcome this limitation, a cascaded approach that combines a dynamic wavelet coefficient map-axial attention network (DWCM-AAN) model for identifying gases and a prelayer normalization weighted dynamic response signal-cosformer (WDRS-cosformer) for estimating the concentration of each gas component is developed in our work. Both models directly employ the real-time dynamic response signals of the sensor array as input without any signal preprocessing. Experimental validation of CO, H-2, CO, and H-2 gas mixture on our fabricated artificial olfaction revealed that the DWCM-AAN model can achieve nearly 100% accuracy in gas identification and enhance identification in real time with fewer labeled data samples. Moreover, our proposed WDRS-cosformer model achieves greater precision in concentration estimation for all different gases compared to existing state-of-the-art concentration estimation methods.

Automated summary

In this work, a cascaded approach combining a dynamic wavelet coefficient map-axial attention network model and a prelayer normalization weighted dynamic response signal-cosformer model is proposed for accurate gas identification and concentration estimation using real-time dynamic response signals.