|
Keywords
|
Ammonia gas sensor, Electronic nose (E-nose), Metal-oxide semiconductor, Convolutional
neutral network (CNN), Sensor data fusion, Agricultural emission monitoring
|
|
Abstract
|
Enhanced Selectivity Electronic
Electronic noses (e-noses) offer a practical solution for real-time monitoring of ammonia (NH3) in
agricultural environments, where NH3 often coexists with interfering gases such as CO2, CH4, and H2S.
However, semiconductor-based gas sensors commonly used in e-nose systems suffer from inherent
cross-sensitivity, which reduces measurement accuracy. This study investigates the cross-sensitivity of
NH3 detection and introduces a mitigation strategy through convolutional neural networks (CNNs) for
sensor data fusion. Experimental results show that WO2-based sensors exhibit strong NH3 selectivity,
with response ratios of 7.3:1 against CH4 and 17.8:1 against H2S. Density functional theory (DFT)
analysis confirmed that the WO3 sensor exhibited strongest NH3 binding energy (− 1.45 eV), compared
to SnO2 (− 1.10 eV), explaining the observed selectivity. Measurement uncertainties (± 8%) were
quantified under varying humidity (30–90% RH) and temperature (10–40 °C) using a weighted least
squares error propagation model. A quasi-2D sensor array improved NH3 classification accuracy to
96.4% (7.2% increase) while reducing concentration errors by 50.8%, as validated by linear discriminant
analysis. Long-term stability tests demonstrated that SnO2 sensors maintained a low baseline drift of
0.18%/day over 180 days, outperforming CH4 (0.31%/day) and ZnO (0.42%/day) sensors. Furthermore,
the CNN model, trained on multi-sensor time-series data, achieved 91.7% accuracy in mixed-gas
environments by capturing non-linear response patterns, ensuring reliable NH3 quantification despite
interferents. These findings highlight the promise of CNN-enhanced e-nose systems for precise
NH3 monitoring in complex agricultural settings, addressing key challenges of cross-sensitivity and
environmental stability
|