Impedance-based multivariate analysis for accurate estimation of H₂S concentrations using CuCrO₂ gas sensor

This study unveils an innovative approach to fabricating H₂S gas sensor prototypes for continuous monitoring, leveraging Pd-decorated CuCrO₂-based metal oxide semiconductor (MOS) chemiresistors and artificial neural network-assisted impedance-based multivariate analysis. Sensors were exposed to H₂S in cross-interfering environments containing humidity, NO₂, NH₃, CH₄, H₂, and CO₂. Impedance-based parameters (Z, phase difference, Z′ and Z") obtained at various frequencies demonstrated that sensors were reproducible and selective for H₂S detection. A neural network-based multilayer perceptron (MLP) regression model was trained with different impedance-based parameters to estimate the H₂S concentrations. Continuous operation resulted in larger baseline variation for Z, Z′, and Z" readings; however, the measured phase difference values exhibited less depletion than other parameters. Furthermore, concerns about baseline changes were effectively addressed with a fine-tuned MLP model, which predicted both pure air and H₂S atmospheres more correctly under cross-interfering and baseline-depleted conditions by employing phase differences at different frequencies as input. Possible reasons for the accurate prediction can be attributed to the confined behaviour of phase difference and discussed with the help of sensor statistical parameters such as mean variation, standard deviation and principal components.