Neural network sensitivity analysis of the detected signal from an SO₂ electrode

A novel SO₂ electrode was made by doping polyaniline onto Nafion to detect SO₂ at ppm level with a linear correlation between the response current and the SO₂ concentration in the range of 20 to 250 ppm. By applying artificial neural network, it was possible to predict the SO₂ concentration so that a shorter response time (3 min compared with 6 min) was achieved without the need of a noise filter. The operation conditions, cycles for acid/base treatment and immersion time, considered as the affecting factors of the polyaniline membrane treatment were used for the study of sensitivity analysis. Both the results analyzed from the transfer functions of 2/(1 + e^-x) and sgn(x)·x²/(1 + x²) are presented. Prediction of the neural network for sensitivity analysis of the SO₂ electrode signal was tested first. Then, the two operation variables considered as important factors affecting the properties of the membrane were studied in view of their influence toward the response current.