NEURAL NETWORK FOR THE MODELING OF NO{sub}x MICROSENSOR WITH SENSING ELEMENT CARDO POLYSULFONE

摘要

The sensor was made by thick film technology, A polymeric structure as sensitive layer containing cardo polysulfone has been tested in nitric oxides sensing. Feed-forward neural networks with two hidden layers are used in mathematical modeling of the system, to predict the voltage of the sensor at a certain time. In this way, the efficiency of the sensor can be appreciated. An alternative methodology of modeling was based on empirical equations that explicitly render the characteristic voltage - time. Both types of models provide accurate predictions that means they describe well the actual behavior of the sensor.