Modeling of thermal-conductivity of smart humidity sensor

This paper presents a design of a smart humidity sensor. First we begin by the modeling of a thermal-conductivity based humidity sensor (THS). Using neuronal networks and Matlab environment to accurately express the non-linearity, the cross sensitivity and the hysteresis of the output sensor used. We have done the training to create an analytical model dasiaTHSpsila. In a second step a linearization, by Matlab program, is applied to THS response whose goal is to create a database for an element of correction dasiaCORRECTORpsila. After that we use the bias matrix and the weights matrix obtained by training to establish the THS model and the CORRECTOR model on PSPICE simulator, where the output of the first is identical to the output of the THS and the last correct its nonlinear response, eliminate the hysteresis effect and the cross sensitivity.