Modeling of a smart humidity sensor

This work aims to achieve a design of a smart humidity sensor, the goal of this study is to eliminate the non-linearity and the cross sensitivity of the output sensor used. The humidity sensor is a MEMS capacitive kind. Using neuronal networks and Matlab environment we have done the training to design an analytical model ANN and create a model for this component in the PSPICE simulator library, where the output of this model is identical to the output of the MEMS humidity sensor used. Because our sensor is a capacitive type, the obtained model on PSPICE reflects the humidity variation by a capacity variation, which is a passive magnitude; it requires a conversion to an active magnitude, why we realize a conversion capacity/voltage using a switched capacitor circuit SCC. A linearization, by a Matlab program, is applied to ANN response whose goal is to create a database for an element of correction, can correct its nonlinear response. The training for the new database provides us with the inverse model INV-ANN. The three blocks; ANN model, model reverse INV-ANN and the capacity/voltage converter, represent the smart sensor.