An ANN-based smart capacitive pressure sensor in dynamic environment

A multilayer artificial neural network (ANN) is proposed for modeling of a capacitive pressure sensor (CPS). When the ambient temperature changes over a wide range, the nonlinear response characteristics of a CPS change signi ficantly. In many practical conditions, the effect of temperature on the ch ange in the CPS characteristics may be nonlinear. The proposed ANN model ca n provide correct readout of the applied pressure under such conditions. A novel scheme for estimation of the ambient temperature from the sensor char acteristics itself is proposed. A second ANN is utilized to estimate the am bient temperature from the knowledge of the offset capacitance, i.e., the z ero-pressure capacitance. A microcontroller unit (MCU)-based implementation scheme for this model is also considered. Simulation results show that thi s model can estimate the pressure with a maximum error of +/- 2% over a wid e variation of temperature from - 50 degreesC to 150 degreesC. (C) 2000 Els evier Science B.V. All rights reserved.