An ANN-based smart capacitive pressure sensor in dynamic environment

Abstract

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 significantly. In many practical conditions, the effect of temperature on the change in the CPS characteristics may be nonlinear. The proposed ANN model can provide correct readout of the applied pressure under such conditions. A novel scheme for estimation of the ambient temperature from the sensor characteristics itself is proposed. A second ANN is utilized to estimate the ambient temperature from the knowledge of the offset capacitance, i.e., the zero-pressure capacitance. A microcontroller unit (MCU)-based implementation scheme for this model is also considered. Simulation results show that this model can estimate the pressure with a maximum error of ±2% over a wide variation of temperature from −50°C to 150°C.