Abstract
The nonlinear response characteristics of a capacitive pressure sensor (CPS) changes when ambient temperature changes widely. In such condition, the calibration becomes difficult and to obtain accurate pressure readout, appropriate compensation to the CPS characteristics is needed. We propose an intelligent CPS using rough set neural networks (RSNN) to provide self-calibration and compensation. The proposed model based on rough set and neural networks can provide the calibrated response characteristics irrespective of change in the sensor characteristics due to change in ambient temperature using rough set theory and compensates the nonlinearity in the respond characteristics using neural networks. Simulation results show that this model can estimate the pressure with a maximum full-scale error of plusmn2.5 percent over a variation of temperature from -50degC to 150degC