ARTIFICIAL NEURAL-NETWORK-BASED NONLINEARITY ESTIMATION OF PRESSURE SENSORS

A new approach to pressure sensor modelling based on a simple function al link artificial neural network (FLANN) is proposed. The response of the sensor is expressed in terms of its input by a power series. In t he direct modeling, using a FLANN trained by a simple neural algorithm , the unknown coefficients of the power series are estimated accuratel y. The FLANN-based inverse model of the sensor can estimate the applie d pressure accurately. The maximum error between the measured and esti mated values is found to be only +/- 2%. The existing techniques utili ze ROM or nonlinear schemes for linearization of the sensor response. However, the proposed inverse model approach automatically compensates the effect of the associated nonlinearity to estimate the applied pre ssure. Frequent modification of the ROM or nonlinear coding data is re quired for correct readout during changing environmental conditions. U nder such conditions, in the proposed technique, for correct readout, the FLANN is to be retrained and a new set of coefficients is entered into the plug-in module. Thus this modeling technique provides greater flexibility and accuracy in a changing environment.