Artificial neural network-based nonlinearity estimation of pressure sensors

Abstract

A new approach to pressure sensor modeling based on a simple functional link artificial neural network (FLANN) is proposed. The response of the sensor is expressed in terms of its input by a power series. In the direct modeling, using a FLANN trained by a simple neural algorithm, the unknown coefficients of the power series are estimated accurately. The FLANN-based inverse model of the sensor can estimate the applied pressure accurately. The maximum error between the measured and estimated values is found to be only /spl plusmn/2%. The existing techniques utilize 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 pressure. Frequent modification of the ROM or nonlinear coding data is required for correct readout during changing environmental conditions. Under 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. >