ANN-based error reduction for experimentally modeled sensors

A method for correcting the effects of multiple error sources in differential transducers is proposed. The correction is carried out by a nonlinear multidimensional inverse model of the transducer based on an artificial neural network. The model exploits independent information provided by the difference in actual characteristics of the sensing elements, and by an easily controllable auxiliary quantity (e.g., supply voltage of conditioning circuit). Experimental results of the correction of an eddy-current displacement transducer subject to the combined interference of structural and geometrical parameters highlight the practical effectiveness of the proposed method.