Nonlinearity Correction in Dynamic Measuring Devices Using Neural Network Models

Abstract

A neural network compensator for the nonlinearity of a dynamic measuring instrument is proposed, which allows restoring the value of the measured input signal. The inverse model of a nonlinear dynamic measuring device is implemented based on a three-layer perceptron supplemented by delay lines of input signals. The properties of the proposed neural network compensator are studied through simulation computer modelling using various types of calibration input signals for the training of an artificial neural network.