Methods of Predicting the Drift of the Parameters of Dynamic Objects on the Basis of a Linear Extrapolation Model

Abstract

A method of prediction based on linear extrapolation with the use of the mathematical expectation of the rate of variation of the values of a controlled parameter as the slope of an extrapolating line is presented. A method constructed with the use of a correction of a linear function is considered. Correction is performed with the use in the method of least squares of variable weight coefficients that regulate the influence of the interpolation nodes on the final result as a function of the distance of these nodes from the current values of the argument of the extrapolating function.