Determining of Signal Derivatives in Identification Problems- FIR Differential Filters

Abstract

The paper presents a methodology for designing regression filters. The signal x needs to be locally approximated in the neighbourhood of the instant t using a polynomial of an appropriate degree. The values of the signal derivatives are then determined basing on the polynomial parameters. An advantage of the regression differentiating filters is that it is possible to obtain a filtered signal with the same length as that of the original signal. An example of solving the parameter identification problem in case of robot with four degrees of freedom has been also presented.