Non-linear Volterra filtering optimization method based on contribution factor

Abstract

The invention discloses a non-linear Volterra filtering optimization method based on a contribution factor, and the method comprises the steps: 1, obtaining an original output signal of a non-linear Volterra filter; 2, setting the weighting coefficient of each node of the non-linear Volterra filter as zero, forming sub-filters, and obtaining an output signal of each sub-filter; 3, calculating the contribution factor of each node according to the output signal and the original output signal of each sub-filter; 4, comparing the contribution factor of each node with a set threshold value delta, and determining the optimal weighting coefficient of the non-linear Volterra filter; 5, forming an optimized filter according to the optimal weighting coefficient. The method aims at a problem that a conventional non-linear Volterra filtering method is large in calculation burden, proposes a method for searching and deleting the redundant nodes according to the attribution of each node to the corresponding output signal, deletes the redundant nodes with the minimum contribution to the output result under the condition that the filtering performance is not affected, can further reduce the calculation amount, and reduces the occupied resource of engineering implementation.

Description

Technical field [0001] The present invention relates to the technical field of nonlinear Volterra filtering, in particular to a nonlinear Volterra filtering optimization method based on contribution factors. Background technique [0002] The current research proves that under the condition that the input signal energy is limited, the description of the nonlinear system can be arbitrarily approximated by Volterra series. Therefore, the nonlinear Volterra filtering technology has become an effective nonlinear signal processing method. Simple and convenient to operate, it is highly valued in the existing filtering technology field. At present, Volterra filtering technology has been successfully applied to many engineering fields, such as nonlinear system control, radio communication, satellite communication, magnetic tape channel, and biological process modeling. [0003] However, the existing nonlinear Volterra filtering method has the defects of large amount of calculation and larg...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art, and provides a nonlinear Volterra filter optimization method based on contribution factors. This method aims at the problem of large amount of calculation in the existing nonlinear Volterra filter method, and proposes to output according to each node The contribution of the signal, find and delete redundant nodes, so as to reduce the calculation amount of filtering processing, realize filtering optimization, and facilitate the engineering realization of nonlinear Volterra filtering

Images