Analysis of noisy harmonic signals based on application of non-parametric criterion

The paper presents the results of applying the algorithm based on the nonparametric Wilcoxon criterion for evaluating individual parameters of a noisy harmonic signal in absolute value and a harmonic signal for its positive part of the period. A sinusoidal signal with different amplitude values was selected as a signal, and Gaussian noise as an additive noise. As a result of applying the algorithm, the original noisy signal without preliminary filtering was transformed into a random rank function. To estimate the location of the analysis points, not the values of the rank function themselves were used, but their differences. In this case, the points of transition from positive values of the difference to negative values coincided with the amplitude values of the signal, which ultimately made it possible to estimate the frequency of the noisy signal. The accuracy of this estimate depends on the signal-to-noise ratio.