Modeling the Algorithm of Cumulative Sums in the Applied Problems of Detecting the Signals with Random Time of Occurrence in non-Gaussian Noise

摘要

The methods of mathematical modeling of the cumulative sums algorithm in the problems of detecting signals with a random moment of occurrence in non-Gaussian noise are considered. The probability of false alarm errors and correct detection of imbalance based on the statistical characteristics of the algorithm of cumulative sums obtained by modeling real processes is calculated. An experimental distribution of the cumulative sum in state of imbalance at a current step for detection without reflecting or absorbing screens is obtained. A linear dependence between the means of the cumulative sum taken in separate sections is determined. Based on modeling real processes, the probability of correct detection and false alarm under the influence of non-Gaussian noise with a bimodal distribution is calculated. Effectiveness of cumulative sums algorithm both consistent and inconsistent with the density of the probability distribution of influencing noise is compared.