Search

In order to determine the technical condition of energetic objects with the objective of ensuring their operational reliability, durability and safety, systems of noise diagnostics, which are based on the analysis of acoustic diagnostic signals. A promising area of noise diagnostics are cumulant methods, based on cumulant analysis, which involves the use of cumulants and cumulant coefficients. In known literature no characteristics of detection of a signal within an interference-containing additive mixture with the use of a second-order cumulant (variance) can be found. That is why the objective of the paper is to study the use of cumulant method on the basis of point estimations of variance for a sample of momentary values for detection of an acoustic signal against the background of noise interference. The research was carried out by way of modeling the additive mixture of signal and interference using the MATLAB® software package. Interference is a model of a noise acoustic signal, which accompanies the operation of properly functional equipment. Signal is a model of an acoustic signal which is created with the occurrence of a malfunction. Signal and interference are independent random variables, so the property of additivity of cumulants was used – the variance of a mixture equals the sum of variances of signal and interference. The decision about the presence of a signal was made on the basis of testing two statistical hypotheses. The null hypothesis – the signal is absent, variance equals to the variance of the interference. The first hypothesis – the signal is present, variance equals to the variance of the mixture. Additional parameters: probability of a Type I error 0,01, probability of correct determination 0,99. The relative error of estimation determined the minimal sample size. These values allowed for the calculation of the threshold value, upon the exceeding of which by the variance estimation, the decision on the presence of signal is made. For each sample, assessments of variance were made. Experimental probability of correct determination is calculated as a total number of decisions taken regarding the presence of a signal, divided by the number of realizations, and corresponds to the value of the specified probability of correct determination. Its relative error was calculated in order to control the validity of the results. Also, kernel density estimation of the probability of the variance assessment for the case of a signal with normal distribution. As shown by the graphs, the assessments have a distribution that is close to normal. The conducted study proves that a variance -based cumulant method allows to detect a signal against the background of noise interference. The necessary sample size, which shows the number of the necessary momentary values, is given in the paper. That is to say that with the help of the frequency of an analogue digital converter the needed duration of the recording of a real for assessment of its variance can be obtained, and the decision on the presence or absence of a signal is to be made on the basis of the specified threshold values. The results of the study can be added to the known sample sizes and threshold values for the coefficients of asymmetry and excess with different distributions. Application of the described method requires additional testing on real acoustic signals and has the areas of use in systems of noise diagnostics., Проведено аналіз чутливості застосування кумулянта другого порядку адитивної суміші шумового сигналу і шумової завади до виявлення сигналу. Досліджувались нормальний, рівномірний та показниковий розподіли сигналу з різними середніми квадратичними відхиленнями, для завади – стандартний нормальний розподіл. Для ймовірності правильного виявлення сигналу 0,99 при ймовірності помилки першого роду 0,01 розраховано порогові значення та мінімальні об’єми вибірки, які забезпечують задані ймовірності, виходячи з гауссівського розподілу оцінки кумулянта другого порядку. Результати моделювання підтвердили розрахунки, експериментальна ймовірність правильного виявлення отримана не менше заданої.

Проведено аналіз чутливості застосування кумулянта другого порядку адитивної суміші шумового сигналу і шумової завади до виявлення сигналу. Досліджувались нормальний, рівномірний та показниковий розподіли сигналу з різними середніми квадратичними відхиленнями, для завади – стандартний нормальний розподіл. Для ймовірності правильного виявлення сигналу 0,99 при ймовірності помилки першого роду 0,01 розраховано порогові значення та мінімальні об’єми вибірки, які забезпечують задані ймовірності, виходячи з гауссівського розподілу оцінки кумулянта другого порядку. Результати моделювання підтвердили розрахунки, експериментальна ймовірність правильного виявлення отримана не менше заданої. In order to determine the technical condition of energetic objects with the objective of ensuring their operational reliability, durability and safety, systems of noise diagnostics, which are based on the analysis of acoustic diagnostic signals. A promising area of noise diagnostics are cumulant methods, based on cumulant analysis, which involves the use of cumulants and cumulant coefficients. In known literature no characteristics of detection of a signal within an interferencecontaining additive mixture with the use of a second-order cumulant (variance) can be found. That is why the objective of the paper is to study the use of cumulant method on the basis of point estimations of variance for a sample of momentary values for detection of an acoustic signal against the background of noise interference. The research was carried out by way of modeling the additive mixture of signal and interference using the MATLAB® software package. Interference is a model of a noise acoustic signal, which accompanies the operation of properly functional equipment. Signal is a model of an acoustic signal which is created with the occurrence of a malfunction. Signal and interference are independent random variables, so the property of additivity of cumulants was used – the variance of a mixture equals the sum of variances of signal and interference. The decision about the presence of a signal was made on the basis of testing two statistical hypotheses. The null hypothesis – the signal is absent, variance equals to the variance of the interference. The first hypothesis – the signal is present, variance equals to the variance of the mixture. Additional parameters: probability of a Type I error 0,01, probability of correct determination 0,99. The relative error of estimation determined the minimal sample size. These values allowed for the calculation of the threshold value, upon the exceeding of which by the variance estimation, the decision on the presence of signal is made. For each sample, assessments of variance were made. Experimental probability of correct determination is calculated as a total number of decisions taken regarding the presence of a signal, divided by the number of realizations, and corresponds to the value of the specified probability of correct determination. Its relative error was calculated in order to control the validity of the results. Also, kernel density estimation of the probability of the variance assessment for the case of a signal with normal distribution. As shown by the graphs, the assessments have a distribution that is close to normal. The conducted study proves that a variance -based cumulant method allows to detect a signal against the background of noise interference. The necessary sample size, which shows the number of the necessary momentary values, is given in the paper. That is to say that with the help of the frequency of an analogue digital converter the needed duration of the recording of a real for assessment of its variance can be obtained, and the decision on the presence or absence of a signal is to be made on the basis of the specified threshold values. The results of the study can be added to the known sample sizes and threshold values for the coefficients of asymmetry and excess with different distributions. Application of the described method requires additional testing on real acoustic signals and has the areas of use in systems of noise diagnostics.

Метою дослідження є класифікація підстановок в ключах роторних шифрувальних машин в залежності від їх криптографічних характеристик, експериментальне отримання статистичних оцінок потужностей класів для підстановок різного розміру, порівняння точності оцінок при використанні різних апроксимацій для ймовірнісних розподілів в методі Монте-Карло. Об’єктом дослідження є ключі зашифрування у роторних машинах. Предметом дослідження є криптографічні характеристики підстановок над алфавітами. В ході роботи розроблено алгоритми для побудови класів підстановок за характеристиками методом повного перебору перестановок та методом статистичного моделювання Монте-Карло. Виділено класи підстановок довжин 11, 26, 30, 31, 32, 33, 45 та 55, побудовано довірчі інтервали для потужностей отриманих класів з використанням різних методів. Проведено аналіз результатів, отриманих в результаті апроксимацій для ймовірнісних розподілів в методі Монте-Карло. The aim of the research is to classify permutations in the keys of rotary cryptographic machines depending on their cryptographic characteristics, to experimentally obtain statistical estimates of the power classes for permutations of different lengths, to compare the accuracy of the estimates using different approximations for the probability distributions in the Monte Carlo method. The object is cipher keys in rotor engines. The subject is cryptographic properties of alphabets permutations. During the research, algorithms were developed for constructing classes of permutations according to characteristics by the method of complete enumeration of permutations and the method of statistical simulation of Monte Carlo. The classes of permutations of lengths 11, 26, 30, 31, 32, 33, 45, 55 are allocated, the confidence intervals for the powers of the obtained classes are constructed using various methods. The analysis of the results obtained as a result of approximations for the probability distributions in the Monte Carlo method has been carried out.