An Algorithm for Predicting the Technical Condition of Functional Units of a Radar System Based on the Integration of Uneven Time Series

This work is aimed at investigating ways to analyze uneven time series of diagnostic information for predicting technical condition parameters. The urgency of this task is due to the need to ensure high accuracy in predicting diagnostic data in order to control the output of the functional characteristics of the space monitoring radar system (SMRS) beyond a given range and, in case of deviation, to make a decision by the engineer on duty to carry out preventive maintenance measures for the functional units of the SMRS. Generalized estimates of the reliability of forecast data are formed by data fusion of uneven time series of functions of absolute forecast errors and correlation functions of forecast and actual values of each diagnostic parameter. The developed algorithm for data fusion of estimates of the reliability of forecast values based on the Dezert-Smarandache and PCR5 rules is used to achieve high-precision prediction of failures of electronic equipment in real time.