The reliability of aviation equipment is a critical factor that directly influences the efficiency of tasks associated with flight operations. To assess reliability, various indicators are commonly employed, including mean time between failures, mean time between repairs, steady-state availability, availability function, downtime ratio, and utilization factor. However, in modern aviation, the operation of radio equipment often neglects considerations of economic impact, socio-political factors, and a comprehensive analysis of the efficiency of all components within the civil aviation infrastructure. Reliability indicators are typically stochastic in nature, necessitating the development of statistical models, the application of advanced statistical data processing methods, and the enhancement of decision-making technologies, including those leveraging artificial intelligence. External influences, operational conditions, degradation of electrical components, and instability in both autonomous and external power supplies often result in nonstationary trends across the range of parameters being monitored. These dynamic changes highlight the need for advancements in traditional data processing methods, particularly in areas such as dataset formation, classification, evaluation, and forecasting. This article focuses on the development of statistical models for the downtime ratio and utilization factor, specifically addressing scenarios characterized by nonstationary trends in diagnostic parameters.
Zaliskyi et al. (Wed,) studied this question.