Author(s):
1. Predrag Dašić, SaTCIP Publisher Ltd., 36610 Vrnjačka Banja i Visoka tehnička mašinska škola strukovnih studija (VTM, Serbia

Abstract:
Reliability of technical systems is a numerical value that represents the probability, at a specified confidence level, that the technical system will successfully perform the function for which it is intended, without failure, within the specified performance limits, taking into account the system’s prior operating time, over a specified mission duration. Reliability of technical systems is a very complex concept and represents one of the most important characteristics of systems in general or technical systems in particular and one of the key factors in their safety, availability, economic efficiency and overall efficiency throughout their life cycle. In order to determine the reliability parameters, a thorough understanding of the system is required. Reliability is strongly influenced by stochastic processes, so the selection of appropriate reliability indicators is based on the probability of the occurrence of an event, failure, etc. Based on the experimental data obtained by monitoring failures of components of technical systems in the phase of real exploitation, it is possible to establish a theoretical reliability model of components and subsystems of technical systems using traditional methods based on statistical models and artificial intelligence (AI) methods and models. Determining the reliability of the components of technical systems can be determined using conventional methods: on the basis of an a priori assumption that the experimental data follow a specific theoretical probability distribution & on the basis of the choice of the theoretical probability distribution that best approximates the experimental data (according to the characteristics of the theoretical distributions, on the basis of comparative analysis, etc.). The paper will present the structure and application possibilities of two software systems RATSC-CTD and RATSC-CA, developed by the author of this paper. The choice of the theoretical reliability model for the RATSC-CTD software system is mainly based on the recommendations presented in the BS standards (BS-5760-1:1996 and BS-5760-2:1994). The choice of the theoretical model of reliability in the software system RATSC-CA is based on the comparative analysis of different models of theoretical probability distributions and the choice of the distribution model that best approximates the experimental data. The RATSC-CA software system incorporates elements of artificial intelligence (AI) in it when choosing the best-fitting and most appropriate distribution model on the basis of which the reliability of the technical system can be predicted. The paper also discusses the application of artificial intelligence (AI) methods and models in the analysis, assessment and prediction of the reliability of complex technical systems. Special attention is paid to: artificial neural networks (ANN), machine learning (ML) and deep learning (DL) methods, fuyyz-logic systems (FL), hybrid intelligent models, etc. Their application enables the timely detection of failures as well as the possibility of identifying their causes, assessing the remaining useful life of components and predicting the probability of failure. The integration of artificial intelligence with data collected from sensors, the Industrial Internet of Things (IIoT) and real-time monitoring systems creates the basis for the development of predictive maintenance (PdM) and intelligent reliability management. It is concluded that artificial intelligence (AI) methods and models represent an significant direction in the development of modern reliability engineering and an important basis for decision-making based on big data (BD).

Key words:
Reliability,reliability analysis (RA),failure prediction,technical system,artificial intelligence (AI).

Thematic field:
SYMPOSIUM D - Environmental and sustainable materials

Date of abstract submission:
15.07.2026.

Conference:
Contemporary Materials 2026 - Savremeni Materijali