STOCHASTIC AND INTELLIGENT MODELS IN DIAGNOSTIC AND CONTROL SYSTEMS OF ARTILLERY COMPLEXES

This paper explores the application of stochastic and intelligent modeling approaches for enhancing the diagnostic and adaptive control efficiency of modern artillery systems. Particular attention is devoted to stochastic models based on Markov chains, which enable the probabilistic representation of state transitions, system degradation, and uncertainties affecting artillery performance. In parallel, the study introduces a generalized fuzzy model capable of addressing critical challenges such as barrel wear diagnostics, sight correction under uncertain conditions, optimization of higher-level battery control with integrating environmental factors within the firing zone with per-gun operating parameters, and automatic aiming drive regulation through the integration of fuzzy reasoning with advanced control methodologies. The combined use of these approaches is shown to yield a synergistic effect, where the predictive rigor of Markov models complements the adaptive decision-making power of fuzzy logic. This integration offers a robust framework for increasing accuracy, reliability, survivability, and operational efficiency in dynamically changing combat environments. The results highlight the importance of hybrid modeling architectures in advancing next-generation artillery systems and outline future research directions aimed at real-time implementation, large-scale system integration, and experimental validation.