Impact of AI-Driven Maintenance Models on Operational Efficiency in Aircraft Engineering

Abstract

The effect of Artificial Intelligence (AI)-based maintenance models on the operational efficiency of aircraft engineering, as far as predictive reliability analysis and demand forecasting are concerned, is a subject investigated in this research. Conventional maintenance strategies in the aviation sector tend to focus on fixed schedules or reactive behavior, leading to inefficiencies, surprise failures, and high costs. With the help of AI applications like Weibull distribution analysis and SARIMAX time series forecasting, the present study employs data-driven methodologies to investigate propeller blade failure behavior and predict the monthly demand for aircraft landing gearboxes. The Weibull analysis documented a nearly random failure behavior with slight wear-out tendencies, which facilitated the identification of maintenance thresholds and the implementation of early intervention strategies. At the same time, the SARIMAX model replicated seasonal patterns in demand, generating precise six-month forecasts that facilitate effective inventory and resource planning. The deployment of these AI-based approaches enables the transition to predictive and condition-based maintenance, eliminating unnecessary downtime, maximizing fleet availability, and increasing overall operational efficiency in aircraft maintenance engineering.