Predictive maintenance for aircraft using time series analysis:Trend patterns and future forecasts

This thesis aims to develop a predictive maintenance model for the early detection of failures in aircraft engines, flaps, and auxiliary power unit (APU) systems, which are critical for flight safety. The study utilizes flight data obtained from Boeing 737 MAX8 aircraft, which were preprocessed and modeled using time series analysis methods, with the prediction results evaluated through MAE and RMSE error metrics. In addition, the results were visualized through an interactive Power BI-based report, making them usable as a decision support mechanism. The study goes beyond traditional approaches in aviation that primarily focus on engine data by presenting a holistic model that also encompasses flap and APU systems, thereby demonstrating the potential to enhance flight safety, reduce maintenance costs, and minimize Aircraft on Ground (AOG) durations. The findings reveal that predictive maintenance can provide significant contributions to operational efficiency and safety in the aviation industry.