Predictive maintenance analysis with SCADA in aircraft maintenance processes

In this study, the integration of SCADA systems with predictive maintenance methods in aircraft maintenance processes has been examined in detail. Changing conditions in the aviation sector and the requirements of flight safety necessitate more efficient management of maintenance activities, and predictive maintenance methods, which offer the opportunity for detection and intervention before a failure occurs, come to the forefront instead of traditional maintenance approaches. Within the scope of the thesis, structural approaches to aircraft maintenance processes are first explained; then, the structure of SCADA systems and their application areas in aviation are examined. A model is proposed in which real-time data collected from aircraft systems is analyzed using SCADA systems along with artificial intelligence and machine learning algorithms. It has been demonstrated that with this model, maintenance decisions can be automated, human error can be reduced, and maintenance costs can be optimized. The study also details various predictive maintenance techniques and explains how these methods can be integrated with SCADA systems. The contribution of artificial intelligence-based decision support systems to airworthiness processes is modeled within a theoretical framework, and recommendations aligned with maintenance regulations set by international authorities have been developed. This thesis aims to provide an academic contribution to maintenance management by holistically addressing predictive approaches in aviation maintenance processes