AI-Driven Fault Detection and Maintenance Optimization for Aviation Technical Support Systems

This study investigates the integration of customization and personalization approaches in aviation maintenance through Aviation Technical Support as a Service (ATSaaS) platform. Through a comprehensive survey of 86 small and medium-sized airlines, combined with mathematical modeling of fault detection systems, the study develops and validates a hybrid framework that integrates traditional maintenance approaches with AI-driven solutions. The comparative analysis demonstrates that the hybrid model significantly outperforms both pure customization and pure personalization approaches, achieving a 95% fault detection rate compared to 75% for customization-only and 88% for personalization-only models. The hybrid approach also showed superior performance in predictive maintenance effectiveness (96%), operational downtime reduction (92%), and cost optimization (90%). The research presents three architectural frameworks for ATSaaS implementation—customization-based, personalization-based, and hybrid—providing a structured approach for different airline categories. Large airlines, with their extensive technical expertise and complex operational requirements, benefit from enhancing their customized maintenance programs with personalization tools, improving overall maintenance efficiency by 23%. Simultaneously, smaller operators, often constrained by limited resources, can use ATSaaS platforms to access sophisticated maintenance capabilities without extensive in-house expertise, reducing operational costs by 35% compared to traditional approaches. The study concludes that the successful integration of customization and personalization through ATSaaS platforms represents a promising direction for optimizing aviation maintenance operations, supporting the industry’s movement toward data-driven, adaptive maintenance solutions.