A Decision-Theoretic and Economic Assessment of Artificial Intelligence Applications in Predictive Maintenance and Quality Management in the European Aerospace Industry

Abstract

The European aerospace industry is subject to stringent safety, regulatory, and quality requirements while simultaneously facing increasing pressure to improve efficiency, cost transparency, and sustainability. Artificial intelligence (AI) has become a critical enabler for advanced predictive maintenance (PdM) and data-driven quality management (QM), offering capabilities such as early fault detection, process optimization, and reduced operational downtime. Despite substantial technological progress, the economic value of AI-based PdM and QM systems remains insufficiently quantified, particularly within the highly regulated European aerospace context. This study proposes an integrative, decision-theoretic framework for the economic evaluation of AI applications in aerospace maintenance and production. The framework systematically links technical performance indicators-such as prediction accuracy, system availability, and defect rates-with economic metrics including return on investment, total cost of ownership, and overall equipment effectiveness. European regulatory and certification requirements are explicitly incorporated to ensure applicability under aerospace-specific compliance constraints. Methodologically, the research combines a structured literature review with probabilistic modeling and simulation-based analysis. Bayesian networks and Monte Carlo simulations are employed to capture uncertainty related to data quality, operational variability, and model performance. The framework is illustrated using representative aerospace manufacturing and maintenance scenarios reflecting European industry conditions. The results demonstrate how technical AI performance translates into measurable economic outcomes under regulatory constraints. The proposed approach provides a transparent and reproducible basis for evaluating AI investments, supporting evidence-based decision-making in aerospace organizations and contributing to economically sustainable digital transformation.