Potential of Generative Artificial Intelligence in Knowledge-Based Predictive Maintenance for Aircraft Engines

Predictive maintenance based on remaining useful life (RUL) estimation is widely recognized as a promising strategy for monitoring the health of critical systems such as aircraft engines, anticipating failures, and optimizing maintenance planning. A variety of approaches have been proposed in the literature, including data-driven, physics-based, and knowledgebased methods. Among them, deep learning-based methods have shown strong performance and gained the most traction, but industrial adoption remains limited due to challenges in interpretability, scalability and adaptability. Recent advances in generative artificial intelligence (GAI) offer new opportunities to address challenges related to data scarcity and variability but issues of model transparency persist. In this context, our paper highlights how these recent advances could open new opportunities, especially when integrated within hybrid frameworks combining data-driven and knowledge based reasoning. By clarifying industrial requirements and open challenges, this work provides a comprehensive synthesis of current needs and outlines a framework establishing a methodological foundation for producing interpretable RUL estimates along with the rules guiding the reasoning process.