This study delves into the application of Large Language Models (LLMs) in the diagnostics and maintenance of aircraft propulsion systems. Rapid advancements in aviation technology make there is an increasing need for sophisticated tools to assist in predicting and preventing equipment failures. LLMs, trained on extensive datasets, offer the potential to analyze telemetry and operational data, providing diagnostic insights and maintenance recommendations. This research explores the capabilities of LLMs in interpreting sensor data, identifying anomalies, and generating maintenance guidelines. The performance and limitations of LLMs are evaluated utilizing synthetic data from NASA to simulate real-world scenarios. Findings indicate that LLMs can enhance the reliability and efficiency of aircraft propulsion system maintenance significantly, despite challenges related to data quality and model limitations.