Fu, ShuaiAvdelidis, Nicolas P.Plastropoulos, Angelos2025-06-242025-06-242025-05-28Fu S, Avdelidis NP, Plastropoulos A. (2025) Novel hybrid prognostics of aircraft systems. Electronics, Volume 14, Issue 11, May 2025, Article number 21931450-5843https://doi.org/10.3390/electronics14112193https://dspace.lib.cranfield.ac.uk/handle/1826/24047This article belongs to the Special Issue Fault Detection Technology Based on Deep LearningAccurate forecasting of the remaining useful life (RUL) of aviation equipment is crucial for enhancing safety and reducing maintenance costs. This study presents a novel hybrid prognostic methodology that integrates physics-based and data-driven models to improve RUL estimations for critical aircraft components. The physics-based approach simulates long-term degradation patterns using fundamental principles such as mass conservation and Bernoulli’s equation, while the data-driven model employs a hyper tangent boosted neural network (HTBNN) to detect short-term anomalies and deviations in real-time sensor data. The integration of various models enhances accuracy, adaptability, and reliability in prognostics. The proposed methodology is assessed using NASA’s N-CMAPSS dataset for gas turbines and a fuel system test rig, demonstrating a 15% improvement in prediction accuracy and a 20% reduction in uncertainty compared to traditional methods. These findings highlight the potential for widespread application of this hybrid methodology in predictive maintenance and prognostic and health management (PHM) of aircraft systems.enAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/4007 Control Engineering, Mechatronics and Robotics40 Engineering7 Affordable and Clean Energy4009 Electronics, sensors and digital hardwareremaining useful lifehybrid prognosticspredictive maintenanceaircraft systemsdata-driven modelsphysics-based modelshyper tangent boosted neural network (HTBNN)Article2079-929267359321931411