AI-Based Exhaust Gas Temperature
Publication - November 2022
Data-driven condition-based maintenance (CBM) and predictive maintenance (PdM) strategies have emerged over recent years with the goal of minimizing aviation maintenance costs and environmental impact through the diagnosis and prognosis of aircraft systems. As the use of data and relevant algorithms is crucial to AI-based gas turbine diagnostics, the aeronautical industry faces various technical, operational, and regulatory challenges that must be addressed to fully exploit their potential.
Machine Learning Methodology
In this work, the machine learning (ML) method of the Generalised Additive Model (GAM) is used to predict the evolution of an aero engine’s exhaust gas temperature (EGT). The study employs 3 different continuous synthetic data sets developed by NASA, known as the New Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS), which present increasing complexity in engine deterioration.
Predicting EGT With High Accuracy
The results show that the GAM can predict the evolution of the EGT with high accuracy when using several input features that resemble the types of physical sensors currently installed in aero gas turbines. As the GAM offers good interpretability, this case study is used to discuss the different data attributes a dataset needs in order to build trust and move towards certifiable models in the future, addressing critical needs in safety-critical applications.
Authors
- Asteris Apostolidis
- Nicolas Bouriquet
- Konstantinos Stamoulis
Aviation Engineering research group
The aviation industry must become smarter and more sustainable. The Aviation Engineering research group is ensuring the sector has all the knowledge and insights it needs to transition to, and develop, more-efficient en more-environmentally friendly engineering and operational practices.