Remaining Useful Life (RUL) estimation is directly related with the application of predictive maintenance. When RUL estimation is performed via data-driven methods and Artificial Intelligence algorithms, explainability and interpretability of the model are necessary for trusted predictions. This is especially important when predictive maintenance is applied to gas turbines or aeroengines, as they have high operational and maintenance costs, while their safety standards are strict and highly regulated. The objective of this work is to study the explainability of a Deep Neural Network (DNN) RUL prediction model. An open-source database is used, which is composed by computed measurements through a thermodynamic model for a given turbofan engine, considering non-linear degradation and data points for every second of a full flight cycle. First, the necessary data pre-processing is performed, and a DNN is used for the regression model. The selection of its hyper-parameters is done using random search and Bayesian optimisation. Tests considering the feature selection and the requirements of additional virtual sensors are discussed. The generalisability of the model is performed, showing that the type of faults as well as the dominant degradation has an important effect on the overall accuracy of the model. The explainability and interpretability aspects are studied, following the Local Interpretable Model-agnostic Explanations (LIME) method. The outcomes are showing that for simple data sets, the model can better understand physics, and LIME can give a good explanation. However, as the complexity of the data increases, both the accuracy of the model drops but also LIME seems to have difficulties in giving satisfactory explanations.
Turbine blade cooling has been a topic of significant interest, as increasing turbine entry temperatures result in higher cooling requirements. The present numerical method divides the blade into a finite number of elements in the span and peripheral directions and solves the heat transfer fundamental equations for convection and conduction in both directions. As inputs, the span and chord gas temperature and heat transfer coefficient distributions are required. The results include high resolution temperature prediction for the blade and coolant, at all span and chord positions. The advantages of the method include the capturing of blade temperature variation in all directions, while considering the thermal diffusion due to conduction. Mach number effects to the resulted blade and coolant temperature are highlighted, as local distribution of the gas static temperature can have a dominant role. The effect of averaging the input parameters to the predicted blade temperature is discussed and finally, different values for the material conductivity are simulated and the results are analysed.
MULTIFILE
Data-driven condition-based maintenance (CBM) and predictive maintenance (PdM) strategies have emerged over recent years and aim at minimizing the aviation maintenance costs and environmental impact by the diagnosis and prognosis of aircraft systems. As the use of data and relevant algorithms is essential to AI-based gas turbine diagnostics, there are different technical, operational, and regulatory challenges that need to be tackled in order for the aeronautical industry to be able to exploit their full potential. In this work, the machine learning (ML) method of the generalised additive model (GAM) is used in order to predict the evolution of an aero engine’s exhaust gas temperature (EGT). Three different continuous synthetic data sets developed by NASA are employed, known as New Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS), with increasing complexity in engine deterioration. The results show that the GAM can be predict the evolution of the EGT with high accuracy when using several input features that resemble the types of physical sensors installed in aero gas turbines currently in operation. As the GAM offers good interpretability, this case study is used to discuss the different data attributes a data set needs to have in order to build trust and move towards certifiable models in the future.