Asymmetric Loss Functions for Deep Learning Early Predictions of Remaining Useful Life in Aerospace Gas Turbine Engines

Abstract

Asymmetric loss functions have been successfully applied to deep learning for image analysis and imbalanced classification. In this paper, we extend the use of particular types of weighted loss functions, namely asymmetric loss functions, to investigate how predictions of engine remaining useful life (RUL) in aerospace are affected. Within prognostics and health management, the main metric used to evaluate deep learning RUL predictions is the scoring function. Our hypothesis is that by using asymmetric loss functions we will improve results for this metric. In order to investigate our hypothesis, we test 4 different asymmetric loss functions, i.e, Mean Square Logarithmic Error-Mean Square Error, Linear-Mean Square Error, Linear-Linear, and Quadratic-Quadratic and evaluate whether and how much they affect different deep learning architectures performance. Results show that the use of asymmetric loss functions improve RUL predictions for the case study investigated.