The remaining useful life prediction is a key element in decision-making and maintenance strategies development. Therefore, in practical situation, it is usually affected by uncertainty. The aim of this work is hence to propose a deep learning method which predicts when an in-service machine will fail to overcome the latter problem. It is based on deep convolutional variational autoencoder (CVAE). The proposed approach is validated using the C-MAPSS dataset of the aero-engine. The model's classification performance has reached a superior accuracy compared to existing models and it is used for machine failure prediction in different time windows.
Predicting the remaining useful life (RUL) is a critical step before the decision-making process and developing maintenance strategies. As a result, it is frequently impacted by uncertainty in a practical context and may cause issues. This paper proposes a new hybrid deep architecture that predicts when an in-service machine will fail to overcome the latter problem, allowing for an improved data analysis and dimensionality reduction capability providing better spatial distributions of features and increasing interpretability. A deep Convolutional Variational AutoEncoder with an Attention mechanism (ACVAE) has been developed and tested using the aero-engine C-MAPSS dataset. We defined two adapted threshold settings (α1, α2) by analysing the spatial distribution and minimizing the overlapping area between the degradation classes. To reduce the conflict zone, we used the soft voting classifier. The performance of our visual explainable deep learning model has reached a higher level of accuracy compared with previous existing models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.