RUL Prediction Using a Fusion of Attention-Based Convolutional Variational AutoEncoder and Ensemble Learning Classifier

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 article 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 (
$\alpha 1, \alpha 2$
) by analyzing 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.