Remaining Useful Life Prediction Using a Novel Feature-Attention-Based End-to-End Approach

Deep learning plays an increasingly important role in industrial applications, such as the remaining useful life (RUL) prediction of machines. However, when dealing with multifeature data, most deep learning approaches do not have effective mechanisms to weigh the input features adaptively. In this article, a novel feature-attention-based end-to-end approach is proposed for RUL prediction. First, the proposed feature-attention mechanism is directly applied to the input data, which gives greater attention weights to more important features dynamically in the training process. This helps the model focus more on those critical inputs, and the prediction performance is therefore improved. Next, bidirectional gated recurrent units (BGRU) are used to extract long-term dependencies from the weighted input data, and convolutional neural networks are employed to capture local features from the output sequences of BGRU. Finally, fully connected networks are used to learn the above-mentioned abstract representations to predict the RUL. The proposed approach is validated in a case study of turbofan engines. The experimental results demonstrate that the proposed approach outperforms other latest existing approaches.

Automated summary

This article introduces a novel feature-attention-based end-to-end approach for RUL prediction, which effectively improves the model's predictive performance. By dynamically allocating attention weights in the input data and combining the use of BGRU and convolutional neural networks for extracting long-term dependencies and capturing local features, abstract representations for RUL prediction are learned.