Remaining Useful Life Estimation of Bearing Using Deep Multiscale Window-Based Transformer

Accurate and reliable remaining useful life (RUL) estimation for bearings relies on the extraction of desired degradation features from vibration signals. Now, various feature extractors based on convolutional neural networks (CNNs) have been proposed for RUL prediction and achieved great success. However, these approaches focus on extracting degradation features from data in a single time frame but fail to capture the degradation information across multiple time frames, leading to degenerate estimation performance. In this study, we propose a novel multiscale feature extractor called deep multiscale window-based transformer (DMW-Trans) to overcome these limitations. To be more specific, a bunch of feature maps (FMs) are first generated with time–frequency maps (TFMs) at multiple time frames. Then, sequential layers equipped with window-based transformer blocks (i.e., WT-Blocks) and patch-merge modules are designed, where the former is used to extract features with multihead self-attention windows, while the latter is employed to fuse features from neighboring areas on TFMs to enlarge the attention fields from layer to layer. Through this hierarchical feature extraction process, multiscale degradation-related features can be effectively extracted. Finally, multilayer perceptron (MLP) is applied to fuse the multiscale features to estimate RUL. Due to the excellent multiscale feature extraction capability, the proposed DMW-Trans can provide accurate and reliable RUL prediction results. Extensive experiments on two public run-to-failure bearing datasets demonstrate the superior performance of our proposed method compared to some state-of-the-art approaches.