Search

• The RUL prognosis framework combines the wavelet transform and the ConvLSTM. • Channel self-attention highlights weak but crucial features in wavelet coefficients. • Global attention improves the representation of the learned features in multiple wavelet coefficients of different channels. • Hybrid attention-based method boosts convlstm's performance in RUL prognosis. Wavelet transform, a time-frequency analysis method for evaluating non-stationary signals, can assist in representing equipment degradation over prolonged usage. However, a single wavelet basis function is challenging to apply to all periodic transient waveforms. As a result, this research suggests a hybrid attention-based multi-wavelet coefficient fusion method for evaluating the remaining useful life (RUL) of bearings. Firstly, a two-dimensional map is created by organizing the decomposed individual frequency bands after the approach employs several wavelets to get the original signal properties. Secondly, a hybrid attention-based ConvLSTM (HA-ConvLSTM) network is designed to weight wavelet coefficient channels adaptively. The learned features are used to evaluate RULs by a multi-layer perceptron. Finally, tests were run on the PHM2012 rolling bearing dataset to validate the proposed method. Overall, the suggested scheme outperforms previous comparable methods in the performance index. This approach optionally resolves the wavelet basis function matching issue for periodic transient waveforms. [ABSTRACT FROM AUTHOR]