Remaining useful life prediction of bearings based on adaptive degradation point detection and a hybrid deep learning framework

This study addresses the challenges in bearing remaining useful life (RUL) prediction, including small sample size and incomplete labels. A novel RUL prediction method is proposed. The method is based on adaptive degradation point detection and a hybrid deep learning framework. First, to determine the initial degradation time, the original vibration signals are combined with a physical bearing model. The Aquila Optimizer optimization algorithm is used to quantify the real-time crack values. An improved adaptive dynamic 3 σ criterion is applied together with the real-time crack values to identify the first prediction time. Second, to reduce the need for manually defined labels in RUL prediction, a feature model combining Gaussian mixture model and fuzzy entropy is developed. This model constructs an unsupervised health indicators (HI). Finally, a convolutional neural network-Bidirectional GRU-Attention model is proposed to predict the HI. The model integrates time-series modeling with an attention mechanism. The bearing HI is predicted sequentially. When the predicted HI exceeds the life threshold, the RUL is calculated. Experimental results on multiple datasets and comparisons with other methods show that the proposed method achieves the highest prediction accuracy, exceeding 93.59%. The results demonstrate that the method is reliable and practical for bearing RUL prediction.