Residual life prediction of progressive failure bearings based on NGO-AVMD hybrid domain features

Accurate bearing Remaining Useful Life (RUL) prediction is vital for equipment availability, cost reduction, and safety. Existing data-driven methods often yield insufficient accuracy due to single-scale feature extraction and poor differentiation of failure modes. This paper proposes a hybrid-domain feature extraction method, integrating original vibration signals with Adaptive Variational Mode Decomposition optimized by Northern Goshawk Optimization (NGO-AVMD) reconstructed signals and additional deep features. These mixed-domain features are used to compute a health index that effectively distinguishes progressive and sudden bearing failure modes. Focusing on progressive degradation, a multi-attention Temporal Convolutional Network (TCN) is then employed for RUL prediction, using these features as input. Validated on the PHM2012 dataset, the method achieves an R2 of 98%, demonstrating its high accuracy in bearing life prediction.