Two-stage optimization-driven RUL prediction for rolling bearings

Abstract

Reliable remaining useful life (RUL) prediction of rolling bearings serves as the core support for the prognostics and health management (PHM) of industrial rotating equipment. Although data-driven methods have achieved remarkable breakthroughs in prediction accuracy, the existing approaches still encounter three critical limitations: the insufficient informational dimensions of individual features, the poor adaptability between degraded features and prediction tasks in mainstream feature fusion models, and the channel-wise and temporal redundancy in multi-dimensional features that masks the inherent degradation trends of bearings. To tackle these challenges, this paper presents a novel rolling bearing RUL prediction method based on multivariate time series mixers with cross-channel convolutional fusion (CCF) (MTS-mixers-CCF). The proposed method initially constructs an initial feature set from bearing vibration signals. Subsequently, it establishes a feature-task adaptability evaluation framework using an adaptive differential evolution based on comprehensive evaluation metrics (CEM) algorithm to reconstruct a high-adaptability feature ensemble. Finally, it attains accurate RUL estimation through the MTS-mixers-CCF model, which reduces feature redundancy by means of factorization mechanisms and enhances inter-feature correlation via CCF layers. Experiments conducted on the widely adopted PHM2012 and XJTU-SY bearing datasets demonstrate that the MTS-mixers-CCF model outperforms traditional time series prediction methods and state of the art deep learning models, exhibiting significantly higher accuracy and stability for RUL prediction under ambiguous degradation trends. This research offers a robust and high-performance solution for rolling bearing RUL estimation, with promising application prospects in industrial PHM scenarios.