Adaptive Extracting Wavelet Transform-Based Damage Indicator-Integrated Improved GPR Model for Bearing RUL Prediction
- 23 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (16) , 30984-30997
Abstract
The bearing is one of the most essential parts of rotating machinery and equipment, and it is of great engineering significance in the accurate prediction of the remaining useful life (RUL) of the bearing. Aiming at this problem, a novel hybrid prediction strategy based on time-frequency representation (TFR) is proposed in this paper. Firstly, adaptive extracting wavelet transform (AEWT) is proposed to obtain accurate TFR by creatively exploiting the window width by adjusting center frequency and scale factor based on an attention mechanism, and taking the advantage of synchroextracting operator in IF estimation operator. Then this paper introduces a novel damage indicator (DI) based on time-frequency fractional dispersion entropy (TFDE) to directly extract fault information from TFR to avoid information loss. Finally, the obtained DIs are used as inputs for a prediction model, where the adaptive particle swarm optimization algorithm (APSO) is employed to optimize Gaussian process regression (GPR). This method effectively tracks the bearing’s degradation state and accurately predicts its remaining useful life. The experimental verification was carried out with data sets of bearings running to failure. The results show that the proposed time-frequency damage indicator (TFDI) has better monotonicity, and the hybrid prediction model is more accurate to predict bearing RUL.Keywords
Funding Information
- National Natural Science Foundation of China (52305125, 51875416)
- Natural Science Foundation of Hubei Province (2023AFB028, 2023AFD001)
- Open Projects Program of State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS-2023-15)
- 14th Five Year Plan Hubei Provincial Advantaged Characteristic Disciplines (Groups) Project of Wuhan University of Science and Technology (2023B0301)
This publication has 54 references indexed in Scilit:
- Method for predicting remaining useful life of rolling bearings based on dynamic complexity characteristic entropy and quantum neural networksEngineering Failure Analysis, 2025
- Prediction of bearing remaining useful life based on a two-stage updated digital twinAdvanced Engineering Informatics, 2025
- A unified out-of-distribution detection framework for trustworthy prognostics and health management in renewable energy systemsEngineering Applications of Artificial Intelligence, 2023
- Multiscale three-dimensional Holo–Hilbert spectral entropy: a novel complexity-based early fault feature representation method for rotating machineryNonlinear Dynamics, 2023
- Composite multi-scale phase reverse permutation entropy and its application to fault diagnosis of rolling bearingNonlinear Dynamics, 2022
- Wavelet-based Synchroextracting Transform: An effective TFA tool for machinery fault diagnosisControl Engineering Practice, 2021
- Adaptive synchrosqueezing transform with a time-varying parameter for non-stationary signal separationApplied and Computational Harmonic Analysis, 2020
- Research on prediction model of geotechnical parameters based on BP neural networkNeural Computing and Applications, 2018
- Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVRApplied Acoustics, 2017
- Remaining useful life estimation for mechanical systems based on similarity of phase space trajectoryExpert Systems with Applications, 2015