Remaining useful life estimation of rolling element bearings based on an interpretable feature extraction method
Source abstract
Abstract
Dealing with the remaining useful life (RUL) estimation issue of rolling element bearings (REBs), feature extraction is a fundamental step and is of great importance in the estimation of the RUL of REBs. However, few studies have considered the interpretability of the feature extraction. A new interpretable feature extraction method and an exponential model-based RUL estimation method are proposed in this study. The feature selection strategy and partial least squares (PLS) method were used to ensure the interpretability of the extracted features. First, the extracted time-domain features were screened by calculating the monotonicity, robustness, and predictability of the time-domain feature vectors. Meanwhile, time-domain feature vectors with calculation results within [0,1] are preserved, weighted, and reused to achieve good predictive performance. Subsequently, the PLS method was used for feature extraction, and a new feature vector describing the bearing degradation process was constructed. Finally, an exponential model was proposed for RUL estimation. A strong tracking filter is employed to fuse the residuals of the model parameters and improve the accuracy of the estimation. Under the three experimental working conditions, the root mean square error (RMSE) values of this study’s method were reduced by 15.87%–82.40%, and the scoring function values were reduced by 1.13%–34.70% compared with other methods. The obtained RMSE and scoring function values prove the rationality and superiority of the proposed method and indicate that the method is effective in reducing the safety risks associated with bearing failures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Fatigue and fracture mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Electrical Engineering, Changchun University of Technology 1 , Changchun 130012,
Beijing Aerospace Manufacturing Technology Development Co., Ltd. 2 , Beijing 100043,
Department of Automation, Tsinghua University 3 , Beijing 100084,
Advanced Center for Electrical and Electronic Engineering, Universidad Técnica Federico Santa María 4 , Valparaíso,
Funding
National Natural Science Foundation of China · Natural Science Foundation of Jilin Province · Talent Project of Jilin Province
References (40)
Show source-provided references
1. A comprehensive review of deep learning-based fault diagnosis approaches for rolling bearings: Advancements and challenges10.1063/5.0255451 ↗
2. Study on the influence of the parameters of the roller swaging process on the no-load starting torque of self-lubricating spherical plain bearings10.1063/5.0246020 ↗
3. Comparative study on heteropolar/homopolar magnetic bearings for high-speed rotating applications10.1063/9.0000712 ↗
4. Research on rolling bearing fault diagnosis technology based on singular value decomposition10.1063/5.0225222 ↗
5. SRCAE-STCBiGRU: A fused deep learning model for remaining useful life prediction of rolling bearings10.1007/s11760-024-03534-1 ↗
6. A novel spatio-temporal characteristic extraction network for bearing remaining useful life prediction10.1088/1361-6501/ad6f37 ↗
7. An entire life-cycle rolling bearing remaining useful life prediction method using new degradation feature evaluation indicators10.1177/09544089241228943 ↗
8. A two-stage data-driven approach to remaining useful life prediction via long short-term memory networks10.1016/j.ress.2023.109332 ↗
9. An adaptive method for predicting bearing remaining useful life across various degradation stages10.1088/1361-6501/ad903e ↗
10. Robust dual-model collaborative broad learning system for classification under label noise environments10.1109/jiot.2025.3545741 ↗
11. Remaining useful life prediction of rolling bearings based on CBAM-CNN-LSTM10.3390/s25020554 ↗
12. A novel competitive temporal convolutional network for remaining useful life prediction of rolling bearings10.1109/tim.2023.3293877 ↗
13. Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks10.1016/j.knosys.2021.107866 ↗
14. Cross-domain adaptation fault diagnosis with maximum classifier discrepancy and deep feature alignment under variable working conditions10.1109/tr.2025.3551155 ↗
15. Remaining useful life prediction of rolling element bearings using degradation feature based on amplitude decrease at specific frequencies10.1177/1475921717736226 ↗
16. Remaining useful life prediction method for rolling bearings based on hybrid dilated convolution transfer10.1002/qre.3563 ↗
17. Remaining useful life prediction method of rolling bearings based on improved 3σ and DBO-HKELM10.1088/1361-6501/ad52b5 ↗
18. Remaining life prediction of rolling bearings with secondary feature selection and BSBiLSTM10.1088/1361-6501/ad3ea6 ↗
19. A remaining useful life prediction method of rolling bearings based on deep reinforcement learning10.1109/jiot.2024.3363610 ↗
20. Parallel convolutional transfer network for bearing fault diagnosis under varying operation states10.1109/tim.2024.3480212 ↗
21. A hybrid algorithm for predicting the remaining service life of hybrid bearings based on bidirectional feature extraction10.1016/j.measurement.2024.116152 ↗
22. Research on the remaining life prediction method of rolling bearings based on optimized TPA-LSTM10.3390/machines12040224 ↗
23. Rolling bearing residual useful life prediction model based on the particle swarm optimization-optimized fusion of convolutional neural network and bidirectional long–short-term memory–multihead self-attention10.3390/electronics13112120 ↗
24. Remaining useful life prediction of rolling bearings based on PCA and GSACO-SVR model10.1088/1742-6596/2405/1/012018 ↗
25. Dual-scale complementary spatial-spectral joint model for hyperspectral image classification10.1109/jstars.2025.3540001 ↗
26. Remaining useful life prediction for fractional degradation processes under varying modes10.1002/cjce.23666 ↗
27. Stochastic fractal search-optimized multi-support vector regression for remaining useful life prediction of bearings10.1007/s40430-021-03138-7 ↗
28. An optimized support vector regression for prediction of bearing degradation10.1016/j.asoc.2021.108008 ↗
29. A health index construction framework for prognostics based on feature fusion and constrained optimization10.1109/tim.2021.3104414 ↗
30. An improved BRB-based anomaly detection method of drive end bearings10.3233/jifs-224102 ↗
31. On function-on-function regression: Partial least squares approach10.1007/s10651-019-00436-1 ↗
32. Residual-life distributions from component degradation signals: A Bayesian approach10.1080/07408170590929018 ↗
33. Remaining useful life estimation for micro switches of railway vehicles10.1016/j.conengprac.2018.10.010 ↗
34. A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution10.1016/j.ejor.2012.10.030 ↗
35. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings10.1109/tr.2018.2882682 ↗
36. Data-driven prognostic scheme for rolling-element bearings using a new health index and variants of least-square support vector machines10.1016/j.ymssp.2021.107853 ↗
37. AE-MCDM: An autoencoder-based multi-criteria decision-making approach for unsupervised feature selection10.1007/s11227-025-07316-5 ↗
38. A dynamic prediction method for rolling bearings residual life via multi-stage exponential model10.1109/access.2024.3498895 ↗
39. Rolling bearing remaining useful life prediction method based on vibration signal and mechanism model10.1016/j.apacoust.2024.110334 ↗
40. Parameterized iterative time-frequency-multisqueezing transform for bearing fault diagnosis10.1109/TIM.2025.3561399 ↗