A Review of Rolling Bearing Fault Diagnosis Methods based on Empirical Mode Decomposition

Yang Yu; Tao Zhang; Lianhai Wang; Shaoda Wang

doi:10.54691/yfgbq471

Authors

Yang Yu
Tao Zhang
Lianhai Wang
Shaoda Wang

DOI:

https://doi.org/10.54691/yfgbq471

Keywords:

Empirical Mode Decomposition, Rolling Bearing, Fault Diagnosis.

Abstract

Empirical Mode Decomposition (EMD) has unique advantages in processing nonlinear and non-stationary signals due to its adaptability, and has been widely applied in the research on fault diagnosis of rolling bearings.This paper systematically combs the relevant literatures in this field in the past five years. From the perspective of the evolution of methods, the research has experienced a gradual deepening process from a single decomposition method to the fusion of multiple technologies and from traditional machine learning to deep learning integration.The existing research mainly focuses on three directions: improvement of decomposition algorithms, enhancement of noise suppression, and construction of intelligent recognition models, and has achieved remarkable progress in diagnostic accuracy and robustness.Analysis shows that the current research still has problems such as the disconnection between laboratory data and industrial practice, insufficient adaptability to complex working conditions, and lack of model interpretability.Future research needs to further focus on the design of lightweight algorithms, the improvement of cross-domain adaptability, and the fusion path of physical knowledge and data-driven methods.

Downloads

Download data is not yet available.

References

[1] Li N. Application of EMD Based on Signal Sequence Difference in Bearing Fault Diagnosis[J]. Mechanical Management Development, 2024, 39(12): 72-74. (In Chinese)

[2] Lv Z, Luo J, Yang X, Su J, Li X, Zhan R. Application of HHT Time-Frequency Analysis Based on Wavelet Packet and EMD in Aircraft Test Rig Bearing Fault Diagnosis[J]. Measurement & Control Technology, 2022, 41(10): 17-25. (In Chinese)

[3] Bao H, Wei Y, Zhang Z, et al. Application of EMD-CSF in Early Weak Fault Diagnosis of Rolling Bearings[J]. Noise & Vibration Control, 2022, 42(6): 105-110. (In Chinese)

[4] Chen L, Zhang C. Rolling Bearing Fault Diagnosis Based on EMD Envelope Spectrum Features and PCA-PNN[J]. Coal Mine Machinery, 2022, 43(10): 173-176. (In Chinese)

[5] Yu Y, Li J, Wu Y, et al. A Fault Diagnosis Method Based on EMD and PCA[J]. 2024 4th International Conference on Neural Networks, Information and Communication (NNICE), 2024: 1366-1373.

[6] Morgan J, Hall S, Young D, et al. Rolling Bearing Fault Diagnosis Method Based on SSA-IWT-EMD[J]. Journal of Applied Artificial Intelligence, 2024, 1(1): 437-450.

[7] Lei C, Jiao M, Fan G, et al. Fault Diagnosis Method of Rolling Bearings Based on SSA-IWT-EMD[J]. Journal of Beijing University of Aeronautics and Astronautics, 2025, 51(4): 1152-1162.

[8] Gao Y, Zhang J. Bearing Fault Diagnosis Based on EMD and FastICA[J]. Mechanical Design & Manufacture, 2024(6): 48-52. (In Chinese)

[9] Ma W, Hong K, An N, et al. Rolling Bearing Fault Diagnosis Method Based on ICEEMD-FastICA[J]. Journal of Mechanical Strength / Jixie Qiangdu, 2024, 46(2).

[10] Wu B, Yang L, Zhang J, et al. Multi-Domain Feature Bearing Fault Diagnosis Based on EMD-SVD and KNN[C]// 15th National Conference on Rotor Dynamics. 2023.

[11] Zhang Y, Yang B. Bearing Fault Diagnosis Based on EMD and SSA-SVM[J]. Combined Machine Tool & Automated Processing Technology, 2023(8): 113-117. (In Chinese)

[12] Li T, Yang W, Li Y, et al. Simulation of EMD Diagnosis Method for Main Ventilation Fan Rolling Bearing Fault in Coal Mine[J]. Computer Simulation, 2025, 42(5): 520-524. (In Chinese)

[13] Jing Z, Zhang C. Rolling Bearing Fault Diagnosis Method Based on EMD and Classifier Ensemble[J]. Gongkuang Automation, 2023(S2): 152-155. (In Chinese)

[14] Zhao G, Zeng J. Rolling Bearing Fault Diagnosis Based on EMD-GAF and Improved SERE-DenseNet[J]. Electronic Measurement Technology, 2023(020): 046. (In Chinese)

[15] Zhao F, Zhen D, Yu X, et al. Bearing Fault Diagnosis Method Based on EMD and Multi-channel Convolutional Neural Network[C]// International Conference on the Efficiency and Performance Engineering Network. Springer, Cham, 2023.

[16] Shang S, Guo Z, Cao Z, et al. A Fault Diagnosis Technique Based on EMD and CNN-LSTM[J]. Proceedings of SPIE, 2023, 12803(000): 7.

[17] Chennana A, Ahmia A, Megherbi AC, et al. A Bearing Faults Diagnosis Enhancement Using EMD and MEDA[J]. 2024 2nd International Conference on Electrical Engineering and Automatic Control (ICEEAC), 2024: 1-6.

[18] Chang B, Cui R. Bearing Fault Diagnosis Based on TVF-EMD Decomposition and Random Forest Prediction[J]. Proceedings of SPIE, 2023, 12793(000): 7.

[19] Shi Q, Yang F. Composite Fault Diagnosis of Rolling Bearings Based on EMD-AADPCI Vibration Images[J]. Frontiers in Mechanical Engineering, 2025, 11(11): 1688598.