Abstract
In the field of vibration monitoring for rotating machinery, high-precision bearing fault diagnosis faces challenges due to imbalanced measurement data and noise interference from complex environments. To address these issues, this paper proposes a bearing fault diagnosis method based on an ensemble undersampling extended belief rule base (EBRB-EU), aiming to improve the reliability and accuracy of equipment condition assessment. Specifically, to overcome the limitation of using Euclidean distance in EBRB, which fails to effectively capture the differences in the probability distribution of vibration signals, the paper introduces the Kullback-Leibler (KL) divergence to replace the Euclidean distance, providing a more accurate measure of the match between samples and rule antecedent attributes. An ensemble undersampling strategy is then employed to calibrate the training set, reducing the impact of majority class samples on model training. Subsequently, the data is divided into multiple subsets, and a set of parallel sub-EBRB models is constructed. The differential evolution algorithm is used to optimize the parameters of each sub-model, minimizing evaluation bias. Finally, an ensemble voting mechanism is applied to integrate the diagnostic results, enhancing the accuracy of fault state identification. Experimental results demonstrate that the KL divergence-based EBRB-EU model outperforms the Euclidean distance-based EBRB method on multiple datasets, effectively alleviates the data imbalance issue, and exhibits strong resistance to interference.
Data availability
Data will be made available on request.
References
Dai, X. & Gao, Z. From model, signal to knowledge: A data-driven perspective of fault detection and diagnosis[J]. IEEE Trans. Industr. Inf. 9 (4), 2226–2238. https://doi.org/10.1109/TII.2013.2243743 (2013).
Zhou, J., Ren, J. & He, C. Improved medical waste plasma gasification modelling based on implicit knowledge-guided interpretable machine learning[J]. Waste Manage. (New York NY). 188, 48–59. https://doi.org/10.1016/j.wasman.2024.07.035 (2024).
Li, T. et al. A hierarchical object oriented Bayesian network-based fault diagnosis method for building energy systems[J]. Appl. Energy. 306, 118088. https://doi.org/10.1016/j.apenergy.2021.118088 (2022).
Dou, D. et al. A rule-based intelligent method for fault diagnosis of rotating machinery[J]. Knowl. Based Syst. 36, 1–8. https://doi.org/10.1016/j.knosys.2012.05.013 (2012).
Ge, Z. et al. A knowledge-driven graph convolutional network for abnormal electrocardiogram diagnosis[J]. Knowl. Based Syst. 296, 111906doi. https://doi.org/10.1016/j.knosys.2024.111906 (2024).
Wang, Y., Shen, F. & Ye, L. A knowledge-refined hybrid graph model for quality prediction of industrial processes[J]. Eng. Appl. Artif. Intell. 139, 109711doi. https://doi.org/10.1016/j.engappai.2024.109711 (2025).
Guo, L. et al. A knowledge-driven spatial-temporal graph neural network for quality-related fault detection[J]. Process Saf. Environ. Prot. 184, 1512–1524. https://doi.org/10.1016/j.psep.2024.02.070 (2024).
Wang, L. & Zhao, W. An ensemble deep learning network based on 2D convolutional neural network and 1D LSTM with self-attention for bearing fault diagnosis[J]. Appl. Soft Comput. 172, 112889. https://doi.org/10.1016/j.asoc.2025.112889 (2025).
Zheng, B. et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis[J]. Mech. Syst. Signal Process. 208, 111047. https://doi.org/10.1016/j.ymssp.2023.111047 (2024).
Cui, L. et al. A self-attention based contrastive learning method for bearing fault diagnosis[J]. Expert Syst. Appl. 238, 121645doi. https://doi.org/10.1016/j.eswa.2023.121645 (2024).
Cui, L. et al. A novel adaptive generalized domain data fusion-driven kernel sparse representation classification method for intelligent bearing fault diagnosis[J]. Expert Syst. Appl. 247, 123225. https://doi.org/10.1016/j.eswa.2024.123225 (2024).
Xiang, Q. et al. ISONet: Reforming 1DCNN for aero-engine system inter-shaft bearing fault diagnosis via input spatial over-parameterization[J]. Expert Syst. Appl. 277, 127248. https://doi.org/10.1016/j.eswa.2025.127248 (2025).
Kulevome, D. K. B. et al. Effective time-series data augmentation with analytic wavelets for bearing fault diagnosis[J]. Expert Syst. Appl. 249, 123536. https://doi.org/10.1016/j.eswa.2024.123536 (2024).
Kumar, P. et al. Multi-size wide kernel convolutional neural network for bearing fault diagnosis[J]. Adv. Eng. Softw. 198, 103799doi. https://doi.org/10.1016/j.advengsoft.2024.103799 (2024).
Wang, Z. et al. Few-shot fault diagnosis for machinery using multi-scale perception multi-level feature fusion image quadrant entropy. Adv. Eng. Inform. 63, 102972doi. https://doi.org/10.1016/j.aei.2024.102972 (2025).
Wang, Z. et al. Multi-modal multi-scale multi-level fusion quadrant entropy for mechanical fault diagnosis. Expert Syst. Appl. 281, 127715. https://doi.org/10.1016/j.eswa.2025.127715 (2025).
Wang, Z. et al. A generalized fault diagnosis framework for rotating machinery based on phase entropy. Reliab. Eng. Syst. Saf. 256, 110745doi. https://doi.org/10.1016/j.ress.2024.110745 (2025).
Li, J. et al. Cross-domain adaptation fault diagnosis with maximum classifier discrepancy and deep feature alignment under variable working conditions[J]. IEEE Trans. Reliab. https://doi.org/10.1109/TR.2025.3551155 (2025).
Yao, R. et al. Parallel convolutional transfer network for bearing fault diagnosis under varying operation states[J]. IEEE Trans. Instrum. Meas. https://doi.org/10.1109/TIM.2024.3480212 (2024).
Deng, W., Guan, H. & Zhao, H. Parameterized Iterative Time-Frequency-Multisqueezing Transform for Bearing Fault Diagnosis[J]. IEEE Trans. Instrum. Meas. https://doi.org/10.1109/TIM.2025.3561399 (2025).
Deng, W. et al. Robust dual-model collaborative broad learning system for classification under label noise environments[J]. IEEE Internet Things J. https://doi.org/10.1109/JIOT.2025.3545741 (2025).
Zhang, J. et al. Source-free domain adaptation for cross-domain remaining useful life prediction: A distributed federated learning perspective[J]. Reliab. Eng. Syst. Saf. 112271 https://doi.org/10.1016/j.ress.2026.112271 (2026).
Zhang, J. et al. Remaining useful life prediction based on self-attention mechanism-sequential variational autoencoder: From a semi-supervised perspective. Adv. Eng. Inform. 71, 104242. https://doi.org/10.1016/j.aei.2025.104242 (2026).
Zhang, J. et al. A transferable topology-aware graph pooling network for remaining useful life prediction under cross-domain conditions[J]. IEEE Trans. Reliab. https://doi.org/10.1109/TR.2025.3643102 (2025).
Yang, Q. et al. Hybrid data-driven and model-informed online tool wear detection in milling machines[J]. J. Manuf. Syst. 63, 329–343. https://doi.org/10.1016/j.jmsy.2022.04.001 (2022).
Shen, S. et al. A physics-informed deep learning approach for bearing fault detection[J]. Eng. Appl. Artif. Intell. 103, 104295doi. https://doi.org/10.1016/j.engappai.2021.104295 (2021).
Li, H. et al. An interpretable waveform segmentation model for bearing fault diagnosis[J]. Adv. Eng. Inform. 61, 102480doi. https://doi.org/10.1016/j.aei.2024.102480 (2024).
Liao, J. X. et al. Classifier-guided neural blind deconvolution: A physics-informed denoising module for bearing fault diagnosis under noisy conditions[J]. Mech. Syst. Signal Process. 222, 111750. https://doi.org/10.1016/j.ymssp.2024.111750 (2025).
Russell, M. & Wang, P. Physics-informed deep learning for signal compression and reconstruction of big data in industrial condition monitoring[J]. Mech. Syst. Signal Process. 168, 108709doi. https://doi.org/10.1016/j.ymssp.2021.108709 (2022).
Lee, S. et al. Revolution and peak discrepancy-based domain alignment method for bearing fault diagnosis under very low-speed conditions[J]. Expert Syst. Appl. 251, 124084. https://doi.org/10.1016/j.eswa.2024.124084 (2024).
Qin, Y. et al. Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samples[J]. Knowl. Based Syst. 292, 111641. https://doi.org/10.1016/j.knosys.2024.111641 (2024).
Yang, J. B. & Xu, D. L. Evidential reasoning rule for evidence combination[J]. Artif. Intell. 205, 1–29. https://doi.org/10.1016/j.artint.2013.09.003 (2013).
Zimmermann, H. J. Fuzzy set theory[J]. Wiley Interdiscip Rev. Comput. Stat. 2 (3), 317–332. https://doi.org/10.1002/wics.82 (2010).
Cheng, X. et al. A model for flywheel fault diagnosis based on fuzzy fault tree analysis and belief rule base[J]. Machines 10 (2), 73. https://doi.org/10.3390/machines10020073 (2022).
Yin, X. et al. A new interpretable belief rule base model with step-length convergence strategy for aerospace relay health state assessment[J]. Sci. Rep. 13 (1), 14066. https://doi.org/10.1038/s41598-023-41305-z (2023).
Kong, G. et al. A belief rule-based decision support system for clinical risk assessment of cardiac chest pain[J]. Eur. J. Oper. Res. 219 (3), 564–573. https://doi.org/10.1016/j.ejor.2011.10.044 (2012).
Deng, Q. et al. A new health state assessment method for complex systems based on approximate belief rule base with attribute reliability[J]. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3490701 (2024).
Liu, J. et al. A novel belief rule base representation, generation and its inference methodology[J]. Knowl. Based Syst. 53, 129–141. https://doi.org/10.1016/j.knosys.2013.08.019 (2013).
Li, J. et al. A novel classification method based on an online extended belief rule base with a human-in-the-loop strategy[J]. Appl. Intell. 55 (7), 586. https://doi.org/10.1007/s10489-025-06434-0 (2025).
Hou, B. et al. Multi-output extended belief rule-base system and its parameter learning schemes[J]. Appl. Soft Comput. 170, 112687doi. https://doi.org/10.1016/j.asoc.2024.112687 (2025).
Yang, L. H. et al. A micro-extended belief rule-based system for big data multiclass classification problems[J]. IEEE Trans. Syst. Man. Cybernetics: Syst. 51 (1), 420–440. https://doi.org/10.1109/TSMC.2018.2872843 (2018).
Fu, Y. G. et al. EBRB cascade classifier for imbalanced data via rule weight updating[J]. Knowl. Based Syst. 223, 107010. https://doi.org/10.1016/j.knosys.2021.107010 (2021).
Ran, X. et al. A novel fuzzy system-based genetic algorithm for trajectory segment generation in urban global positioning system[J]. J. Adv. Res. https://doi.org/10.1016/j.jare.2025.06.007 (2025).
Dong, Y. et al. An interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis with small samples[J]. Reliab. Eng. Syst. Saf. 251, 110404. https://doi.org/10.1016/j.ress.2024.110404 (2024).
Zheng, X. et al. A novel empirical reconstruction Gauss decomposition method and its application in gear fault diagnosis[J]. Mech. Syst. Signal Process. 210, 111174. https://doi.org/10.1016/j.ymssp.2024.111174 (2024).
Zhang, Y. et al. Multi-modal data cross-domain fusion network for gearbox fault diagnosis under variable operating conditions[J]. Eng. Appl. Artif. Intell. 133, 108236. https://doi.org/10.1016/j.engappai.2024.108236 (2024).
Funding
This work was supported in part by Key Laboratory of Equipment Data Security and Guarantee Technology, Ministry of Education under Grant No.GDZB2024050100, in part by the Natural Science Foundation of Heilongjiang Province under Grant No. PL2024G009, in part by the Basic Research Support Program for Outstanding Young Teachers in Provincial Undergraduate Universities of Heilongjiang Province under Grant No. YQJH2024116, in part by Shandong Provincial Natural Science Foundation under Grant No. ZR2023QF010, in part by National Science Foundation of China Grant No. 72471067.
Author information
Authors and Affiliations
Contributions
**XingChi Yan** : Writing – original draft, Software, Methodology, Formal analysis, Data curation.**Ning Li** : Writing – original draft, Methodology, Investigation. **ShuYin Nan** : Conceptualization, Investigation. **Yan Yu** : Writing – review & editing, Supervision, Funding acquisition, Conceptualization. Resources. **Run Dai** : Investigation.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Yan, X., Li, N., Nan, S. et al. A bearing fault diagnosis method for complex system based on improved extended belief rule base. Sci Rep (2026). https://doi.org/10.1038/s41598-026-44629-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-44629-8
