RESEARCH PAPER
Experimental Research on Vibration Feature Recognition for Bearing Reliability Based on Improved Convolutional Neural Networks
1
Henan University of Science and Technology, China
Submission date: 2025-06-29
Final revision date: 2025-07-23
Acceptance date: 2025-09-24
Online publication date: 2025-09-26
Publication date: 2025-09-26
Eksploatacja i Niezawodność – Maintenance and Reliability 2026;28(2):211279
HIGHLIGHTS
- A fault recognition method based on an improved convolutional neural network (PCNN) is proposed, and a model combining the zebra optimization algorithm (ZOA), PCNN, and attention mechanism (AT) is established.
- Comparative validation between the ZOA-PCNN-AT model and the traditional CNN model demonstrates that the proposed model can recognize different fault types with fewer iterations, achieves higher recognition accuracy, and enhances the reliability of fault identification.
- The Empirical Mode Decomposition (EMD) algorithm is upgraded to the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm, yielding denoised signals with improved signal-to-noise ratios.
KEYWORDS
TOPICS
ABSTRACT
In the past network model application, convolutional neural networks (CNN) have better performance in the recognition of vibration characteristics of electric spindle bearings, but due to their own structural limitations, the actual recognition is still misjudged, which affects the efficient operation of machine tools and product quality. To enhance the reliability of bearing fault identification, this paper selects motorized spindle bearings as the main research object. First, it analyzes the identification process and issues of traditional CNN regarding vibration characteristics. Subsequently, it innovatively proposes a Parallel Convolutional Neural Network-Attention Mechanism (ZOA-PCNN-AT) model improved by the Zebra Optimization Algorithm. This model uses the Zebra Optimization Algorithm to optimize the structure of the parallel convolutional neural network and combines an attention mechanism to enhance the ability to capture key features. Finally, comparative experiments verify the effectiveness of the proposed method.
ACKNOWLEDGEMENTS
This work was partially supported by the National Natural Science Foundation of China (Grant No. 52375052), in part by the Provincial Science and Technology Research and Development Program Joint Fund under Grant 222103810040, and in part by the 2023 Key Scientific Research of Universities in Henan Province Project, under Grant 23A460017.
REFERENCES (31)
1.
Wang H, Deng S, Yang J, et al. A fault diagnosis method for rolling element bearing (REB) based on reducing REB foundation vibration and noise-assisted vibration signal analysis. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2019, 233 (7): 2574-2587. https://doi.org/10.1177/095440....
2.
He M, He D. A new hybrid deep signal processing approach for bearing fault diagnosis using vibration signals. Neurocomputing, 2020, 396(prepublish): 542-555. https://doi.org/10.1016/j.neuc....
3.
Zhang J, Selvakumar S R, Deng N, et al. Bearing Fault Vibration Signal Feature Extraction and Recognition Method Based on EEMD Superresolution Sparse Decomposition. Shock and Vibration, 2022. https://doi.org/10.1155/2022/9....
4.
Fang S, Hu B, Liu P S. The Analysis on Fire Smoke Exhausting Robot Vibration Based on Wavelet Transform. Advanced Materials Research, 2011, 1442 (328-330): 1887-1891. https://doi.org/10.4028/www.sc....
5.
Liu F G, Tao Y F, Li G X. Research on the Impeller Tip Screenout Fault Feature Extraction of the Submersible Pump Units Based on Wavelet Analysis. Advanced Materials Research, 2011, 1250 (225-226): 835-838. https://doi.org/10.4028/www.sc....
6.
Shi J, Li J, Wang T. A Convolutional Neural Network Model-Based Approach for Multi-Fault Diagnosis of Asynchronous Motors[C]//2023 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia). IEEE, 2023: 883-888. https://doi.org/10.1109/ICPSAs....
7.
Tang Y, Zhang C, Wu J, et al. Deep learning-based bearing fault diagnosis using a trusted multi-scale quadratic attention-embedded convolutional neural network. IEEE Transactions on Instrumentation and Measurement, 2024. https://doi.org/10.1109/TIM.20....
8.
Guo J, Yang Y, Li H, et al. A parallel deep neural network for intelligent fault diagnosis of drilling pumps. Engineering Applications of Artificial Intelligence, 2024, 133: 108071. https://doi.org/10.1016/j.enga....
9.
Jiang R, Hu P, Cheng S, et al. Rolling bearing fault diagnosis based on VMD optimized by zebra algorithm[C]//2023 10th International Forum on Electrical Engineering and Automation (IFEEA). IEEE, 2023: 1145-1150. https://doi.org/10.1109/IFEEA6....
10.
Liang J, Wang W, Qu Z, et al. Prediction of Color Change in Heat-Treated Wood Based on Improved Zebra Algorithm Optimized Deep Hybrid Kernel Extreme Learning Machine Model (IZOA-DHKELM). Forests, 2025, 16 (2): 253. https://doi.org/10.3390/f16020....
11.
Liang Q, Niu M, Xu X, et al. UAV Obstacle Avoidance Trajectory Planning Based on Improved Zebra Optimization Algorithm[C]//2024 43rd Chinese Control Conference (CCC). IEEE, 2024: 3174-3179. https://doi.org/10.23919/CCC63....
12.
Deepanraj B, Saravanan A, Senthilkumar N, et al. Drilling characteristics optimization of polymer composite fortified with eggshells using box-Behnken design and zebra optimization algorithm. Results in Engineering, 2025, 25104102-104102. https://doi.org/10.1016/j.rine....
13.
Punia P, Raj A, Kumar P. Enhanced zebra optimization algorithm for reliability redundancy allocation and engineering optimization problems. Cluster Computing, 2025, 28 (4): 267-267. https://doi.org/10.1007/s10586....
14.
Liu H, Yu S, Wang X. Mega-constellation satellite maneuver forecast via network with attention mechanism. Advances in Space Research, 2025, 75 (6): 4942-4962. https://doi.org/10.1016/j.asr.....
15.
Sen S, Pandit K A, Chakraborty P, et al. Performance evaluation of efficient interpretable CNN-transformer model for redshift prediction. Signal, Image and Video Processing, 2025, 19 (4): 326-326. https://doi.org/10.1007/s11760....
16.
Yang M, Song M, Guo Y, et al. Prediction of shield tunneling-induced ground settlement using LSTM architecture enhanced by multi-head self-attention mechanism. Tunnelling and Underground Space Technology incorporating Trenchless Technology Research, 2025, 161106536-106536. https://doi.org/10.1016/j.tust....
17.
Ding S, Chen R, Liu H, et al. ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis. Measurement Science and Technology, 2024, 35 (6). https://doi.org/10.1088/1361-6....
18.
Zhang H, Wu Q, Tang W, et al. Acoustic Signal-Based Defect Identification for Directed Energy Deposition-Arc Using Wavelet Time–Frequency Diagrams. Sensors, 2024, 24 (13): 4397-4397. https://doi.org/10.3390/S24134....
19.
Zhang Q, Zhang X, Yang J, et al. Introducing Euclidean distance optimization into Softmax loss under neural collapse. Pattern Recognition, 2025, 162111400-111400. https://doi.org/10.1016/J.PATC....
20.
Xiangzhi W, Chaojiang L, Hun G, et al. Electrical discharge machining of polycrystalline diamond: A review. Proceedings of the Institution of Mechanical Engineers, 2023, 237 (11): 1611-1627. https://doi.org/10.1177/095440....
21.
Koçillari L, Lorenz M G, Engel M N, et al. Sampling bias corrections for accurate neural measures of redundant, unique, and synergistic information. bioRxiv: the preprint server for biology, 2024. https://doi.org/10.1101/2024.0....
22.
Layton W O, Peng S, Steinmetz T S. ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks. Sensors, 2024, 24 (23): 7453-7453. https://doi.org/10.3390/S24237....
23.
Zhao W, Zhu X, Shi H, et al. Global Cross-Entropy Loss for Deep Face Recognition. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 2025, PP. https://doi.org/10.1109/TIP.20....
24.
Wang Q, Xu F, Ma T. Wavelet packet decomposition with motif patterns for rolling bearing fault diagnosis under variable working loads. Journal of Vibration and Control, 2025, 31 (3-4): 516-527. https://doi.org/10.1177/107754....
25.
Assri E N, Jallal A M, Chabaa S, et al. Enhancing building energy consumption prediction using LSTM, Kalman filter, and continuous wavelet transform. Scientific African, 2025, 27e02560-e02560. https://doi.org/10.1016/J.SCIA....
26.
Ping Y, Bin R L, Jie C, et al. Bearing fault diagnosis method for unbalance data based on Gramian angular field. Journal of Intelligent & Fuzzy Systems, 2024, 47 (1-2): 45-54. https://doi.org/10.3233/JIFS-2....
27.
Adrien B, Valentin D, Benoît F. DT-SNE: t-SNE discrete visualizations as decision tree structures. Neurocomputing, 2023, 529101-112. https://doi.org/10.1016/J.NEUC....
28.
Mandal K A, Dehuri S, Sarma D K P. Analysis of machine learning approaches for predictive modeling in heart disease detection systems. Biomedical Signal Processing and Control, 2025, 106107723-107723. https://doi.org/10.1016/J.BSPC....
29.
Zeng Q, Wang M, Zhang Y, et al. Machine learning-assisted development of TMDs-type gas-sensitive materials for dissolved gases in oil-immersed transformer oils. Materials Today Chemistry, 2025, 44102583-102583. https://doi.org/10.1016/J.MTCH....
30.
DevarasiddappaD, ChandrasekaranM, RavikumarM, et al. Modified teaching learning based optimization for maximization of MRR in wire-cut EDM of Ti6Al4V alloy for sustainable production. AIP Conference Proceedings, 2019, 2128 (1): 040007. https://doi.org/10.1063/1.5117....
31.
Ayetiran F E, Özgöbek Ö. An inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection. Information Systems, 2024, 123102378. https://doi.org/10.1016/J.IS.2....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
