Search for Author, Title, Keyword
RESEARCH PAPER
Rolling bearing fault diagnosis method based on multi-scale pooling residual convolutional neural network under noisy environment
,
 
,
 
,
 
 
 
 
More details
Hide details
1
Lanzhou university of technology, China
 
2
Yunnan Wenshan Aluminum Co, Ltd, China
 
 
Submission date: 2024-05-03
 
 
Final revision date: 2024-06-15
 
 
Acceptance date: 2024-08-08
 
 
Online publication date: 2024-08-11
 
 
Publication date: 2024-08-11
 
 
Corresponding author
Chengxiang Miao   

Lanzhou university of technology, China
 
 
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(1):192167
 
HIGHLIGHTS
  • Wide convolution kernel is used for feature extraction.
  • The MSPFE module combined with UPA is proposed.
  • Gated convolution and a new activation function IReLU are put forward. On the basis of the ReLU function, the IReLU activation function introduces a new continuous function in the negative half axis to overcome the shortcomings of the existing activation function.
KEYWORDS
TOPICS
ABSTRACT
To address the issues of unstable performance and poor generalization ability of bearing fault diagnosis model caused by strong noise and variable operating conditions in actual production,this paper proposes a rolling bearing fault diagnosis method based on MSPRCNN model. By converting vibration signals to frequency domain with FTand utilizing wide convolution kernels for feature extraction, the approach aims to enhance fault detection. A MSPFE module captures information at different scales to simplify complexity, while an UPA module establishes correlations between frequency domain positions. To reduce the impact of noise and address the vanishing gradient problem, the MSPRCNN model employs GC instead of standard convolution, and utilizes the IReLU activation function to improve model feature representation. Experimental results on two datasets show that the fault recognition accuracy is 98.71% under variable loads and 98.2% under variable speeds. The MSPRCNN model outperforms other methods in fault recognition and generalization in noisy environments.
REFERENCES (32)
1.
He M, He D. Deep learning based approach for bearing fault diagnosis[J]. IEEE Transactions on Industry Applications, 2017, 53(3): 3057-3065. DOI: 10.1109/tia.2017.2661250.
 
2.
Sun HM, He DQ, Lao ZP, Jin ZZ, Liu C, Shan S. Fault diagnosis of train traction motor bearing based on improved deep residual network[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2024, 238(7): 3084-3099. DOI: 10.1177/09544062231196938.
 
3.
Du SC, Liu T, Huang DL, Li GL. An optimal ensemble empirical mode decomposition method for vibration signal decomposition[J]. Journal of Vibration and Acoustics, 2017, 139(3): 031003. DOI: 10.1115/1.4035480.
 
4.
Wang FT, Deng G, Liu CX, Su WS, Han QK, Li HK. A deep feature extraction method for bearing fault diagnosis based on empirical mode decomposition and kernel function[J]. Advances in Mechanical Engineering, 2018, 10(9): 1687814018798251. DOI: 10.1177/1687814018798251.
 
5.
He KM, Zhang XY, Ren SQ, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. DOI: 10.1109/tpami.2015.2389824.
 
6.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. DOI: 10.1145/3065386.
 
7.
Zhao J, Yang SP, Li Q, Liu YQ, Gu XH, Liu WP. A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network[J]. Measurement, 2021, 176: 109088. DOI: 10.1016/j.measurement.2021.109088.
 
8.
Wu GG, Ji XR, Yang GL, Jia Y, Cao CC. Signal-to-Image: Rolling bearing fault diagnosis using ResNet family deep-learning models[J]. Processes, 2023, 11(5): 1527. DOI: 10.3390/pr11051527.
 
9.
Zhang YH, Shang L, Gao HB, He YL, Xu XB, Chen YJ. A new method for diagnosing motor bearing faults based on gramian angular field image coding and improved CNN-ELM [J]. IEEE Access, 2023, 11: 11337-11349. DOI: 10.1109/access.2023.3241367.
 
10.
Xie SL, Ren GY, Zhu JJ. Application of a new one-dimensional deep convolutional neural network for intelligent fault diagnosis of rolling bearings[J]. Science Progress, 2020, 103(3): 0036850420951394. DOI: 10.1177/0036850420951394.
 
11.
Hakim M, Omran AAB, Inayat-Hussain JI, Ahmed AN, Abdellatef H, Abdellatif A, Gheni HM. Bearing fault diagnosis using lightweight and robust one-dimensional convolution neural network in the frequency domain[J]. Sensors, 2022, 22(15): 5793. DOI: 10.3390/s22155793.
 
12.
Chen XH, Zhang BK, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32(4): 971-987. DOI: 10.1007/s10845-020-01600-2.
 
13.
Chen JB, Huang RY, Zhao K, Wang W, Liu LC, Li WH. Multiscale convolutional neural network with feature alignment for bearing fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10. DOI: 10.1109/tim.2021.3077673.
 
14.
Zhao WL, Wang ZJ, Cai WA, Zhang QQ, Wang JY, Du WH, Yang NN, He XX. Multiscale inverted residual convolutional neural network for intelligent diagnosis of bearings under variable load condition[J]. Measurement, 2022, 188: 110511. DOI: 10.1016/j.measurement.2021.110511.
 
15.
Lee CY, Zhuo GL. Identifying bearing faults using multiscale residual attention and multichannel neural network[J]. IEEE Access, 2023, 11: 26953-26963. DOI: 10.1109/access.2023.3257101.
 
16.
Kang J, Luo YT, Wang P, Wei Y, Zhou YR. Fault diagnosis of rotating machinery under complex conditions based on multi-scale convolutional neural networks[C]//Journal of Physics: Conference Series. IOP Publishing, 2023, 2658(1): 012038. DOI: 10.1088/1742-6596/2658/1/012038.
 
17.
Zhang HC, Shi PM, Han DY, Jia LJ. Research on rolling bearing fault diagnosis method based on AMVMD and convolutional neural networks[J]. Measurement, 2023, 217: 113028. DOI: 10.1016/j.measurement.2023.113028.
 
18.
Peng DD, Wang H, Liu ZL, Zhang W, Zuo MJ, Chen J. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4949-4960. DOI: 10.1109/tii.2020.2967557.
 
19.
Huang NT, Chen QZ, Cai GW, Xu DG, Zhang L, Zhao WG. Fault diagnosis of bearing in wind turbine gearbox under actual operating conditions driven by limited data with noise labels[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70: 1-10. DOI: 10.1109/tim.2020.3025396.
 
20.
Liang PF, Wang WH, Yuan XM, Liu SY, Zhang LJ, Cheng YW. Intelligent fault diagnosis of rolling bearing based on wavelet transform and improved ResNet under noisy labels and environment[J]. Engineering Applications of Artificial Intelligence, 2022, 115: 105269. DOI: 10.1016/j.engappai.2022.105269.
 
21.
Hu BB, Tang JH, Wu JM, Qing JJ. An attention EfficientNet-based strategy for bearing fault diagnosis under strong noise[J]. Sensors, 2022, 22(17): 6570. DOI: 10.3390/s22176570.
 
22.
Wang X, Qin Y, Wang Y, Xiang S, Chen HZ. ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis[J]. Neurocomputing, 2019, 363: 88-98. DOI: 10.1016/j.neucom.2019.07.017.
 
23.
Zheng QM, Tan D, Wang FH. Improved convolutional neural network based on fast exponentially linear unit activation function[J]. IEEE Access, 2019, 7: 151359-151367. DOI: 10.1109/access.2019.2948112.
 
24.
Lin GF, Shen W. Research on convolutional neural network based on improved Relu piecewise activation function[J]. Procedia computer science, 2018, 131: 977-984. DOI: 10.1016/j.procs.2018.04.239.
 
25.
Chang SY, Zhang Y, Han W, Yu M, Guo XX, Tan W, Cui XD, Witbrock M, Hasegawa-Johnson M, Huang TS. Dilated recurrent neural networks[J]. Advances in Neural Information Processing Systems, 2017, 30. DOI: arxiv-1710.02224.
 
26.
Kuo CCJ. Understanding convolutional neural networks with a mathematical model[J]. Journal of Visual Communication and Image Representation, 2016, 41: 406-413. DOI: 10.1016/j.jvcir.2016.11.003.
 
27.
Yu JH, Lin Z, Yang JM, Shen XH, Lu X, Huang TM. Free-form image inpainting with gated convolution[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 4471-4480. https://doi.org/10.1109/ICCV.2....
 
28.
Case Western Reserve University Bearing Data Center; 2018. Available at: https://csegroups.case.edu/bea... data center/pages/download-data-file.
 
29.
Shao ZH, Li WQ, Xiang H, Yang SX, Weng ZQ. Fault diagnosis method and application based on multi-scale neural network and data enhancement for strong noise[J]. Journal of Vibration Engineering & Technologies, 2024, 12(1): 295-308. DOI: 10.1007/s42417-022-00844-x.
 
30.
Chao ZQ, Han T. A novel convolutional neural network with multiscale cascade midpoint residual for fault diagnosis of rolling bearings[J]. Neurocomputing, 2022, 506: 213-227. DOI: 10.1016/j.neucom.2022.07.022.
 
31.
Li F, Wang LP, Wang DC, Wu J, Zhao HJ. An adaptive multiscale fully convolutional network for bearing fault diagnosis under noisy environments[J]. Measurement, 2023, 216: 112993. DOI: 10.1016/j.measurement.2023.112993.
 
32.
Wang Q, Xu FY. A novel rolling bearing fault diagnosis method based on adaptive denoising convolutional neural network under noise background[J]. Measurement, 2023: 113209. DOI: 10.1016/j.measurement.2023.113209.
 
 
CITATIONS (1):
1.
Rolling bearing fault diagnosis method based on MTF-MMCNN
Ruicheng Feng, Qiyue Zhang, Lu Wang, Manwen Li, Chunli Lei
Nondestructive Testing and Evaluation
 
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top