Abstract
Convolutional neural network models in rolling bearing fault diagnosis have problems such as relatively large number of parameters, overly complex structure and long computation time. To address the above issues, this paper designs an improved fully connected layer (FC) layer in the multilayer perceptron model that can be used for rolling bearing fault diagnosis. Based on this idea, this paper proposes a “Reshape, Linear, Transpose, Linear” fully connected layer replacement strategy (RLTL) by using the Kronecker decomposition method. This method decomposes the weight matrix, converting one linear operation to two linear operations in the FC layer, which results in a significant reduction in the total number of parameters and calculations. On this foundation, this paper also uses one-dimensional convolution to improve the current mainstream two-dimensional lightweight convolutional neural networks and lightweight strategies, and designs nine alternative modules. The results show that the proposed RLTL module replacement scheme decreases the number of parameters of the multilayer perceptron to less than 1%, reduces the number of calculations to less than 10%, and increases the diagnostic accuracy by more than 30% in a small-sample and noise-free environment. In addition, this paper also verifies and compares the effects of different transformation methods of convolutional neural networks in each alternative module on small sample diagnosis and noise immunity diagnosis of rolling bearings.
Similar content being viewed by others
Data availability
The figures and tables data used to support the findings of this study are included within the article, and the article permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abbreviations
- CNN:
-
Convolutional neural network
- FC:
-
Fully connected layer
- MLP:
-
Multilayer perceptron
- RLTL:
-
“Reshape, Linear, Transpose, Linear” fully connected layer
- AE:
-
Auto-encoder
- DNN:
-
Deep neural network
- RNN:
-
Recurrent neural network
- DBN:
-
Deep belief network
- RBF:
-
Radial basis function
- PNN:
-
Probabilistic neural network
- 1DCNN:
-
One-dimensional data convolutional neural network
- 2DCNN:
-
Two-dimensional data convolutional neural network
References
Nandi S, Toliyat HA, Li X (2005) Condition monitoring and fault diagnosis of electrical motors—a review. IEEE T Energy Conver 20(4):719–729
Zhang S, Zhang S, Wang B et al (2019) Deep learning algorithms for bearing fault diagnostics-a review. In: 2019 IEEE 12th international symposium on diagnostics for electrical machines, pp 257–263
Mushtaq S, Islam MM, Sohaib M (2021) Deep learning aided data-driven fault diagnosis of rotatory machine: a comprehensive review. Energies 14(16):5150. https://doi.org/10.3390/en14165150
Zhao Z, Li T, Wu J et al (2020) Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study. ISA T 107:224–255. https://doi.org/10.1016/j.isatra.2020.08.010
Padovese LR (2002) Comparison between probabilistic and multilayer perceptron neural networks for rolling bearing fault classification. Int J Model Simul 22(2):97–103. https://doi.org/10.1080/02286203.2002.11442229
Samanta B, Al-Balushi KR, Al-Araimi SA (2006) Artificial neural networks and genetic algorithm for bearing fault detection. Soft Comput 10(3):264–271. https://doi.org/10.1007/s00500-005-0481-0
Sinitsin V, Ibryaeva O, Sakovskaya V et al (2021) Intelligent Bearing fault diagnosis method combining mixed input and hybrid CNN-MLP model. arXiv preprint arXiv:2112.08673. https://doi.org/10.48550/arXiv.2112.08673
de Almeida LF, Bizarria JWP, Bizarria FCP et al (2015) Condition-based monitoring system for rolling element bearing using a generic multi-layer perceptron. J Vib Control 21(16):3456–3464. https://doi.org/10.1177/1077546314524260
Zhang W, Peng G, Li C et al (2017) A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors-Basel 17(2):425. https://doi.org/10.3390/s17020425
Zhao B, Zhang X, Li H et al (2020) Intelligent fault diagnosis of rolling bearings based on normalized CNN considering data imbalance and variable working conditions. Knowl-Based Syst 199:105971. https://doi.org/10.1016/j.knosys.2020.105971
Zhang K, Wang J, Shi H et al (2021) A fault diagnosis method based on improved convolutional neural network for bearings under variable working conditions. Measurement 182:109749. https://doi.org/10.1016/j.measurement.2021.109749
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Srivastava RK, Greff K, Schmidhuber J (2015) Highway NETWORKS. arXiv preprint arXiv:1505.00387. https://doi.org/10.48550/arXiv.1505.00387
Iandola F N, Han S, Moskewicz M W et al (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. arXiv preprint arXiv:1602.07360. https://doi.org/10.48550/arXiv.1602.07360
Gholami A, Kwon K, Wu B et al (2016) SqueezeNext:hardware-aware neural network design. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 1638–1647
Howard A G, Zhu M, Chen B et al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. https://doi.org/10.48550/arXiv.1704.04861
Sandler M, Howard A, Zhu M et al (2018) MobileNetV2:inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Zhang X, Zhou X, Lin M et al (2017) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848–6856
Ma N, Zhang X, Zheng H T et al (2018) ShuffleNet V2: Practical guidelines for efficient CNN architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116–131
Yang Z, Jia M (2019) GA-1DLCNN method and its application in bearing fault diagnosis. J Southeast Univ (English Edition) 35(1):36–42
Xue F, Zhang W, Xue F et al (2021) A novel intelligent fault diagnosis method of rolling bearing based on two-stream feature fusion convolutional neural network. Measurement 176:109226
Merino DI (1991) Topics in matrix analysis. Cambridge, UK
Acknowledgements
This study was funded by: National Natural Science Foundation of China (Grant No. 52005352, 62173238, 52205163). Key Laboratory of Vibration and Control of Aero-Propulsion System, Ministry of Education, Northeastern University (VCAME202007). Open Fund of Key Laboratory of Fundamental Science for National Defense of Aeronautical Digital Manufacturing Process of Shenyang Aerospace University (SHSYS202107)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflicts of interest. This manuscript has not been published or presented elsewhere in part or in entirety and is not under consideration by another journal. We have read and understood your journal’s policies, and we believe that neither the manuscript nor the study violates any of these. There are no conflicts of interest to declare. The data of article permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Additional information
Technical Editor: Jarir Mahfoud.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, X., Li, H., Meng, W. et al. Research on fault diagnosis of rolling bearing based on lightweight convolutional neural network. J Braz. Soc. Mech. Sci. Eng. 44, 462 (2022). https://doi.org/10.1007/s40430-022-03759-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-022-03759-6