Bearing fault diagnosis with parallel CNN and LSTM

Guanghua Fu; Qingjuan Wei; Yongsheng Yang; Guanghua Fu; Qingjuan Wei; Yongsheng Yang

doi:10.3934/mbe.2024105

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 2: 2385-2406. doi: 10.3934/mbe.2024105

Previous Article Next Article

Research article

Bearing fault diagnosis with parallel CNN and LSTM

Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China

Academic Editor: Vladimir Mityushev

Received: 02 November 2023 Revised: 07 December 2023 Accepted: 25 December 2023 Published: 16 January 2024

Intelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signals and the robustness of the model, we construct a fault diagnostic model based on convolutional neural network (CNN) and long short-term memory (LSTM) parallel network to extract their temporal and spatial features from two perspectives. First, via resampling, vibration signal is split into equal-sized slices which are then converted into time-frequency images by continuous wavelet transform (CWT). Second, LSTM extracts the time-correlation features of 1D signals as one path, and 2D-CNN extracts the local frequency distribution features of time-frequency images as another path. Third, 1D-CNN further extracts integrated features from the fusion features yielded by former parallel paths. Finally, these categories are calculated through the softmax function. According to experimental results, the proposed model has satisfactory diagnostic accuracy and robustness in different contexts on two different datasets.
- bearing fault diagnosis,
- CWT,
- CNN,
- LSTM,
- parallel path
Citation: Guanghua Fu, Qingjuan Wei, Yongsheng Yang. Bearing fault diagnosis with parallel CNN and LSTM[J]. Mathematical Biosciences and Engineering, 2024, 21(2): 2385-2406. doi: 10.3934/mbe.2024105

Related Papers:

Abstract

Intelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signals and the robustness of the model, we construct a fault diagnostic model based on convolutional neural network (CNN) and long short-term memory (LSTM) parallel network to extract their temporal and spatial features from two perspectives. First, via resampling, vibration signal is split into equal-sized slices which are then converted into time-frequency images by continuous wavelet transform (CWT). Second, LSTM extracts the time-correlation features of 1D signals as one path, and 2D-CNN extracts the local frequency distribution features of time-frequency images as another path. Third, 1D-CNN further extracts integrated features from the fusion features yielded by former parallel paths. Finally, these categories are calculated through the softmax function. According to experimental results, the proposed model has satisfactory diagnostic accuracy and robustness in different contexts on two different datasets.

References

[1]	D. T. Hoang, H. J. Kang, A survey on deep learning based bearing fault diagnosis, Neurocomputing, 335 (2019), 327–335. https://doi.org/10.1016/j.neucom.2018.06.078 doi: 10.1016/j.neucom.2018.06.078
[2]	M. Zeng, W. Zhang, Z. Chen, Group-based K-SVD denoising for bearing fault diagnosis, IEEE Sens. J., 19 (2019), 6335–6343. https://doi.org/10.1109/JSEN.2019.2910868 doi: 10.1109/JSEN.2019.2910868
[3]	X. Yan, D. She, Y. Xu, Deep order-wavelet convolutional variational autoencoder for fault identification of rolling bearing under fluctuating speed conditions, Expert Syst. Appl., 216 (2023), 119479. https://doi.org/10.1016/j.eswa.2022.119479 doi: 10.1016/j.eswa.2022.119479
[4]	N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. Math. Phys. Eng. Sci., 454 (1998), 903–995. https://doi.org/10.1098/rspa.1998.0193 doi: 10.1098/rspa.1998.0193
[5]	K. Dragomiretskiy, D. Zosso, Variational mode decomposition, IEEE Trans. Signal Process, 62 (2013), 531–544. https://doi.org/10.1109/TSP.2013.2288675 doi: 10.1109/TSP.2013.2288675
[6]	G. Xin, Z. Li, L. Jia, Q. Zhong, H. Dong, N. Hamzaoui, et al., Fault diagnosis of wheelset bearings in high-speed trains using logarithmic short-time Fourier transform and modified self-calibrated residual network, IEEE Trans. Ind. Inf., 18 (2021), 7285–7295. https://doi.org/10.1109/TIM.2021.3139706 doi: 10.1109/TIM.2021.3139706
[7]	I. Daubechies, Ten Lectures on Wavelets, Society for industrial and applied mathematics, 1992.
[8]	M. Q. Tran, M. K. Liu, Q. V. Tran, T. K. Nguyen, Effective fault diagnosis based on wavelet and convolutional attention neural network for induction motors, IEEE Trans. Instrum. Meas., 71 (2021), 1–13. https://doi.org/10.1109/TIM.2021.3139706 doi: 10.1109/TIM.2021.3139706
[9]	L. Yuan, D. Lian, X. Kang, Y. Chen, K. Zhai, Rolling bearing fault diagnosis based on convolutional neural network and support vector machine, IEEE Access, 8 (2020), 137395–137406. https://doi.org/10.1109/ACCESS.2020.3012053 doi: 10.1109/ACCESS.2020.3012053
[10]	T. Jin, Q. Cheng, H. Chen, S. Wang, J. Guo, C. Chen, Fault diagnosis of rotating machines based on EEMD-MPE and GA-BP, Int. J. Adv. Manuf. Technol., (2021), 1-12. https://doi.org/10.1007/s00170-021-08159-z doi: 10.1007/s00170-021-08159-z
[11]	P. Chen, X. Zhao, Q. Zhu, A novel classification method based on ICGOA-KELM for fault diagnosis of rolling bearing, Appl. Intell., 50 (2020), 2833–2847.
[12]	H. Tao, P. Wang, Y. Chen, V. Stojanovic, H. Yang, An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks, J. Franklin Inst., 357 (2020), 7286–7307. https://doi.org/10.1007/s10489-020-01684-6 doi: 10.1007/s10489-020-01684-6
[13]	J. Gu, Y. Peng, H. Lu, X. Chang, G. Chen, A novel fault diagnosis method of rotating machinery via VMD, CWT and improved CNN, Measurement, 200 (2022), 111635. https://doi.org/10.1016/j.measurement.2022.111635 doi: 10.1016/j.measurement.2022.111635
[14]	N. Saravanan, V. K. Siddabattuni, K. Ramachandran, A comparative study on classification of features by SVM and PSVM extracted using Morlet wavelet for fault diagnosis of spur bevel gear box, Expert Syst. Appl., 35 (2008), 1351–1366. https://doi.org/10.1016/j.eswa.2007.08.026 doi: 10.1016/j.eswa.2007.08.026
[15]	V. Muralidharan, V. Sugumaran, A comparative study of Naïve Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis, Appl. Soft Comput., 12 (2012), 2023–2029. https://doi.org/10.1016/j.asoc.2012.03.021 doi: 10.1016/j.asoc.2012.03.021
[16]	J. Li, X. Yao, X. Wang, Q. Yu, Y. Zhang, Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis, Measurement, 153 (2020), 107419. https://doi.org/10.1016/j.measurement.2019.107419 doi: 10.1016/j.measurement.2019.107419
[17]	H. Li, T. Liu, X. Wu, Q. Chen, Application of EEMD and improved frequency band entropy in bearing fault feature extraction, ISA Trans., 88 (2019), 170–185. https://doi.org/10.1016/j.isatra.2018.12.002 doi: 10.1016/j.isatra.2018.12.002
[18]	H. S. Najim, J. K. Alsalaet, Cross-domain diagnosis of roller bearing faults based on the envelope analysis adaptive features and artificial neural networks, J. Vib. Control, 2023 (2023), 10775463231191684. https://doi.org/10.1177/1077546323119168 doi: 10.1177/1077546323119168
[19]	J. Yang, J. Liu, J. Xie, C. Wang, T. Ding, Conditional GAN and 2-D CNN for bearing fault diagnosis with small samples, IEEE Trans. Instrum. Meas., 70 (2021), 1–12. https://doi.org/10.1109/tim.2021.3119135 doi: 10.1109/tim.2021.3119135
[20]	X. Song, Y. Cong, Y. Song, Y. Chen, P. Liang, A bearing fault diagnosis model based on CNN with wide convolution kernels, J. Ambient Intell. Hum. Comput., 13 (2022), 4041–4056. https://doi.org/10.1007/s12652-021-03177-x doi: 10.1007/s12652-021-03177-x
[21]	J. Zhu, T. Hu, B. Jiang, X. Yang, Intelligent bearing fault diagnosis using PCA-DBN framework, Neural Comput. Appl., 32 (2020), 10773–10781. https://doi.org/10.1007/s00521-019-04612-z doi: 10.1007/s00521-019-04612-z
[22]	P. Zou, B. Hou, J. Lei, Z. Zhang, Bearing fault diagnosis method based on EEMD and LSTM, Int. J. Comput. Commun., 15 (2020). http://doi.org/10.15837/ijccc.2020.1.3780 doi: 10.15837/ijccc.2020.1.3780
[23]	X. Yan, D. She, Y. Xu, M. Jia, Deep regularized variational autoencoder for intelligent fault diagnosis of rotor-bearing system within entire life-cycle process, Knowl.-Based Syst., 226 (2021), 107142.
[24]	K. Tong, Y. Wu, F. Zhou, Recent advances in small object detection based on deep learning: A review, Image Vis. Comput., 97 (2020), 103910. https://doi.org/10.1016/j.imavis.2020.103910 doi: 10.1016/j.imavis.2020.103910
[25]	G. Algan, I. Ulusoy, Image classification with deep learning in the presence of noisy labels: A survey, Knowl.-Based Syst., 215 (2021), 106771. https://doi.org/10.1016/j.knosys.2021.106771 doi: 10.1016/j.knosys.2021.106771
[26]	M. Morchid, Parsimonious memory unit for recurrent neural networks with application to natural language processing, Neurocomputing, 314 (2018), 48–64. https://doi.org/10.1016/j.neucom.2018.05.081 doi: 10.1016/j.neucom.2018.05.081
[27]	Y. Ma, X. Jia, H. Bai, G. Liu, G. Wang, C. Guo, et al., A new fault diagnosis method based on convolutional neural network and compressive sensing, J. Mech. Sci. Technol., 33 (2019), 5177–5188. https://doi.org/10.1007/s12206-019-1007-5 doi: 10.1007/s12206-019-1007-5
[28]	C. Lu, Z. Wang, B. Zhou, Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification, Adv. Eng. Inf., 32 (2017), 139–151. https://doi.org/10.1016/j.aei.2017.02.005 doi: 10.1016/j.aei.2017.02.005
[29]	H. Liu, D. Yao, J. Yang, X. Li, Lightweight convolutional neural network and its application in rolling bearing fault diagnosis under variable working conditions, Sensors, 19 (2019), 4827. https://doi.org/10.3390/s19224827 doi: 10.3390/s19224827
[30]	Y. Jin, C. Chen, S. Zhao, Multisource data fusion diagnosis method of rolling bearings based on improved multiscale CNN, J. Sensors, 2021 (2021), 1–17. https://doi.org/10.1155/2021/2251530 doi: 10.1155/2021/2251530
[31]	Z. Xing, R. Zhao, Y. Wu, T. He, Intelligent fault diagnosis of rolling bearing based on novel CNN model considering data imbalance, Appl. Intell., 52 (2022), 16281–16293. https://doi.org/10.1007/s10489-022-03196-x doi: 10.1007/s10489-022-03196-x
[32]	C. Zhang, J. Feng, C. Hu, Z. Liu, L. Cheng, Y. Zhou, An intelligent fault diagnosis method of rolling bearing under variable working loads using 1-D stacked dilated convolutional neural network, IEEE Access, 8 (2020), 63027–63042. https://doi.org/10.1109/ACCESS.2020.2981289 doi: 10.1109/ACCESS.2020.2981289
[33]	M. Ye, X. Yan, N. Chen, M. Jia, Intelligent fault diagnosis of rolling bearing using variational mode extraction and improved one-dimensional convolutional neural network, Appl. Acoust., 202 (2023), 109143.
[34]	D. Gao, Y. Zhu, Z. Ren, K. Yan, W. Kang, A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity, Knowl.-Based Syst., 231 (2021), 107413. https://doi.org/10.1016/j.apacoust.2022.109143 doi: 10.1016/j.apacoust.2022.109143
[35]	H. Liu, J. Zhou, Y. Zheng, W. Jiang, Y. Zhang, Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders, ISA Trans., 77 (2018), 167–178. https://doi.org/10.1016/j.isatra.2018.04.005 doi: 10.1016/j.isatra.2018.04.005
[36]	B. An, Z. Zhao, S. Wang, S. Chen, X. Chen, Sparsity-assisted bearing fault diagnosis using multiscale period group lasso, ISA Trans., 98 (2020), 338–348. https://doi.org/10.1016/j.isatra.2019.08.042 doi: 10.1016/j.isatra.2019.08.042
[37]	M. Qiao, S. Yan, X. Tang, C. Xu, Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads, IEEE Access, 8 (2020), 66257–66269. https://doi.org/10.1109/ACCESS.2020.2985617 doi: 10.1109/ACCESS.2020.2985617
[38]	G. Fu, Q. Wei, Y. Yang, C. Li, Bearing fault diagnosis based on CNN-BiLSTM and residual module, Meas. Sci. Technol., 34 (2023), 125050. https://doi.org/10.1088/1361-6501/acf598 doi: 10.1088/1361-6501/acf598
[39]	H. Chen, W. Meng, Y. Li, Q. Xiong, An anti-noise fault diagnosis approach for rolling bearings based on multiscale CNN-LSTM and a deep residual learning model, Meas. Sci. Technol., 34 (2023), 045013. https://doi.org/10.1088/1361-6501/acb074 doi: 10.1088/1361-6501/acb074
[40]	S. Ning, Y. Wang, W. Cai, Z. Zhang, Y. Wu, Y. Ren, et al., Research on intelligent fault diagnosis of rolling bearing based on improved shufflenetV2-LSTM, J. Sensors, 2022 (2022). https://doi.org/10.1088/1361-6501/acf598 doi: 10.1088/1361-6501/acf598
[41]	Y. Guo, J. Mao, M. Zhao, Rolling bearing fault diagnosis method based on attention CNN and BiLSTM network, Neural Process. Lett., 55 (2023), 3377–3410. https://doi.org/10.1007/s11063-022-11013-2 doi: 10.1007/s11063-022-11013-2
[42]	M. Ye, X. Yan, N. Chen, Y. Liu, A robust multi-scale learning network with quasi-hyperbolic momentum-based Adam optimizer for bearing intelligent fault diagnosis under sample imbalance scenarios and strong noise environment, Struct. Health Monit., (2023), 14759217231192363. https://doi.org/10.1177/14759217231192363 doi: 10.1177/14759217231192363
[43]	H. Wang, Z. Liu, D. Peng, Y. Qin, Understanding and learning discriminant features based on multiattention 1DCNN for wheelset bearing fault diagnosis, IEEE Trans. Ind. Inf., 16 (2019), 5735–5745. https://doi.org/10.1109/TⅡ.2019.2955540 doi: 10.1109/TⅡ.2019.2955540
[44]	S. Shao, S. Mcaleer, R. Yan, P. Baldi, Highly accurate machine fault diagnosis using deep transfer learning, IEEE Trans. Ind. Inf., 15 (2018), 2446–2455. https://doi.org/10.1109/TⅡ.2018.2864759 doi: 10.1109/TⅡ.2018.2864759
[45]	J. Zhang, Y. Sun, L. Guo, H. Gao, X. Hong, H. Song, A new bearing fault diagnosis method based on modified convolutional neural networks, Chin. J. Aeronaut., 33 (2020), 439–447. https://doi.org/10.1016/j.cja.2019.07.011 doi: 10.1016/j.cja.2019.07.011
[46]	L. Wen, X. Li, L. Gao, Y. Zhang, A new convolutional neural network-based data-driven fault diagnosis method, IEEE Trans. Ind. Electron., 65 (2017), 5990–5998. https://doi.org/10.1109/TIE.2017.2774777 doi: 10.1109/TIE.2017.2774777
[47]	S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, in International Conference on Machine Learning, (2015), 448–456. https://doi.org/10.48550/arXiv.1502.03167

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)