Abstract
Rotating components of mechanical drive systems usually work in harsh environments, and the collected vibration signals are immensely affected by strong noise, which poses a great challenge for fault diagnosis. Intelligent fault diagnosis techniques have been widely used in the field of mechanical fault diagnosis, but the denoising process and diagnosis process of most intelligent schemes are independent of each other, ignoring the synergy of both. In this paper, a parallel learning attention-guided convolutional neural network (PLA-CNN) combining noise reduction and fault diagnosis for mechanical fault detection is presented, which can realize the cooperation and mutual learning between networks for improving the ability of deep learning. The PLA-CNN consists of a global feature sharing network and two special task networks with feature attention modules. The performance of the proposed network is evaluated using datasets of gear and bearing defects. The results show that the signal denoising network can improve the signal-to-noise ratio of the input signal, and the fault diagnosis network can improve the fault identification accuracy with the assistance of the former. The method has a better performance compared with traditional intelligent fault diagnosis methods.
Similar content being viewed by others
References
Ayas S, Ayas MS (2022) A novel bearing fault diagnosis method using deep residual learning network. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-11617-1
Qiao M, Tang X, Liu Y et al (2021) Fault diagnosis method of rolling bearings based on VMD and MDSVM. Multimed Tools Appl 80:14521–14544
Singh SK, Kumar S, Dwivedi JP (2017) Compound fault prediction of rolling bearing using multimedia data. Multimed Tools Appl 76:18771–18788
Kim S, Choi J (2018) Convolutional neural network for gear fault diagnosis based on signal segmentation approach. Struct Health Monit 18(5):1401–1415
Saidi L, Ali JB, Fnaiech F (2014) Bi-spectrum based-EMD applied to the non-stationary vibration signals for bearing faults diagnosis. ISA Trans 53:1650–1660
Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 1:1–41
Dibaj A, Ettefagh MM, Hassannejad R, Ehghaghi MB (2019) Fine-tuned variational mode decomposition for fault diagnosis of rotary machinery. Struct Health Monit 19(5):1453–1470
Chen J, Li Z, Pan J, Chen G, Zi Y, Yuan J (2016) Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review. Mech Syst Sig Process 70:1–35
Zhang M, Jiang Z, Feng K (2017) Research on variational mode decomposition in rolling bearings fault diagnosis of the multistage centrifugal pump. Mech Syst Sig Process 93:460–493
Antoni J (2007) Fast computation of the kurtogram for the detection of transient faults. Mech Syst Signal Process 21:108–124
Zhong X, Gao X, Mei Q, Huang T, Zhao X (2021) Fault feature extraction method of gear based on optimized minimum entropy deconvolution and accugram. J Intell Fuzzy Syst 40(6):12265–12282
Zhang X, Miao Q, Zhang H, Wang L (2018) A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery. Mech Syst Signal Process 108:58–72
Toma RN, Prosvirin AE, Kim JM (2020) Bearing fault diagnosis of induction motors using a genetic algorithm and machine learning classifiers. Robot Mach Learn 20:1884
Amin K, Mohammad K, Mansoor R (2021) End-to-end CNN + LSTM deep learning approach for bearing fault diagnosis. Appl Intell 51:736–751
Huang X, Wang X, Wu H (2020) A novel fault diagnosis procedure based on improved symplectic geometry mode decomposition and optimized SVM. Measurement 173:108644
Yang Y, Jiang D (2017) Casing vibration fault diagnosis based on variational mode decomposition, local linear embedding, and support vector machine. Shock Vib 1971:1–14
Jung U, Koh BH (2015) Wavelet energy-based visualization and classification of high-dimensional signal for bearing fault detection. Knowl Inf Syst 44:197–215
Zhao X, Jia M, Lin M (2020) Deep laplacian auto-encoder and its application into imbalanced fault diagnosis of rotating machinery. Measurement 152:107320
Li Z, Wang Y, Wang K (2019) A deep learning driven method for fault classification and degradation assessment in mechanical equipment. Comput Ind 104:1–10
Pinedo-Sánchez LA, Mercado-Ravell DA, Carballo-Monsivais CA (2022) Vibration analysis in bearings for failure prevention using CNN. J Braz Soc Mech Sci 42:628
Han T, Tian Z, Yin Z, Tan AC (2020) Bearing fault identifcation based on convolutional neural network by different input modes. J Braz Soc Mech Sci 42:474
Feng F, Wu C, Zhu J, Wu S, Tian Q, Jiang P et al (2020) Research on multitask fault diagnosis and weight visualization of rotating machinery based on convolutional neural network. J Braz Soc Mech Sci 42:603
Hoang DT, Kang HJ (2020) A motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Trans Instrum Meas 69(6):3325–3333
Gao Y, Gong P, Li L (2018) An end-to-end model based on CNN-LSTM for industrial fault diagnosis and prognosis. IC-NIDC. https://doi.org/10.1109/ICNIDC.2018.8525759
Wang X, Mao D, Li X (2018) Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement 173(6):108518
Cheng Y, Lin M, Wu J, Zhu H, Shao X (2021) Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowl-Based Syst 216:106796
Liang P, Deng C, Wu J, Yang Z (2020) Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network. Measurement 159(15):107768
Wang H, Liu Z, Peng D, Yang M, Qin Y (2021) Feature-level attention-guided multitask CNN for fault diagnosis and working conditions identification of rolling bearing. IEEE Trans Neural Netw Learn Syst 99:1–13
Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023
Woo S, Park J, Lee JY, Kweon IS (2018) CBAM: Convolutional block attention module. ECCV, pp. 3–19
Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. ICML
Zhu Y, Li G, Wang R, Tang S, Su H, Cao K (2021) Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization. Appl Acoust 183:108336
Lu T, Yu F, Han B, Wang J (2020) A generic intelligent bearing fault diagnosis system using convolutional neural Networks with transfer learning. IEEE Access 8:164807–164814. https://doi.org/10.1109/ACCESS.2020.3022840
Acknowledgements
The authors would like to thank the reviewers for the careful reading and constructive feedback on the material presented in this article.
Funding
This work is supported by the Science Foundation of Hubei Key Laboratory of hydropower equipment design and maintenance (No. 2020KJX11).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
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 (e.g. a society or other partner) 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
Zhong, X., Li, Y. & Xia, T. Parallel learning attention-guided CNN for signal denoising and mechanical fault diagnosis. J Braz. Soc. Mech. Sci. Eng. 45, 239 (2023). https://doi.org/10.1007/s40430-023-04139-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-023-04139-4