Abstract
Aiming at the problems of nonstationary, nonlinear, strong background noise interference and difficult feature extraction of rolling bearing vibration signal of road heading machine, a fault diagnosis method based on improved singular value decomposition, S-transform and improved convolutional neural network (ICNN) was proposed. First, the original signal is constructed into a Hankel matrix, and the singular value decomposition of the Hankel matrix is carried out. In this paper, the singular value curvature spectrum is used to select the effective singular value for signal reconstruction, the reconstructed signal is transformed by S transformation and time–frequency transformation, and the time–frequency features are extracted. Secondly, the improved convolutional neural network takes VGG16 as the bottleneck structure and introduces multi-scale feature extraction. It also adds fine tune based on ICNN and realizes fault classification and recognition through network parameter adjustment. The method is applied to the fault diagnosis of the rolling bearing of the road heading machine, and the accuracy rate reaches 98.2%, which is 9.55% higher than that of the classic VGG16 model.
Similar content being viewed by others
References
Morsali M, Frisk E, Aslund J (2020) Spatio-temporal planning in multi-vehicle scenarios for autonomous vehicle using support vector machines. IEEE Trans Intell Veh 6:611–621
Chen W, Lei X, Chakrabortty R et al (2021) Evaluation of different boosting ensemble machine learning models and novel deep learning and boosting framework for head-cut gully erosion susceptibility. J Environ Manag 284:112015
Xie W, Li Z, Xu Y et al (2022) Evaluation of different bearing fault classifiers in utilizing CNN feature extraction ability. Sens-Basel 22:3314
Lin SL (2021) Intelligent fault diagnosis and forecast of time-varying bearing based on deep learning VMD-DenseNet. Sens-Basel 21:7467
Zhou S, Qian S, Chang W et al (1934) A novel bearing multi-fault diagnosis approach based on weighted permutation entropy and an improved SVM ensemble classifier. Sens-Basel 2018:18
Wang ZJ, Yang NN, Li NP et al (2021) A new fault diagnosis method based on adaptive spectrum mode extraction. Struct Health Monit 20:3354–3370
Xu Y, Li ZX, Wang SQ et al (2021) A hybrid deep-learning model for fault diagnosis of rolling bearings. Measurement 169:108502
Tao HF, Wang P, Chen YY et al (2020) An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks. J Franklin I(357):7286–7307
Lin RY, Lin ZW, Jin YL (2021) Instantaneous frequency estimation for wheelset bearings weak fault signals using second-order synchrosqueezing S-transform with optimally weighted sliding window. Isa T 115:218–233
Li GQ, Deng C, Wu J et al (2019) Sensor data-driven bearing fault diagnosis based on deep convolutional neural networks and S-transform. Sens-Basel 19:2750
Li H, Tao L, Wu X et al (2020) A bearing fault diagnosis method based on enhanced singular value decomposition. IEEE T Ind Inform 17:3220–3230
Zhao HS, Zhang W, Wang GL et al (2019) Fault diagnosis method for wind turbine rolling bearings based on Hankel tensor decomposition. IET Renew Power Gen 13:220–226
Li H, Liu T, Wu X et al (2019) Research on bearing fault feature extraction based on singular value decomposition and optimized frequency band entropy. Mech Syst Signal Pr 118:477–502
Pham MT, Kim JM, Kim CH (2020) Deep learning-based bearing fault diagnosis method for embedded systems. Sensors-Basel 20:6886
Chen X, Wang Z, Zhang Z et al (2018) A semi-supervised approach to bearing fault diagnosis under variable conditions towards imbalanced unlabeled data. Sens-Basel 18:2097
Sun C, Yin HP, Liu YX et al (2020) A novel rolling bearing vibration impulsive signals detection approach based on dictionary learning. IEEE-Caa J Automatic 8:1188–1198
Xu G, Liu M, Jiang Z et al (2019) Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning. Sens-Basel 19:1088
Wu J, Tang T, Chen M et al (2018) Self-adaptive spectrum analysis based bearing fault diagnosis. Sensors-Basel 18:3312
Zhao DZ, Wang TY, Gao RX et al (2019) Signal optimization-based generalized demodulation transform for rolling bearing nonstationary fault characteristic extraction. Mech Syst Signal Pr 134:106297
Qin Y, Jin L, Zhang AB et al (2021) Rolling bearing fault diagnosis with adaptive harmonic kurtosis with improved bat algorithm. IEEE T Instrum Meas 70:3508112
Lin C, Cheng G, Chen XH et al (2018) Planetary gears feature extraction and fault diagnosis method based on VMD and CNN. Sens-Basel 18:1523
Li SB, Liu GK, Tang XH et al (2017) An ensemble deep convolutional neural network model with improved D-S evidence fusion for bearing fault diagnosis. Sens-Basel 17:1729
Xu ZF, Mei X, Wang XY et al (2022) Fault diagnosis of wind turbine bearing using a multi-scale convolutional neural network with bidirectional long short term memory and weighted majority voting for multi-sensors. Renew Energ 182:615–626
Yi CC, Qin JQ, Xiao H et al (2022) Second-order synchrosqueezing modified S transform for wind turbine fault diagnosis. Appl Acoust 189:108614
Zhou FN, Yang S, Fujita H et al (2020) Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowl-Based Syst 187:104837
Chen ZY, Mauricio A, Li WH et al (2020) A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks. Mech Syst Signal Pr 140:106683
Mao WT, Feng WS, Liu YM et al (2021) A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mech Syst Signal Pr 150:107233
Wu ZH, Jiang HK, Zhao K et al (2019) An adaptive deep transfer learning method for bearing fault diagnosis. Measurement 151:107227
Zhang Y, Xing KS, Bai RX et al (2020) An enhanced convolutional neural network for bearing fault diagnosis based on time-frequency image. Measurement 157:107667
Yuan HD, Wu NL, Chen XY et al (2021) Fault diagnosis of rolling bearing based on shift invariant sparse feature and optimized support vector machine. Machines 9:98
Liang K, Zhao M, Lin J, Jiao J (2020) An information-based K-singular-value decomposition method for rolling element bearing diagnosis. ISA Trans 1(96):444–456
Ji M, Peng G, He J et al (2021) A two-stage, intelligent bearing-fault-diagnosis method using order-tracking and a one-dimensional convolutional neural network with variable speeds. Sens-Basel 21:675
Zheng XX, Wei YB, Liu J et al (2021) Multi-synchrosqueezing S-transform for fault diagnosis in rolling bearings. Meas Sci Technol 32:025013
Guo S, Zhang B, Yang T et al (2020) Multitask convolutional neural network with information fusion for bearing fault diagnosis and localization. IEEE T Ind Electron 67:8005–8015
Wang H, Xu JW, Yan RQ et al (2020) A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE T Instrum Meas 69:2377–2389
Chen JB, Huang RY, Zhao K et al (2021) Multiscale convolutional neural network with feature alignment for bearing fault diagnosis. IEEE T Instrum Meas 70:3517010
Zhang FL, Yan JX, Fu PL et al (2020) Ensemble sparse supervised model for bearing fault diagnosis in smart manufacturing. Robot Cim-Int Manuf 65:101920
Yang JL, Yin SY, Chang YQ et al (2020) A fault diagnosis method of rotating machinery based on one-dimensional. Self-Normalizing Convol Neural Net Sens-Basel 20:3837
Yao DC, Liu HC, Yang JW et al (2021) Implementation of a novel algorithm of wheelset and axle box concurrent fault identification based on an efficient neural network with the attention mechanism. J Intell Manuf 32:729–743
Acknowledgements
This work was partly supported by the National Natural Science Foundation of China under Grant No. 51775117 and the Innovative Project of Foshan under Grant No. 2018IT100112.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author(s) declared no potential conflicts concerning this article's research, authorship and publication.
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
Qu, X., Zhang, Y. & Yin, L. Fault diagnosis for rolling bearing of road heading machine via SVDS-ICNN. J Braz. Soc. Mech. Sci. Eng. 45, 439 (2023). https://doi.org/10.1007/s40430-023-04344-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-023-04344-1