Просмотр новости
Найдите то, что Вас интересует
Спутники
РН
SpaceX
Роскосмос
NASA
СпутникиРНSpaceXРоскосмосNASAAiming at the difficult problem of fault feature extraction for rolling bearings, a fault feature extraction method is proposed by comprehensively applying singular value decomposition (SVD), dung beetle optimisation algorithm (DBO) and variational modal decomposition (VMD). Firstly, the vibration signal is reconstructed into a matrix, and the SVD noise reduction order is set through the difference spectrum to complete the vibration signal preprocessing; secondly, the VMD parameters are optimised using the DBO, and the optimal modal number K decomposition signals are selected to obtain the IMFs components; lastly, the IMF components, which contain rich and sensitive fault information, are subjected to the Hilbert envelope spectral analysis in order to achieve the effective extraction of the fault frequencies. The results verified by the experimental dataset show that this method can more accurately extract the rolling bearing periodic collision features and identify the fault types, providing an effective means for the rolling bearing fault feature extraction method.
Aiming at the difficult problem of fault feature extraction for rolling bearings, a fault feature extraction method is proposed by comprehensively applying singular value decomposition (SVD), dung beetle optimisation algorithm (DBO) and variational modal decomposition (VMD). Firstly, the vibration signal is reconstructed into a matrix, and the SVD noise reduction order is set through the difference spectrum to complete the vibration signal preprocessing; secondly, the VMD parameters are optimised using the DBO, and the optimal modal number K decomposition signals are selected to obtain the IMFs components; lastly, the IMF components, which contain rich and sensitive fault information, are subjected to the Hilbert envelope spectral analysis in order to achieve the effective extraction of the fault frequencies. The results verified by the experimental dataset show that this method can more accurately extract the rolling bearing periodic collision features and identify the fault types, providing an effective means for the rolling bearing fault feature extraction method.
Feng, Z., Liu, L., Zhang, W., et al.: Fault diagnosis of rolling element bearings based on wavelet time-frequency frame decomposition. J. Vibr. Shock 27(2), 110–114 (2008)
Zhang, C., Zhao, R., Deng, L., et al.: Weak fault feature extraction method for rolling bearings based on SVD EEMD and TEO energy spectrum. J. Vibr. Meas. Diagn. 39(4), 720–726 (2019)
Zhao, S., Ma, L., Xu, L., Liu, M., Chen, X.: A study of fault signal noise reduction based on improved CEEMDAN-SVD. Appl. Sci. 13(19), 10713 (2023)
Wang, Q., Wang, L., Yu, H., Wang, D., Nandi, A.K.: Utilizing SVD and VMD for denoising non-stationary signals of roller bearings. Sensors 22(1), 195 (2022)
Dragomiretskiy, K., Zosso, D.: Variational mode decomposition. IEEE Trans. Signal Process. 62(3), 531–544 (2014)
Zhou, J., Xiao, M., Niu, Y., Ji, G.: Rolling bearing fault diagnosis based on WGWOA-VMD-SVM. Sensors 22, 6281 (2022)
Xue, J., Shen, B.: Dung Beetle Optimizer: a new meta-heuristic algorithm for global optimization. J. Supercomput., 1–32 (2022)
Campus of Urumqi, Engineering University of PAP, Urumqi, China
Chen Zhang & Luyan Xu
Authors
Correspondence to Chen Zhang.
School of Mechanical Engineering, Zhejiang University, Hangzhou, Zhejiang, China
Jianrong Tan
School of Mechanical Engineering, Zhejiang University, Hangzhou, Zhejiang, China
Zhenyu Liu
Mechanical Engineering, Zhejiang University, Hangzhou, Zhejiang, China
Weifei Hu
© 2027 The Chinese Mechanical Engineering Society
Zhang, C., Xu, L. (2027). Research on Fault Feature Extraction Method for Rolling Bearing Based on SVD-DBO-VMD. In: Tan, J., Liu, Z., Hu, W. (eds) Advances in Mechanical Design. ICMD 2025. Mechanisms and Machine Science, vol 206. Springer, Singapore. https://doi.org/10.1007/978-981-95-7904-4_16
Download citationDOI: https://doi.org/10.1007/978-981-95-7904-4_16
Published: 25 June 2026
Publisher Name: Springer, Singapore
Print ISBN: 978-981-95-7903-7
Online ISBN: 978-981-95-7904-4
eBook Packages: Mechanical Engineering (R0)Springer Nature Proceedings excluding Computer Science