Abstract
Fault diagnosis of rolling bearings is crucial in areas related to rotating machinery and equipment applications. If faults are detected in time at an early stage, it can guarantee the safe and effective operation of the equipment, saving valuable time and high maintenance costs. Traditional fault diagnosis techniques have achieved remarkable results in rolling bearing fault detection, but they rely heavily on expert knowledge to extract fault features. Manual extraction of features in the face of massive industrial data exhibits poor timeliness. In recent years, with the development and wide application of deep learning, data-driven mechanical fault diagnosis methods are becoming a hot topic of discussion among related researchers. Among them, Convolutional Neural Network (CNN) is an effective deep learning method. In this study, a new method of multiscale redundant second generation wavelet kernel-driven convolutional neural network for rolling bearing fault diagnosis is proposed, called RW-Net. By performing two layers of redundant second generation wavelet decomposition on the input time-domain signal in the shallow layer of the network, the network can automatically extract fault features with rich information. The proposed method is validated by Case Western Reserve University (CWRU) bearing test data, and the average fault identification accuracy is 99.4%, which verifies the feasibility and effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, Z., Lei, Z., Huang, X., et al.: A multisource dense adaptation adversarial network for fault diagnosis of machinery. IEEE Trans. Ind. Electron. 69(6), 6298–6307 (2021)
Jiang, Y., Yin, S.: Recursive total principle component regression based fault detection and its application to vehicular cyber-physical systems. IEEE Trans. Ind. Inf. 14(4), 1415–1423 (2017)
Yuan, J., Cao, S., Ren, G., et al.: LW-Net: an interpretable network with smart lifting wavelet kernel for mechanical feature extraction and fault diagnosis. Neural Comput. Appl. 34(18), 15661–15672 (2022)
Yuan, J., He, Z., Zi, Y., et al.: Adaptive multiwavelets via two-scale similarity transforms for rotating machinery fault diagnosis. Mech. Syst. Sig. Process. 23(5), 1490–1508 (2009)
Shao, H., Jiang, H., Zhang, H., et al.: Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing. Mech. Syst. Sig. Process. 100, 743–765 (2018)
Li, Z., Chen, J., Pan, J.: Independence-oriented VMD to identify fault feature for wheelset bearing fault diagnosis of high-speed locomotive. Mech. Syst. Sig. Process. 85, 512–529 (2016)
Chen, J., Li, Z., Chen, G., et al.: Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review. Mech. Syst. Sig. Process. 70, 1–35 (2016)
Ming, A., Qin, Z., Zhang, W., et al.: Spectrum auto-correlation analysis and its application to fault diagnosis of rolling element bearings. Mech. Syst. Sig. Process. 41(1–2), 141–154 (2013)
Wang, P., Song, L., Guo, X., et al.: A high-stability diagnosis model based on a multiscale feature fusion convolutional neural network. IEEE Trans. Instrum. Meas. 70, 1–9 (2021)
Lund, D., MacGillivray, C., Turner, V., et al.: Worldwide and regional internet of things (IoT) 2014–2020 forecast: a virtuous circle of proven value and demand. International Data Corporation (IDC), Technical Report, vol. 1, no. 1, p. 9 (2014)
Chen, Z., Li, W.: Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network. IEEE Trans. Instrum. Meas. 66(7), 1693–1702 (2017)
Duan, C., Li, L., He, Z.: Application of second generation wavelet transform to fault diagnosis of rotating machinery. Mech. Sci. Technol. 23(2), 224–226 (2004)
Duan, C., He, Z.: Second generation wavelet denoising and its application in machinery monitoring and diagnosis. Mini-Micro Syst. 25(7), 1341–1343 (2004)
Gao, L., Tang, W., et al.: Noise reduction technology based on redundant second generation wavelet. J. Beijing Univ. Technol. 34(12), 1233–1237 (2008)
Jiang, H., He, Z., Duan, C.: Construction of redundant second generation wavelet and mechanical signal feature extraction. J. Xi’an Jiaotong Univ. 38(11), 1140–1142 (2004)
Zhang, W.: Study on Bearing Fault Diagnosis Algorithm Based on Convolutional Neural Network. Harbin University of Science and Technology (2017)
Chen, X., Xiang, S., Liu, C., et al.: Vehicle detection in satellite images by hybrid deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 11(10), 1797–1801 (2014)
Claypoole, R.L., Baraniuk, R.G., et al.: Adaptive wavelet transforms via lifting. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 3, pp. 1513–1516 (1998)
Bearing Data Center, Case Western Reserve University, Cleve land, OH, USA (2004). http://csegroups.case.edu/bearing datacenter/home
Li, K.: School of Mechanical Engineering, Jiangnan University (2019)
Li, K., Ping, X., Wang, H., Chen, P., Cao, Y.: Sequential fuzzy diagnosis method for motor roller bearing in variable operating conditions based on vibration analysis. Sensors 13(6), 8013–8041 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Su, F., Cao, S., Hai, T., Yuan, J. (2023). Multiscale Redundant Second Generation Wavelet Kernel-Driven Convolutional Neural Network for Rolling Bearing Fault Diagnosis. In: Zhang, H., et al. International Conference on Neural Computing for Advanced Applications. NCAA 2023. Communications in Computer and Information Science, vol 1870. Springer, Singapore. https://doi.org/10.1007/978-981-99-5847-4_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-5847-4_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5846-7
Online ISBN: 978-981-99-5847-4
eBook Packages: Computer ScienceComputer Science (R0)