Abstract
Deep learning and neural network have great advantages in the field of mechanical fault diagnosis. Mechanical fault diagnosis is stepping into the era of big data and artificial intelligence. CNN (Convolutional Neural Network) is popular in fault pattern recognition due to its powerful nonlinear mapping and feature learning ability, and the signal features extracted by the first layer of CNN influence the performance of the entire network. Therefore, a new one-dimensional convolutional neural network (SGWnet) is proposed in this paper. The first layer of SGWnet is the second-generation wavelet convolution in signal processing, which greatly increases the feature extraction ability of the neural network for the original signal. The interpretability of the second generation wavelet layer in SGWnet is explored in this paper. Meanwhile, CWRU bearing fault data is used to validated the effectiveness of the 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
Similar content being viewed by others
References
Bruin, T., Verbert, K., Babuka, R.: Railway track circuit fault diagnosis using recurrent neural networks. IEEE Trans. Neural Netw. Learsn. Syst. 28(3), 523–533 (2016)
Zhang, Y., Zhou, T., Huang, X., et al.: Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement 171, 108774 (2020)
Cao, J., He, Z., Wang, J., et al.: An antinoise fault diagnosis method based on multiscale 1DCNN. Shock Vib. 7, 1–10 (2020)
Zhang, W., Peng, G., Li, C., et al.: A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors 17(3), 425 (2017)
Chen, C., Liu, Z., Yang, G., et.al.: An improved fault diagnosis using 1D-convolutional neural network model. Electronics 10, 1–59 (2021)
Alekseev, A., Bobe, A.: GaborNet: gabor filters with learnable parameters in deep convolutional neural network. Artificial Neural Networks (2019)
Grezmak, J., Wang, P., Sun, C., et.al.: Explainable convolutional neural network for gearbox fault diagnosis. In: Procedia CIRP, pp. 476–481(2019)
Li, T., et al.: WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis (2019)
Claypoole, R.L., Baraniuk, R.G., Nowak, R.D.: Adaptive wavelet transforms via lifting. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp, 1513–1516 (1998)
Jawerth, B., Sweldens, W.: An overview of wavelet based multiresulotion analysis (1994)
Case Western Reserve University. Bearing Data Center [M/OL]. http://csegroupscaseedu/bearingdatacenter/
Acknowledgements
This research is sponsored by National Natural Science Foundations of China (No. 51975377 and 52005335), Shanghai Sailing Program (No. 18YF1417800) and Shanghai Aerospace Science and Technology Innovation Fund (SAST2019-100). The work is also partly supported by the Shanghai Special Funds for Industrial Transformation, Upgrading and Development (No. GYQJ-2019-1-03), and Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education, Northeastern University (VCAME201907). (Corresponding author: Jing Yuan.)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yuan, J., Cao, S., Ren, G., Jiang, H., Zhao, Q. (2021). SGWnet: An Interpretable Convolutional Neural Network for Mechanical Fault Intelligent Diagnosis. In: Zhang, H., Yang, Z., Zhang, Z., Wu, Z., Hao, T. (eds) Neural Computing for Advanced Applications. NCAA 2021. Communications in Computer and Information Science, vol 1449. Springer, Singapore. https://doi.org/10.1007/978-981-16-5188-5_26
Download citation
DOI: https://doi.org/10.1007/978-981-16-5188-5_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5187-8
Online ISBN: 978-981-16-5188-5
eBook Packages: Computer ScienceComputer Science (R0)