Abstract
Wavelet transform is an adaptive signal decomposition method. It inherits the respective advantages of wavelet analysis. It separates the different modalities by extracting the maximum points in the frequency domain and then adaptively divides the Fourier spectrum in the frequency domain. The bandpass filter bank is adaptively constructed to construct an orthogonal wavelet function. In this paper, the method is applied to mechanical fault diagnosis, and a mechanical fault diagnosis method based on wavelet transform is proposed. This method overcomes the shortcomings of non-stationary and nonlinear signals by using meaningless harmonic components in conventional methods. It has good time–frequency focusing characteristics and is especially suitable for analyzing nonlinear and non-stationary signals. The simulation results show that the empirical wavelet transform method is obviously superior to the BP method and can effectively decompose the natural mode of the signal. This method is less decomposed than BP and is theoretically easy to understand. Finally, the method is applied to the fault diagnosis of rotor rubbing. The experimental results further verify the effectiveness of the proposed method, which can effectively reveal the frequency structure of the friction fault data and distinguish the severity of the friction fault.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Qu, J., Z. Zhang, and T. Gong. 2016. A novel intelligent method for mechanical fault diagnosis based on dual-tree complex wavelet packet transform and multiple classifier fusion. Neurocomputing 171(C): 837–853.
He, S., Y. Liu, J. Chen, and Y. Zi. 2016. Wavelet transform based on inner product for fault diagnosis of rotating machinery. Mechanical Systems & Signal Processing 70 (2016): 1–35.
Chen, R.X., X. Huang, L.X. Yang, B.P. Tang, and J. Zhou. 2018. Rolling bearing fault identification based on convolution neural network and discrete wavelet transform. Zhendong Gongcheng Xuebao/Journal of Vibration Engineering 31 (5): 883–891.
Wei, Z., Y. Wang, S. He, and J. Bao. 2017. A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection. Knowledge-Based Systems 116(C): 1–12.
Nantian, H., F. Lihua, C. Guowei, X. Dianguo, C. Huai**, and N. Yonghui. 2016. Mechanical fault diagnosis of high voltage circuit breakers with unknown fault type using hybrid classifier based on lmd and time segmentation energy entropy. Entropy 18 (9): 322.
Li, Y., X. Liang, M. Xu, and W. Huang. 2017. Early fault feature extraction of rolling bearing based on icd and tunable q-factor wavelet transform. Mechanical Systems and Signal Processing 86: 204–223.
Chen, X., G. Cheng, H. Li, and Y. Li. 2017. Fault identification method for planetary gear based on dt-cwt threshold denoising and le. Journal of Mechanical Science and Technology 31 (3): 1035–1047.
Talhaoui, H., A. Menacer, A. Kessal, and A. Tarek. 2018. Experimental diagnosis of broken rotor bars fault in induction machine based on hilbert and discrete wavelet transforms. International Journal of Advanced Manufacturing Technology 95 (1–4): 1399–1408.
Zhao, H., W. Deng, G. Li, L. Yin, and B. Yang. 2017. Research on a new fault diagnosis method based on wt, improved pso and svm for motor. Recent Patents on Mechanical Engineering 9 (4): 289–298.
Sheng, G., Y. Tao, G. Wei, and Z. Chen. 2018. A novel fault diagnosis method for rotating machinery based on a convolutional neural network. Sensors 18 (5): 1429.
Deng, F., and G. Tang. 2017. An intelligent method for rolling element bearing fault diagnosis based on time-wavelet energy spectrum sample entropy. Zhendong Yu Chongji/Journal of Vibration and Shock 36 (9): 28–34.
Guiji, T., W. **aolong, and H. Yuling. 2016. A novel method of fault diagnosis for rolling bearing based on dual tree complex wavelet packet transform and improved multiscale permutation entropy. Mathematical Problems in Engineering 2016: 1–13.
Ke, L., Z. Qiuju, W. Kun, C. Peng, and W. Huaqing. 2016. Intelligent condition diagnosis method based on adaptive statistic test filter and diagnostic bayesian network. Sensors 16 (1): 76.
He, S., J. Chen, Z. Zhou, Y. Zi, Y. Wang, and X. Wang. 2016. Multifractal entropy based adaptive multiwavelet construction and its application for mechanical compound-fault diagnosis. Mechanical Systems and Signal Processing 76–77: 742–758.
**ngmeng, J., W. Li, and G. Mingtao. 2017. A novel faults diagnosis method for rolling element bearings based on ewt and ambiguity correlation classifiers. Entropy 19 (5): 231.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, D. (2021). Intelligent Fault Diagnosis Method of Mechanical Fault Based on Wavelet Transform. In: Chang, JW., Yen, N., Hung, J.C. (eds) Frontier Computing. FC 2020. Lecture Notes in Electrical Engineering, vol 747. Springer, Singapore. https://doi.org/10.1007/978-981-16-0115-6_229
Download citation
DOI: https://doi.org/10.1007/978-981-16-0115-6_229
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0114-9
Online ISBN: 978-981-16-0115-6
eBook Packages: Computer ScienceComputer Science (R0)