Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Electronics and Information Science
  4. Vol 9, Issue 3, 2024

Multi-scale Adaptive Fusion for Rolling Bearing Fault Diagnosis

Download as PDF

DOI: 10.23977/jeis.2024.090309 | Downloads: 17 | Views: 491

Author(s)

Ke Xu 1, Yongyong Hui 1,2

Affiliation(s)

1 College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou, 730050, China
2 National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou, 730050, China

Corresponding Author

Yongyong Hui

ABSTRACT

In order to fully extract the bearing fault feature information under strong noise and variable load, a rolling bearing fault diagnosis method based on multi-scale adaptive fusion (MSAF) is proposed. Firstly, a multi-scale feature extraction module is designed, which uses convolutional layers of different scales to extract feature information, in order to better capture the characteristics of different fault signals. Secondly, a Self-Calibrated Convolution (SCC) module is constructed. This module automatically adjusts the weights of the convolutional kernels according to the characteristics of the input data, which enhances the network's perception of the input data. Thirdly, a lightweight channel attention residual module is established, which combines channel attention and residual connections, allowing the network to automatically select channels related to fault features, thereby reducing information redundancy. Finally, the Softmax probability distribution function is used as a classifier to achieve bearing fault classification. By using the bearing data set of CWRU for experiment and comparison, it is verified that the method still has strong fault diagnosis performance under variable load and variable noise.

KEYWORDS

Rolling bearing, Fault diagnosis, Self-correcting convolution, Convolutional neural network, Attention mechanism

CITE THIS PAPER

Ke Xu, Yongyong Hui, Multi-scale Adaptive Fusion for Rolling Bearing Fault Diagnosis. Journal of Electronics and Information Science (2024) Vol. 9: 54-61. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2024.090309.

REFERENCES

[1] Ni Q, Ji J C, Halkon B, et al. Physics-Informed Residual Network (PIResNet) for rolling element bearing fault diagnostics[J]. Mechanical Systems and Signal Processing, 2023, 200: 110544. 
[2] Khan M A, Asad B, Kudelina K, et al. The Bearing Faults Detection Methods for Electrical Machines—The State of the Art [J]. Energies, 2022, 16(1): 296.
[3] Fu W, Jiang X, Li B, et al. Rolling bearing fault diagnosis based on 2D time-frequency images and data augmentation technique [J]. Measurement Science and Technology, 2023, 34(4): 045005.
[4] Liu W, Zhang Z, Zhang J, et al. A novel fault diagnosis method of rolling bearings combining convolutional neural network and transformer [J]. Electronics, 2023, 12(8): 1838. 
[5] Zhou Jianmin, Li Hui, Zhang Long, et al. Evaluation of bearing performance degradation based on EMD and logistic regression[J]. Mechanical Design and Research, 2016, 32(5): 72-75.
[6] Xu Ke, Chen Zonghai, Zhang Chenbin, et al. Fault Diagnosis of Rolling Bearings Based on Empirical Mode Decomposition and Support Vector Machine[J]. Control Theory & Applications, 2019, 36(6): 915-922.
[7] Zhang Xining, Zhang Wenwen, Zhou Rongtong, et al. Bearing Fault Diagnosis Method Based on Multi-dimensional Scale and Random Forest[J]. Journal of Xi'an Jiaotong University, 2019, 53(8): 1-7.
[8] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786): 504-507.
[9] Jia F, Lei Y, Lu N, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing, 2018, 110: 349-367.
[10] Zhou Xiangyu, Mao Shanjun, Li Mei. Bearing Fault Diagnosis Method Based on Frequency Domain Downsampling and CNN[J]. Journal of Peking University (Natural Science), 2023, 59(2): 251-260.
[11] Gan M, Wang C. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2016, 72: 92-104.
[12] 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[J]. Sensors, 2017, 17(2): 425.
[13] Qu Jianling, Yu Lu, Yuan Tao, et al. Adaptive Fault Diagnosis Algorithm for Rolling Bearings Based on One-dimensional Convolutional Neural Network[J]. Chinese Journal of Scientific Instrument, 2018, 39(7): 134-143.
[14] Tang Bo, Chen Shenshen. Bearing fault diagnosis method based on deep convolutional neural network[J]. Journal of Electronic Measurement and Instrumentation, 2020, 32(3): 88-93.
[15] YE Zhuang, YU Jianbo. Gearbox Vibration Signal Feature Extraction Based on Multi-channel Weighted Convolutional Neural Network[J]. Journal of Mechanical Engineering, 2021, 57(1): 110-120.
[16] Liang M, Cao P, Tang J. Rolling bearing fault diagnosis based on feature fusion with parallel convolutional neural network[J]. The International Journal of Advanced Manufacturing Technology, 2021, 112: 819-831.
[17] LI Yandong, HAO Zongbo, LEI Hang. A Review of Convolutional Neural Networks[J]. Journal of Computer Applications, 2016, 36(9): 2508-2515.
[18] Kang Tao, Duan Rongkai, Yang Lei. Bearing Fault Diagnosis Method of Convolutional Neural Network Integrating Multi-attention Mechanism[J]. Journal of Xi'an Jiaotong University, 2022, 56(12): 68-77.
[19] Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 11534-11542.
[20] Liu J J, Hou Q, Cheng M M, et al. Improving convolutional networks with self-calibrated convolutions[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10096-10105.
[21] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. Mechanical systems and signal processing, 2015, 64: 100-131.
[22] Zhao Xiaoqiang, Liang Haopeng. Fault Diagnosis Method for Variable Working Conditions of Rolling Bearings Based on Improved Residual Neural Network [J]. Journal of Xi'an Jiaotong University, 2020, 54(9). 23-31.
[23] He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. Springer International Publishing, 2016: 630-645.
[24] Zhao Xiaoqiang, Luo Weilan.Bearing fault diagnosis method for improved convolutional Lenet-5 neural network [J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(06):113-125.
[25] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. 
[26] Abdeljaber O, Avci O, Kiranyaz S, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks[J]. Journal of Sound and Vibration, 2017, 388: 154-170.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 11052
Visits: 383081

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.