Bearing fault diagnosis based on cross image multi-attention mechanism.

Journal: Scientific reports
Published Date: Jul 1, 2025

Abstract

Bearings are crucial components of rotating machinery, and fault diagnosis is essential for ensuring the safe operation of mechanical systems. Neural networks, commonly used in bearing fault diagnosis, are effective in extracting deep features from fault signals but often fail to emphasize critical information. We propose a fault diagnosis method that integrates a cross-image multi-attention mechanism with a residual neural network. The collected vibration signals are first preprocessed using VMD-GAF and then fed into the network for fault detection. The results demonstrate that the CIMAM-ResNet18 model significantly enhances the robustness of signal processing, achieving an accuracy of 98.00% when tested on the experimental platform.

Authors

  • Yupeng Liu
    School of Electrical and Mechanical Engineering, Jilin University of Architecture and Technology, Changchun, 130114, China. 1589356167@qq.com.
  • Weinan Zheng
    School of Electrical and Mechanical Engineering, Jilin University of Architecture and Technology, Changchun, 130114, China.
  • Ying Du
    School of Electrical and Mechanical Engineering, Jilin University of Architecture and Technology, Changchun, 130114, China.
  • Yuehui Wang
    School of Electrical and Mechanical Engineering, Jilin University of Architecture and Technology, Changchun, 130114, China.
  • Jian Jin
    Department of Agricultural and Biological Engineering, Purdue University, 225 S. University St., West Lafayette, IN 47907, USA.
  • Miao Yu
    Key Laboratory of Bioactive Substances and Resource Utilization of Chinese Herbal Medicine, Ministry of Education, China Institute of Medicinal Plant Development, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, 100193, China; School of Chinese Materia Medica, Guangdong Pharmaceutical University, Guangzhou, 510006, China; Faculty of Arts and Sciences, Beijing Normal University, Zhuhai, 519087, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals