A Classification Method for Bearing Surface Defects Based on Acoustic Emission Technology and the YOLO-V11 Algorithm

Abstract

This paper proposes a bearing surface defect classification method based on acoustic emission signal analysis and the YOLO-V11 algorithm. The proposed framework combines non-stationary acoustic emission features with deep-learning-based defect recognition to improve classification accuracy and robustness in industrial fault diagnosis applications.

Key Contributions

• Developed an acoustic-emission-based bearing defect classification framework
• Applied YOLO-V11 to industrial defect recognition tasks
• Improved defect classification robustness under non-stationary conditions
• Demonstrated feasibility for intelligent equipment health monitoring

@article{guo2025bearing,
  author    = {Xin-Yu Guo and Liu-Yi Yu and Yi Chen and Yan-Zuo Chang},
  title     = {A Classification Method for Bearing Surface Defects Based on Acoustic Emission Technology and the YOLO-V11 Algorithm},
  journal   = {International Journal of Advanced Engineering Research and Science},
  volume    = {12},
  number    = {12},
  pages     = {48--53},
  year      = {2025},
  doi       = {10.22161/ijaers.1212.4},
  keywords  = {Bearing Defect, Acoustic Emission, YOLO-V11, Fault Diagnosis}
}

Recommended citation: Xin-Yu Guo, Liu-Yi Yu, Yi Chen, and Yan-Zuo Chang, “A Classification Method for Bearing Surface Defects Based on Acoustic Emission Technology and the YOLO-V11 Algorithm,” International Journal of Advanced Engineering Research and Science, vol. 12, no. 12, pp. 48-53, 2025.
Download Paper