EUVIMEDEUVIMED entdecken
Crossref

Adapted Oversampling-based Multi-layer Support Vector Machines for interpretable multi-class imbalance fault diagnosis

Tao Chen, Yage Yuan, Jianan Wei, Haisong Huang, Jinxing Wu, Changcheng Wu

ISA Transactions · 2026-09 · 176 · 190-209

DOI: 10.1016/j.isatra.2026.06.035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2026-09. Verfasst von Tao Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China. Electronic address: g…. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In engineering practice, intelligent fault diagnosis for high-end equipment often involves small-sample, multi-class imbalanced data with noise and complex intra- and inter-class distributions. Existing sampling methods may generate low-quality samples, amplify noise, and depend heavily on hyperparameters. To address these issues, this paper proposes an interpretable fault diagnosis framework, termed Adapted Oversampling-based Multi-layer Support Vector Machines (AM-SVMs). The framework embeds a Multi-mechanism Adaptive Oversampling Technique (MAOTE) into a multi-layer LSSVM architecture. MAOTE adaptively determines sampling strategies according to data characteristics and employs a Newton-Raphson-inspired evolutionary mechanism to search for high-quality candidate solutions guided by multi-class classification performance. The optimized solutions are reorganized into diverse and representative fault samples, and a classifier-feedback-based evaluation mechanism improves distributional consistency and interpretability between generated and real samples. Finally, balanced feature samples are used to train a multi-class LSSVM classifier, yielding a robust and generalizable diagnostic model. Experiments on public bearing datasets and self-collected data show that AM-SVMs outperforms ten data augmentation methods and eight multi-class classifiers in diagnostic accuracy and robustness, demonstrating its effectiveness for imbalanced fault diagnosis in intelligent manufacturing.

Schlagwörter

Stichwörter der Autor:innen

Adaptive oversamplingFault diagnosisMulti-class imbalancedMulti-layer classifier

Autor:innen und Institutionen

  • Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China. Electronic address: gs.chent23@gzu.edu.cn.
  • Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China. Electronic address: gs.ygyuan22@gzu.edu.cn.
  • Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China; Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; Guiyang Xianfe…
  • Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China. Electronic address: hshuang@gzu.edu.cn.
  • School of Physics and Mechatronic Engineering, Guizhou Minzu University, Guiyang, Guizhou 550025, China. Electronic address: wjxwoo@gzmu.edu.cn.
  • Guiyang Xianfeng Machine Tool Co., Ltd, Guiyang, Guizhou 550025, China. Electronic address: wcc@gzmu.edu.cn.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Chen, T., Yuan, Y., Wei, J., Huang, H., Wu, J., & Wu, C. (2026). Adapted Oversampling-based Multi-layer Support Vector Machines for interpretable multi-class imbalance fault diagnosis. ISA Transactions, 176, 190-209. https://doi.org/10.1016/j.isatra.2026.06.035

Vancouver

Chen T, Yuan Y, Wei J, Huang H, Wu J, Wu C. Adapted Oversampling-based Multi-layer Support Vector Machines for interpretable multi-class imbalance fault diagnosis. ISA Transactions. 2026;176:190-209. doi:10.1016/j.isatra.2026.06.035

BibTeX
@article{Chen2026,
  author = {Chen, Tao and Yuan, Yage and Wei, Jianan and Huang, Haisong and Wu, Jinxing and Wu, Changcheng},
  title = {Adapted Oversampling-based Multi-layer Support Vector Machines for interpretable multi-class imbalance fault diagnosis},
  journal = {ISA Transactions},
  year = {2026},
  volume = {176},
  pages = {190--209},
  doi = {10.1016/j.isatra.2026.06.035}
}
Kostenlos starten →