EUVIMEDEUVIMED entdecken
Crossref

Robustness enhanced fault diagnosis for rotating machinery heterogeneous modality interactive transformer

Lin Zhu, Jianxin Wu, Lintong Liu, Jin Wang, Min Chen

Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science · 2026-09 · 240 (17) · 6328-6347

DOI: 10.1177/09544062261446736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, online erschienen am 06.05.2026. Verfasst von Lin Zhu und 4 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangsu Province Youth Science and Technology Talent Support Project, Yangzhou Science and Technology Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault diagnosis in rotating machinery is critical for industrial safety, yet existing methods struggle with noise interference and unimodal feature limitations. A Heterogeneous Modal Interaction Transformer (HMIT) integrates time-series, time-frequency, and spatial features via a sparse transformer, enabling cross-modal fusion. This method adaptively tunes complex fault signals and provides robust feature inputs for diagnostic models. Additionally, recognizing that unimodal feature data cannot fully capture the health status of mechanical equipment, this study performs modal feature expansion based on time-series signals. A complementary feature set is constructed by integrating time-domain signals, time-frequency energy spectra, and relative position matrices. To enable deep fusion of these heterogeneous modalities, the HMIT framework is proposed and optimized across key stages, including feature encoding, multimodal fusion, and global correlation modeling. Case studies on both public and in-house datasets validate the effectiveness of HMIT. Results show that the method maintains high accuracy and robustness, even under strong noise and complex fault scenarios. Specifically, experiments on the YZU and SEU datasets reveal a 6.86% improvement in accuracy at an SNR of −9 dB, outperforming conventional models.

Förderung

  • National Natural Science Foundation of China
  • Jiangsu Province Youth Science and Technology Talent Support Project
  • Yangzhou Science and Technology Plan
  • yangzhou university
  • Innovation and Promotion Project of Forestry Science and Technology for Jiangsu Province

Zitieren

APA

Zhu, L., Wu, J., Liu, L., Wang, J., & Chen, M. (2026). Robustness enhanced fault diagnosis for rotating machinery heterogeneous modality interactive transformer. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 240(17), 6328-6347. https://doi.org/10.1177/09544062261446736

Vancouver

Zhu L, Wu J, Liu L, Wang J, Chen M. Robustness enhanced fault diagnosis for rotating machinery heterogeneous modality interactive transformer. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. 2026;240(17):6328-6347. doi:10.1177/09544062261446736

BibTeX
@article{Zhu2026,
  author = {Zhu, Lin and Wu, Jianxin and Liu, Lintong and Wang, Jin and Chen, Min},
  title = {Robustness enhanced fault diagnosis for rotating machinery heterogeneous modality interactive transformer},
  journal = {Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science},
  year = {2026},
  volume = {240},
  number = {17},
  pages = {6328--6347},
  doi = {10.1177/09544062261446736}
}
Kostenlos starten →