EUVIMEDEUVIMED entdecken
Crossref

Multi-modal fault diagnosis network based on MASDN for high-speed train wheelset bearings towards industrial variable speed conditions

Jingwen Liu, Zengqiang Ma

Measurement Science and Technology · 21.08.2026 · 37 (33) · 336107

DOI: 10.1088/1361-6501/ae87b7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 18.08.2026. Verfasst von Jingwen Liu und 1 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Major Project of National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenge of fault diagnosis from high-speed train wheelset bearings towards complex industrial variable speed conditions, we propose a Multi-modal Adaptive Signal Diagnosis Network (MASDN). Firstly, a hybrid architecture combining multi-scale convolution with Informer Encoders is designed to capture time-varying speed features, which dynamically guide vibration feature extraction through adaptive convolutional kernel weighting. Subsequently, combining parallel multi-scale convolutional module enhanced by channel attention mechanisms for robust vibration feature extraction across varying operational conditions. Meanwhile, an adaptive structure incorporating multi-domain constraint loss functions is designed for optimal signal enhancement and noise suppression. On this basis, a speed-guided feature fusion strategy, which automatically prioritizes the most condition-relevant features, is introduced, employing depthwise separable convolution (DSConv) to achieve cross-scale integration of multi-modal features. Experiments indicate that MASDN effectively improves diagnostic accuracy and robustness in scenarios simulating industrial variable speed conditions with ablation studies further validating the effectiveness of each component in the model.

Förderung

  • Major Project of National Natural Science Foundation of China

Zitieren

APA

Liu, J., & Ma, Z. (2026). Multi-modal fault diagnosis network based on MASDN for high-speed train wheelset bearings towards industrial variable speed conditions. Measurement Science and Technology, 37(33), 336107. https://doi.org/10.1088/1361-6501/ae87b7

Vancouver

Liu J, Ma Z. Multi-modal fault diagnosis network based on MASDN for high-speed train wheelset bearings towards industrial variable speed conditions. Measurement Science and Technology. 2026;37(33):336107. doi:10.1088/1361-6501/ae87b7

BibTeX
@article{Liu2026,
  author = {Liu, Jingwen and Ma, Zengqiang},
  title = {Multi-modal fault diagnosis network based on MASDN for high-speed train wheelset bearings towards industrial variable speed conditions},
  journal = {Measurement Science and Technology},
  year = {2026},
  volume = {37},
  number = {33},
  pages = {336107},
  doi = {10.1088/1361-6501/ae87b7}
}
Kostenlos starten →