EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Studentized Multi-Kernel MMD for Cross-Condition Machinery Fault Diagnosis

Shiqian Wu iD, Weiming Zhang, Yurui Sang, Minghui Guo, Yuchen Lu, Yuxuan Zhang iD

Sensors · 07.11.2026 · 26 (21) · 7043

DOI: 10.3390/s26217043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.11.2026. Verfasst von Shiqian Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shipbuilding Engineering Department, Jiangxi Polytechnic University, Jiujiang 332007, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Project of Jiangxi Provincial Department of Education, Mid Sweden University for Open Access Publication.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes adaptive Studentized multi-kernel maximum mean discrepancy (MMD) for cross-condition machinery fault diagnosis. To account for sampling variation in mini-batch alignment, the multi-kernel MMD objective is normalized by empirical variability and integrated with domain-specific batch normalization. A label-free plateau criterion monitors fluctuations in the alignment loss and triggers joint cosine cooling of the learning rate and alignment weight, adapting the cooling onset to the observed training trajectory. The framework is evaluated on 18 window-level transfer tasks from the Paderborn bearing and PHM2009 gearbox datasets, with five random seeds per task and a fixed final-epoch reporting rule. Mean final-epoch accuracies reach 89.32% and 73.86%, exceeding DAN-style multi-kernel alignment by 2.16 and 2.39 percentage points, respectively. Compared with the fixed-schedule Studentized variant, adaptive scheduling improves accuracy by 0.57 and 0.37 percentage points, respectively. These results support combining variability-normalized alignment with label-free adaptive scheduling for cross-condition fault diagnosis.

Schlagwörter

Stichwörter der Autor:innen

Studentized maximum mean discrepancyadaptive schedulingdomain-specific batch normalizationfault diagnosisrotating machineryunsupervised domain adaptation

Autor:innen und Institutionen

  • Shipbuilding Engineering Department, Jiangxi Polytechnic University, Jiujiang 332007, China.
  • Institute of Marine Equipment Structural Safety, Jiangxi Polytechnic University, Jiujiang 332007, China.
  • Yantai Research Institute, Harbin Engineering University, Yantai 264000, China.
  • College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing 102206, China.
  • Department of Computer and Electrical Engineering, Mid Sweden University, 85170 Sundsvall, Sweden.

ORCID-Profile: Shiqian Wu, Yuxuan Zhang

Förderung

  • Science and Technology Research Project of Jiangxi Provincial Department of Education
  • Mid Sweden University for Open Access Publication

Zitieren

APA

Wu, S., Zhang, W., Sang, Y., Guo, M., Lu, Y., & Zhang, Y. (2026). Adaptive Studentized Multi-Kernel MMD for Cross-Condition Machinery Fault Diagnosis. Sensors, 26(21), 7043. https://doi.org/10.3390/s26217043

Vancouver

Wu S, Zhang W, Sang Y, Guo M, Lu Y, Zhang Y. Adaptive Studentized Multi-Kernel MMD for Cross-Condition Machinery Fault Diagnosis. Sensors. 2026;26(21):7043. doi:10.3390/s26217043

BibTeX
@article{Wu2026,
  author = {Wu, Shiqian and Zhang, Weiming and Sang, Yurui and Guo, Minghui and Lu, Yuchen and Zhang, Yuxuan},
  title = {Adaptive Studentized Multi-Kernel MMD for Cross-Condition Machinery Fault Diagnosis},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7043},
  doi = {10.3390/s26217043}
}
Kostenlos starten →