EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Sensor Heterogeneous Signal Fusion Transformer for Tool Wear Prediction

Ju Zhou, Xinyu Liu, Qianghua Liao, Tao Wang, Lin Wang iD, Pin Yang

Sensors · 06.08.2025 · 25 (15) · 4847

DOI: 10.3390/s25154847 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.08.2025. Verfasst von Ju Zhou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Tech X Academy, Shenzhen Polytechnic University, Shenzhen 518055, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Postdoctoral Research Startup Fund Project of Shenzhen Polytechnic University, the Special Projects in Key Fields of General Universities in Guangdong Province, the Shenzhen Strategic Emerging Industry Support Plans.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In tool wear monitoring, the efficient fusion of multi-source sensor signals poses significant challenges due to their inherent heterogeneous characteristics. In this paper, we propose a Multi-Sensor Multi-Domain feature fusion Transformer (MSMDT) model that achieves precise tool wear prediction through innovative feature engineering and cross-modal self-attention mechanisms. Specifically, we first develop a physics-aware feature extraction framework, where time-domain statistical features, frequency-domain energy features, and wavelet packet time–frequency features are systematically extracted for each sensor type. This approach constructs a unified feature matrix that effectively integrates the complementary characteristics of heterogeneous signals while preserving discriminative tool wear signatures. Then, a position-embedding-free Transformer architecture is constructed, which enables adaptive cross-domain feature fusion through joint global context modeling and local feature interaction analysis to predict tool wear values. Experimental results on the PHM2010 demonstrate the superior performance of MSMDT, outperforming state-of-the-art methods in prediction accuracy.

Schlagwörter

Stichwörter der Autor:innen

Transformer modelsdeep learningfeature fusionmulti-sensor signaltool wear prediction

Autor:innen und Institutionen

  • Tech X Academy, Shenzhen Polytechnic University, Shenzhen 518055, China.
  • Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
  • College of Electronic and Information Engineering, Southwest University, Chongqing 400715, China.
  • School of Mechanical Engineering and Automation, University of Science and Technology Liaoning, Anshan 114044, China.

ORCID-Profile: Lin Wang

Förderung

  • the Postdoctoral Research Startup Fund Project of Shenzhen Polytechnic University
  • the Special Projects in Key Fields of General Universities in Guangdong Province
  • the Shenzhen Strategic Emerging Industry Support Plans
  • Postdoctoral Research Startup Fund Project of Shenzhen Polytechnic University
  • Special Projects in Key Fields of General Universities in Guangdong Province
  • Shenzhen Strategic Emerging Industry Support Plans

Zitieren

APA

Zhou, J., Liu, X., Liao, Q., Wang, T., Wang, L., & Yang, P. (2025). Multi-Sensor Heterogeneous Signal Fusion Transformer for Tool Wear Prediction. Sensors, 25(15), 4847. https://doi.org/10.3390/s25154847

Vancouver

Zhou J, Liu X, Liao Q, Wang T, Wang L, Yang P. Multi-Sensor Heterogeneous Signal Fusion Transformer for Tool Wear Prediction. Sensors. 2025;25(15):4847. doi:10.3390/s25154847

BibTeX
@article{Zhou2025,
  author = {Zhou, Ju and Liu, Xinyu and Liao, Qianghua and Wang, Tao and Wang, Lin and Yang, Pin},
  title = {Multi-Sensor Heterogeneous Signal Fusion Transformer for Tool Wear Prediction},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4847},
  doi = {10.3390/s25154847}
}
Kostenlos starten →