EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Head Attention Network for Fast Prediction of Ultrasonic Guided Wave Dispersion Under Coupled Temperature and Stress

Xiao Ying iD, Zhao Wang, Jian Li, Yantao Liu, Haibo Li, Haoran Jin, Fuzai Lv, Yang Liu

Sensors · 01.03.2026 · 26 (5) · 1549

DOI: 10.3390/s26051549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.03.2026. Verfasst von Xiao Ying und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stable Support Project of National Defense Science and Technology Industry Bureau, State Administration of Science, Technology and Industry for National Defence.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasonic guided wave sensors are widely employed for structural health monitoring; yet, their signal interpretation reliability is frequently compromised in extreme environments where coupled temperature and stress induce significant nonlinear drifts in dispersion characteristics. To overcome the computational bottleneck of conventional numerical methods that hinders real-time sensor calibration, this paper proposes a Dispersion Multi-Head Attention Network (D-MHAN) that directly maps eleven raw physical parameters to full-band dispersion responses. By adopting a non-normalized input strategy to internalize underlying physical laws, the model enables robust out-of-distribution extrapolation even when material properties exceed the training manifold. It was validated against a high-fidelity dataset spanning temperatures from −250 °C to 100 °C and stresses from 0 to 150 MPa generated by the Semi-Analytical Finite Element (SAFE) method. The proposed D-MHAN achieves a Pearson correlation coefficient of 0.9999 and provides computational speeds approximately 30 and 168 times faster than SAFE and the Wave Finite Element Method (WFEM). The model’s practical utility is further corroborated by cryogenic experiments on an aerospace storage tank. This work establishes a critical foundation for real-time parameter sensitivity analysis and environmental effect compensation in practical ultrasonic sensing applications.

Schlagwörter

Stichwörter der Autor:innen

deep learningdispersion curvesextreme environmentultrasonic guided waves

Autor:innen und Institutionen

  • State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China.
  • Beijing Institute of Structure and Environment Engineering, Beijing 100076, China.
  • State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China.

ORCID-Profile: Xiao Ying

Förderung

  • Stable Support Project of National Defense Science and Technology Industry Bureau
  • State Administration of Science, Technology and Industry for National Defence

Zitieren

APA

Ying, X., Wang, Z., Li, J., Liu, Y., Li, H., Jin, H., Lv, F., & Liu, Y. (2026). A Multi-Head Attention Network for Fast Prediction of Ultrasonic Guided Wave Dispersion Under Coupled Temperature and Stress. Sensors, 26(5), 1549. https://doi.org/10.3390/s26051549

Vancouver

Ying X, Wang Z, Li J, Liu Y, Li H, Jin H, et al. A Multi-Head Attention Network for Fast Prediction of Ultrasonic Guided Wave Dispersion Under Coupled Temperature and Stress. Sensors. 2026;26(5):1549. doi:10.3390/s26051549

BibTeX
@article{Ying2026,
  author = {Ying, Xiao and Wang, Zhao and Li, Jian and Liu, Yantao and Li, Haibo and Jin, Haoran and Lv, Fuzai and Liu, Yang},
  title = {A Multi-Head Attention Network for Fast Prediction of Ultrasonic Guided Wave Dispersion Under Coupled Temperature and Stress},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {5},
  pages = {1549},
  doi = {10.3390/s26051549}
}
Kostenlos starten →