EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Conditional Dual-Branch Cross-Fusion Network with Cross-Modal Attention for Vibro-Acoustic Engine Fault Diagnosis

Hui Wang, Xiaolong Zhu iD, Junhong Zhang, Qihua Wu, Jiewei Lin iD

Sensors · 26.10.2026 · 26 (21) · 6778

DOI: 10.3390/s26216778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.10.2026. Verfasst von Hui Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Engines, Tianjin University, Tianjin 300072, China. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable diagnosis of diesel-engine thermal and mechanical faults remains difficult when labelled samples are scarce, operating conditions vary, and measurements are strongly contaminated by noise. A conditional dual-branch cross-fusion network with cross-modal attention (CDCFN) is proposed for joint analysis of vibration and acoustic signals. Modality-specific convolutional modules extract fault-related features. A multimodal cross-attention mechanism applies temporal attention separately to the two modalities, concatenates the attended features for joint channel attention, and then separates the reweighted streams. A cross-modal conditional-decision module forms two directional decisions by using one modality to weight the other. CDCFN was evaluated on thermal- and mechanical-fault datasets using 50 training and 100 test sample pairs per class. Across the tested load conditions, the best mean accuracies were 98.23 ± 0.68% for CDCFN_V/A on the thermal-fault dataset and 97.99 ± 0.63% for CDCFN_A/V on the mechanical-fault dataset; the corresponding weighted F1 scores were 98.22% and 98.05%. Under matched Gaussian-noise training and testing at −12 dB, CDCFN_A/V achieved across-load mean accuracies of 94.89 ± 0.34% and 74.71 ± 1.45%, respectively. LayerCAM indicated attention to intake-valve seating, exhaust-valve seating, piston reversal, and combustion responses. These results support directional cross-modal attention for the tested small-sample, variable-load, and matched-noise settings.

Schlagwörter

Stichwörter der Autor:innen

conditional attentioncross-fusion networkdiesel-engine fault diagnosismechanical faultsthermal faultsvibro-acoustic fusion

Autor:innen und Institutionen

  • State Key Laboratory of Engines, Tianjin University, Tianjin 300072, China.
  • Weichai Power Co., Ltd., Weifang 261001, China.
  • School of Information and Intelligent Engineering, Tianjin Renai College, Tianjin 300072, China.

ORCID-Profile: Xiaolong Zhu, Jiewei Lin

Förderung

  • National Key R&D Program of China
  • National Key R&D Program of China

Zitieren

APA

Wang, H., Zhu, X., Zhang, J., Wu, Q., & Lin, J. (2026). A Conditional Dual-Branch Cross-Fusion Network with Cross-Modal Attention for Vibro-Acoustic Engine Fault Diagnosis. Sensors, 26(21), 6778. https://doi.org/10.3390/s26216778

Vancouver

Wang H, Zhu X, Zhang J, Wu Q, Lin J. A Conditional Dual-Branch Cross-Fusion Network with Cross-Modal Attention for Vibro-Acoustic Engine Fault Diagnosis. Sensors. 2026;26(21):6778. doi:10.3390/s26216778

BibTeX
@article{Wang2026,
  author = {Wang, Hui and Zhu, Xiaolong and Zhang, Junhong and Wu, Qihua and Lin, Jiewei},
  title = {A Conditional Dual-Branch Cross-Fusion Network with Cross-Modal Attention for Vibro-Acoustic Engine Fault Diagnosis},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6778},
  doi = {10.3390/s26216778}
}
Kostenlos starten →