EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Mechanism-Guided Multi-Branch Neural Network for Acoustic Emission-Based Damage Stage Identification of Freeze–Thaw and Corrosion-Damaged Reinforced Concrete Beams

Xianqiang Wang, Fan Yi, Xiaonan Feng, Yaoxuan Wang

Acoustics · 30.10.2026 · 8 (4) · 73

DOI: 10.3390/acoustics8040073 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acoustics, online erschienen am 30.10.2026. Verfasst von Xianqiang Wang und 3 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangsu Province, Jiangsu Province Youth Science and Technology Talent Support Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To identify the development stages of load-induced cracks in reinforced concrete beams under freeze–thaw and corrosion degradation, this paper proposes a mechanism-guided multi-branch neural network approach. Based on the physical meanings of acoustic emission parameters, the input features are divided into the following four groups: crack evolution process, damage intensity characterization, crack pattern characterization, and structural degradation state. Independent branches are employed for feature extraction, and hierarchical fusion is used to achieve collaborative representation of multidimensional damage information. Additionally, the Coyote Optimization Algorithm (COA) is introduced to optimize the initial parameters of key network layers. A total of 5789 valid acoustic emission event samples were obtained from loading tests, covering four degradation levels and four damage stages. Repeated experiments (20 trials) demonstrated that the proposed COA-MB-MLP model achieved an accuracy of 91.42% and a Macro-F1 score of 0.9118 on the test set, outperforming traditional benchmark models such as KNN, LDA, SVM, and RF, with statistically significant performance improvements. Ablation experiments revealed that the mechanism-guided multi-branch structure is the primary source of performance enhancement; COA initialization provides modest improvements in average test performance and reduces variability across repeated experiments. Feature response and confusion sample analysis indicated that amplitude is more sensitive to damage stage evolution, while features like counts, energy, and duration exhibit significant increases in the failure stage. Confusion between adjacent stages primarily stems from crack evolution continuity and ambiguous phase boundaries. The findings demonstrate that the proposed method effectively integrates multidimensional physical information from acoustic emission signals, providing a valuable reference for identifying crack development stages in freeze–thaw and corrosion-damaged reinforced concrete beams.

Förderung

  • Natural Science Foundation of Jiangsu Province
  • Jiangsu Province Youth Science and Technology Talent Support Project

Zitieren

APA

Wang, X., Yi, F., Feng, X., & Wang, Y. (2026). A Mechanism-Guided Multi-Branch Neural Network for Acoustic Emission-Based Damage Stage Identification of Freeze–Thaw and Corrosion-Damaged Reinforced Concrete Beams. Acoustics, 8(4), 73. https://doi.org/10.3390/acoustics8040073

Vancouver

Wang X, Yi F, Feng X, Wang Y. A Mechanism-Guided Multi-Branch Neural Network for Acoustic Emission-Based Damage Stage Identification of Freeze–Thaw and Corrosion-Damaged Reinforced Concrete Beams. Acoustics. 2026;8(4):73. doi:10.3390/acoustics8040073

BibTeX
@article{Wang2026,
  author = {Wang, Xianqiang and Yi, Fan and Feng, Xiaonan and Wang, Yaoxuan},
  title = {A Mechanism-Guided Multi-Branch Neural Network for Acoustic Emission-Based Damage Stage Identification of Freeze–Thaw and Corrosion-Damaged Reinforced Concrete Beams},
  journal = {Acoustics},
  year = {2026},
  volume = {8},
  number = {4},
  pages = {73},
  doi = {10.3390/acoustics8040073}
}
Kostenlos starten →