EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Heterogeneous CNN with Adaptive Modality Fusion for Intelligent Fault Diagnosis of Bearings

Chang Sun, Chenkun Wang, Shiwei Huang, Tianci Zhang

Machines · 01.08.2026 · 14 (8) · 875

DOI: 10.3390/machines14080875 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 01.08.2026. Verfasst von Chang Sun und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial equipment fault diagnosis, vibration and acoustic signals are highly complementary yet exhibit significant differences in frequency distribution and noise sensitivity. Traditional multimodal methods generally rely on homogeneous feature extractors and direct feature concatenation, which may fail to capture modality-specific characteristics and introduce irrelevant information during fusion. To address this, we propose a novel multimodal heterogeneous convolutional neural network framework. Specifically, separate 1D CNN branches are designed for vibration and acoustic signals. Their architectural differences are determined by the characteristics of each sensing modality. The vibration branch focuses on extracting high-level discriminative fault features, including impulse responses and modulated components from vibration signals, while the acoustic branch is designed to preserve fragile high-frequency details of acoustic signals. Furthermore, an adaptive cross-attention fusion module is introduced to dynamically model cross-modal dependencies, assigning Softmax-based weights to enhance dominant features and suppress noise. Experiments based on bearing fault experimental data demonstrate that the proposed heterogeneous architecture significantly outperforms traditional homogeneous models. The dynamic weighting mechanism effectively prevents inferior noisy modalities from degrading overall performance, achieving high diagnostic accuracy. Although validated on rolling bearing fault diagnosis, the proposed heterogeneous multimodal framework is not restricted to bearings and can be readily extended to other intelligent condition monitoring tasks involving heterogeneous sensor fusion, such as gearboxes, motors, and other rotating machinery.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hunan Province

Zitieren

APA

Sun, C., Wang, C., Huang, S., & Zhang, T. (2026). Multimodal Heterogeneous CNN with Adaptive Modality Fusion for Intelligent Fault Diagnosis of Bearings. Machines, 14(8), 875. https://doi.org/10.3390/machines14080875

Vancouver

Sun C, Wang C, Huang S, Zhang T. Multimodal Heterogeneous CNN with Adaptive Modality Fusion for Intelligent Fault Diagnosis of Bearings. Machines. 2026;14(8):875. doi:10.3390/machines14080875

BibTeX
@article{Sun2026,
  author = {Sun, Chang and Wang, Chenkun and Huang, Shiwei and Zhang, Tianci},
  title = {Multimodal Heterogeneous CNN with Adaptive Modality Fusion for Intelligent Fault Diagnosis of Bearings},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {875},
  doi = {10.3390/machines14080875}
}
Kostenlos starten →