EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Welding Defect Detection Model Based on Hybrid-Enhanced Multi-Granularity Spatiotemporal Representation Learning

Chenbo Shi, Shaojia Yan, Lei Wang, Changsheng Zhu, Yue Yu, Xiangteng Zang, Aiping Liu, Chun Zhang iD, Xiaobing Feng iD

Sensors · 27.07.2025 · 25 (15) · 4656

DOI: 10.3390/s25154656 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.07.2025. Verfasst von Chenbo Shi und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of lntelligent Equipment, Shandong University of Science and Technology, Taian 271019, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Mingjia Technology Co., Shandong Mingjia Technology Co. OF FUNDER.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time quality monitoring using molten pool images is a critical focus in researching high-quality, intelligent automated welding. To address interference problems in molten pool images under complex welding scenarios (e.g., reflected laser spots from spatter misclassified as porosity defects) and the limited interpretability of deep learning models, this paper proposes a multi-granularity spatiotemporal representation learning algorithm based on the hybrid enhancement of handcrafted and deep learning features. A MobileNetV2 backbone network integrated with a Temporal Shift Module (TSM) is designed to progressively capture the short-term dynamic features of the molten pool and integrate temporal information across both low-level and high-level features. A multi-granularity attention-based feature aggregation module is developed to select key interference-free frames using cross-frame attention, generate multi-granularity features via grouped pooling, and apply the Convolutional Block Attention Module (CBAM) at each granularity level. Finally, these multi-granularity spatiotemporal features are adaptively fused. Meanwhile, an independent branch utilizes the Histogram of Oriented Gradient (HOG) and Scale-Invariant Feature Transform (SIFT) features to extract long-term spatial structural information from historical edge images, enhancing the model’s interpretability. The proposed method achieves an accuracy of 99.187% on a self-constructed dataset. Additionally, it attains a real-time inference speed of 20.983 ms per sample on a hardware platform equipped with an Intel i9-12900H CPU and an RTX 3060 GPU, thus effectively balancing accuracy, speed, and interpretability.

Schlagwörter

Stichwörter der Autor:innen

deep learningimage interferencekey interference-free framesmulti-granularity spatiotemporal featuresporosity defect

Autor:innen und Institutionen

  • College of lntelligent Equipment, Shandong University of Science and Technology, Taian 271019, China.
  • Beijing Botsing Technology Co., Ltd., Beijing 100176, China.

ORCID-Profile: Chun Zhang, Xiaobing Feng

Förderung

  • Shandong Mingjia Technology Co.
  • Shandong Mingjia Technology Co. OF FUNDER

Zitieren

APA

Shi, C., Yan, S., Wang, L., Zhu, C., Yu, Y., Zang, X., Liu, A., Zhang, C., & Feng, X. (2025). A Welding Defect Detection Model Based on Hybrid-Enhanced Multi-Granularity Spatiotemporal Representation Learning. Sensors, 25(15), 4656. https://doi.org/10.3390/s25154656

Vancouver

Shi C, Yan S, Wang L, Zhu C, Yu Y, Zang X, et al. A Welding Defect Detection Model Based on Hybrid-Enhanced Multi-Granularity Spatiotemporal Representation Learning. Sensors. 2025;25(15):4656. doi:10.3390/s25154656

BibTeX
@article{Shi2025,
  author = {Shi, Chenbo and Yan, Shaojia and Wang, Lei and Zhu, Changsheng and Yu, Yue and Zang, Xiangteng and Liu, Aiping and Zhang, Chun and Feng, Xiaobing},
  title = {A Welding Defect Detection Model Based on Hybrid-Enhanced Multi-Granularity Spatiotemporal Representation Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4656},
  doi = {10.3390/s25154656}
}
Kostenlos starten →