EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BW-YOLO: A Lightweight Recurrence-Plot-Driven Network for In-Process Defect Identification from Multi-Band Photodiode Signals in Lithium-Ion Battery Laser Welding

Nengsheng Bao, Jiaqi Li, Yuchen Fan, Alessandro Simeone, Runxuan Bao

Journal of Manufacturing and Materials Processing · 30.10.2026 · 10 (11) · 459

DOI: 10.3390/jmmp10110459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Manufacturing and Materials Processing, online erschienen am 30.10.2026. Verfasst von Nengsheng Bao und 4 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2026 Dongguan Outstanding Engineer Joint Training Key Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Laser welding of tabs and busbars determines the electrical integrity and safety of lithium-ion battery modules, yet many weld defects leave little trace on the surface that post-weld vision inspection relies on. Photodiode signals record the weld-pool dynamics during processing, but their short, non-stationary waveforms are difficult to classify reliably with a compact model. This study presents BW-YOLO, a lightweight network designed together with recurrence-plot (RP) encoding of the photoelectric signal. The RP turns each weld signal into an image whose coarse block structure and fine recurrent texture reflect keyhole stability. BW-YOLO matches this two-scale structure with a Haar wavelet convolution module that integrates channel shuffle and one-shot aggregation (WT-ShuffleOSA) and a dual-scale channel reduction pyramid slice attention module (DCR-PSA). The evaluation used a balanced dataset of 1200 industrially produced joints monitored in the visible, infrared and reflected-laser bands, with one fixed training–validation partition. On the 240 validation joints, evaluated separately in each band, BW-YOLO reduced misclassifications by 30–38% in every band relative to the YOLO11n-cls baseline with a reported 15% reduction in operation count. In the infrared band it reached 96.67% accuracy and 98.28% precision with 1.50 M parameters and 2.8 GFLOPs, giving the highest observed accuracy among the ten networks compared on that partition. These results support further investigation of the proposed design; robustness across training runs and datasets, performance relative to direct time-series classifiers, and deployment latency remain to be established.

Förderung

  • 2026 Dongguan Outstanding Engineer Joint Training Key Project

Zitieren

APA

Bao, N., Li, J., Fan, Y., Simeone, A., & Bao, R. (2026). BW-YOLO: A Lightweight Recurrence-Plot-Driven Network for In-Process Defect Identification from Multi-Band Photodiode Signals in Lithium-Ion Battery Laser Welding. Journal of Manufacturing and Materials Processing, 10(11), 459. https://doi.org/10.3390/jmmp10110459

Vancouver

Bao N, Li J, Fan Y, Simeone A, Bao R. BW-YOLO: A Lightweight Recurrence-Plot-Driven Network for In-Process Defect Identification from Multi-Band Photodiode Signals in Lithium-Ion Battery Laser Welding. Journal of Manufacturing and Materials Processing. 2026;10(11):459. doi:10.3390/jmmp10110459

BibTeX
@article{Bao2026,
  author = {Bao, Nengsheng and Li, Jiaqi and Fan, Yuchen and Simeone, Alessandro and Bao, Runxuan},
  title = {BW-YOLO: A Lightweight Recurrence-Plot-Driven Network for In-Process Defect Identification from Multi-Band Photodiode Signals in Lithium-Ion Battery Laser Welding},
  journal = {Journal of Manufacturing and Materials Processing},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {459},
  doi = {10.3390/jmmp10110459}
}
Kostenlos starten →