EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Defect Classification in Electronic Components on PCBs With Deep Learning Models

Ozan Peker, Fatih Uysal, Firat Hardalac

IEEE Access · 2026 · 14 · 98691-98710

DOI: 10.1109/access.2026.3701778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Ozan Peker und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Printed circuit boards (PCBs) are widely used in the production of many electronic devices today, making the accurate detection and classification of defects that may occur during manufacturing critically important. In recent years, deep learning-based approaches have gained prominence in this field. In this study, a novel deep learning approach is proposed to accurately detect and classify defects in electronic components on PCBs. An open-source dataset containing defect samples was selected for the research. This study utilizes the PCB subset of the dataset, focusing on 4 distinct PCB types evaluated across 9 functional categories (8 specific defect types and 1 normal class). To address the class imbalance in the dataset, data augmentation and preprocessing techniques were applied. For feature extraction, the models CSPResNet50, EfficientViT, RepGhostNet, and ResNet50 were employed. While the cross-entropy function was used as the loss function in the training of traditional models, a cosine-based loss function was specially designed to align with the structure and purpose of the proposed model.This study involves both PCB and defect classification processes. When examining the performance on the defect classification validation dataset (which is the key task) the proposed method achieved the highest performance with a precision of 0.90, an F1-score of 0.8961, a Matthews Correlation Coefficient (MCC) of 0.87453, and a Cohen’s Kappa score of 0.8736.

Zitieren

APA

Peker, O., Uysal, F., & Hardalac, F. (2026). Defect Classification in Electronic Components on PCBs With Deep Learning Models. IEEE Access, 14, 98691-98710. https://doi.org/10.1109/access.2026.3701778

Vancouver

Peker O, Uysal F, Hardalac F. Defect Classification in Electronic Components on PCBs With Deep Learning Models. IEEE Access. 2026;14:98691-98710. doi:10.1109/access.2026.3701778

BibTeX
@article{Peker2026,
  author = {Peker, Ozan and Uysal, Fatih and Hardalac, Firat},
  title = {Defect Classification in Electronic Components on PCBs With Deep Learning Models},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {98691--98710},
  doi = {10.1109/access.2026.3701778}
}
Kostenlos starten →