EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Pcb Defect Detection in Manufacturing Using Deep Learning

Raziya Siddiqui, Abhimanyu Pratap Singh, Aniruddh Singh, Anurag Gupta

International Research Journal on Advanced Engineering and Management (IRJAEM) · 28.04.2026 · 4 (04) · 999-1003

DOI: 10.47392/irjaem.2026.0152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Research Journal on Advanced Engineering and Management (IRJAEM), online erschienen am 28.04.2026. Verfasst von Raziya Siddiqui und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Printed Circuit Boards (PCBs) form the structural backbone of modern electronic devices, connecting and supporting electronic components in systems ranging from consumer electronics to aerospace equipment. Ensuring defect-free PCBs during manufacturing is critical because even minor defects such as open circuits, shorts, mouse bites, spurious copper, or micro-cracks can significantly impact product reliability and functionality. Traditional inspection methods, including manual visual inspection and rule-based image processing techniques, often suffer from limitations such as low accuracy, high labor dependency, and sensitivity to environmental conditions like lighting and noise. This review paper presents a comprehensive analysis of recent research developments in PCB defect detection using deep learning techniques. The study categorizes existing approaches into traditional machine vision methods, deep learning-based detection models, and hybrid intelligent inspection systems. Furthermore, the paper discusses recent advancements such as multi-scale feature fusion, attention-based networks, generative data augmentation. The review also highlights key research gaps including the challenges of detecting extremely small defects, dataset limitations, domain adaptation issues, and the integration of intelligent inspection systems within Industry 4.0 manufacturing pipelines. Finally, this work proposes a conceptual framework for an advanced deep learning–based PCB inspection system capable of improving detection accuracy, reducing inspection time, and enabling automated quality control in modern electronics manufacturing.

Zitieren

APA

Siddiqui, R., Singh, A. P., Singh, A., & Gupta, A. (2026). Pcb Defect Detection in Manufacturing Using Deep Learning. International Research Journal on Advanced Engineering and Management (IRJAEM), 4(04), 999-1003. https://doi.org/10.47392/irjaem.2026.0152

Vancouver

Siddiqui R, Singh AP, Singh A, Gupta A. Pcb Defect Detection in Manufacturing Using Deep Learning. International Research Journal on Advanced Engineering and Management (IRJAEM). 2026;4(04):999-1003. doi:10.47392/irjaem.2026.0152

BibTeX
@article{Siddiqui2026,
  author = {Siddiqui, Raziya and Singh, Abhimanyu Pratap and Singh, Aniruddh and Gupta, Anurag},
  title = {Pcb Defect Detection in Manufacturing Using Deep Learning},
  journal = {International Research Journal on Advanced Engineering and Management (IRJAEM)},
  year = {2026},
  volume = {4},
  number = {04},
  pages = {999--1003},
  doi = {10.47392/irjaem.2026.0152}
}
Kostenlos starten →