PCB Defect Detector: Deep Learning to Detect Component Installation Errors in PCB Production

DOI

10.2991/978-94-6463-982-7_36How to use a DOI?

Keywords

PCB; YOLO; Defect Detector; Automatic inspection

Abstract

Errors in component placement on Printed Circuit Boards (PCBs) can lead to functional failures and increased production costs. Manual inspection for identifying and classifying such errors remains a significant challenge in the electronic manufacturing industry. Therefore, there is a need for an accurate and efficient automated inspection system. This study aims to develop an automated detection system for PCB component placement errors using the You Only Look Once (YOLO) algorithm. YOLO provides a one-stage detection process that eliminates the need for multi-step approaches such as region proposal methods. The development process involves dataset collection, defect labeling and annotation, data preprocessing, model training, and performance evaluation. The proposed model is developed to detect various types of defects, including missing components as well as misaligned or improperly mounted parts. The system’s performance is analyzed using accuracy, precision, confusion matrix analysis, and inference speed. Experimental results demonstrate that the proposed YOLO-based system can automatically detect component placement errors with high accuracy, thereby improving inspection reliability and supporting faster and more efficient PCB production processes.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Putri Dezalna
AU  - S. Rahmad Rozak Pratama
AU  - Iman Fahruzi
PY  - 2025
DA  - 2025/12/29
TI  - PCB Defect Detector: Deep Learning to Detect Component Installation Errors in PCB Production
BT  - Proceedings of the  8th International Conference on Applied Engineering (ICAE 2025)
PB  - Atlantis Press
SP  - 597
EP  - 613
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-982-7_36
DO  - 10.2991/978-94-6463-982-7_36
ID  - Dezalna2025
ER  -