Detection of Missing Component in PCB Using YOLO

Authors

  • Shivaji Pandit Chhetri Department of Electronics and Computer Engineering, Sagarmatha Engineering College, Lalitpur, Nepal
  • Santosh Bhat Department of Electronics and Computer Engineering, Sagarmatha Engineering College, Lalitpur, Nepal
  • Pradeep Timalsina Department of Electronics and Computer Engineering, Sagarmatha Engineering College, Lalitpur, Nepal
  • Bipin Thapa Magar Department of Electronics and Computer Engineering, Sagarmatha Engineering College, Lalitpur, Nepal

DOI:

https://doi.org/10.3126/injet.v1i1.60902

Keywords:

Printed circuit board, Inductor, Capacitors, Resistors, Data labeling, YOLO, Machine learning, Label Studio, Push Button, Automated optical inspection, Mean Average Precision

Abstract

The detection of missing components in printed circuit boards (PCBs) is a critical task in the electronics manufacturing industry. The current practice of manual inspection is time-consuming and prone to human error, which can result in faulty products and increased costs. In this paper, we propose a solution that uses the YOLO (You Only Look Once) object detection algorithm to automatically detect missing electronic components in PCBs. Electronic components detection model is trained using YOLOv3 architecture. Dataset is prepared using high quality printed circuit board images and manual labeling in Label Studio. The model is trained on a dataset of 16 different electronic components commonly found in PCBs including Electrolytic Capacitor, QFP, Toroidal core Inductor, Crystal Oscillator etc. Prepared model recognizes these electronic components with an average map score of 65.8%with IoU 50% and 42.6% with IoU 95%. The results show that the proposed solution can detect the missing components.  

Downloads

Download data is not yet available.
Abstract
80
PDF
77

Downloads

Published

2023-12-21

How to Cite

Chhetri, S. P., Bhat, S., Timalsina, P., & Magar, B. T. (2023). Detection of Missing Component in PCB Using YOLO. International Journal on Engineering Technology, 1(1), 62–71. https://doi.org/10.3126/injet.v1i1.60902

Issue

Section

Articles