<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>As computer vision and deep learning detection techniques advance rapidly, their use in identifying defects has become more common across various industries. The significance of Printed Circuit Boards (PCBs) in contemporary electronic devices is undeniable, as they substantially influence the functionality and durability of these products. Thus, utilizing deep learning models for identifying flaws in Printed Circuit Boards (PCBs) is of particular importance. The focus of this study is primarily on examining PCB defect identification utilizing deep learning techniques. Firstly, it introduces the importance and development history of PCBs in the electronics and information industry. It then offers a comprehensive review of the existing research on conventional PCB defect detection approaches alongside methodologies grounded in deep learning. Following that, the structure of the YOLOv8 object detection model and its key technologies are elaborated. Lastly, the superior performance of YOLOv8 in PCB defect detection tasks is verified through comparative experiments. According to the evaluation metrics of the algorithm, the average detection accuracy reaches 92.3%, and the Frames Per Second (FPS) value reaches 157.2, meeting the accuracy requirements for PCB defect detection in the industrial domain.</p>
</abstract>

As computer vision and deep learning detection techniques advance rapidly, their use in identifying defects has become more common across various industries. The significance of Printed Circuit Boards (PCBs) in contemporary electronic devices is undeniable, as they substantially influence the functionality and durability of these products. Thus, utilizing deep learning models for identifying flaws in Printed Circuit Boards (PCBs) is of particular importance. The focus of this study is primarily on examining PCB defect identification utilizing deep learning techniques. Firstly, it introduces the importance and development history of PCBs in the electronics and information industry. It then offers a comprehensive review of the existing research on conventional PCB defect detection approaches alongside methodologies grounded in deep learning. Following that, the structure of the YOLOv8 object detection model and its key technologies are elaborated. Lastly, the superior performance of YOLOv8 in PCB defect detection tasks is verified through comparative experiments. According to the evaluation metrics of the algorithm, the average detection accuracy reaches 92.3%, and the Frames Per Second (FPS) value reaches 157.2, meeting the accuracy requirements for PCB defect detection in the industrial domain.

Deep Learning Based Defect Detection Research on Printed Circuit Boards

School of Computer Science and Engineering

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Deep Learning Based Defect Detection Research on Printed Circuit Boards"}

As computer vision and deep learning detection techniques advance rapidly, their use in identifying defects has become more common across various industries....

Model	mAP(%)	FPS	Quantity of participants/M
Faster R-CNN	89.5	20.5	125.3
YOLOv5	85.3	79.4	42.7
YOLOv7	87.1	102.5	37.2
YOLOv8	92.3	157.2	28.5

Experimental environment	Version
CPU	Intel Core i7-11800H
GPU	NVIDIA GeForce RTX307
Language	Python3.7
Deep Learning Framework	Pytorch1.11.0
CUDA	11.3.0
Compiler	Pycharm2021

Deep Learning Based Defect Detection Research on Printed Circuit Boards

Data publikacji: 21 lip 2024

Zakres stron: 51 - 58

DOI: https://doi.org/10.2478/ijanmc-2024-0015

Słowa kluczowe
Deep Learning, Defect Detection, YOLOv8

© 2024 Qihang Yang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Experimental Results

Experimental Environment

Deep Learning Based Defect Detection Research on Printed Circuit Boards

Data publikacji: 21 lip 2024

Zakres stron: 51 - 58

DOI: https://doi.org/10.2478/ijanmc-2024-0015

Słowa kluczoweDeep Learning, Defect Detection, YOLOv8

© 2024 Qihang Yang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Experimental Results

Experimental Environment

Słowa kluczowe
Deep Learning, Defect Detection, YOLOv8