Deep-Learning Methods for Defect Inspection of Plated Through Holes With Clustering-Based Auto-Labeling and GAN-Based Model Training
Open Access
- 11 December 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 190598-190610
Abstract
This paper presents the integration of several deep learning techniques for defect inspection of plated through-hole (PTH) on printed circuit boards (PCBs). In our proposed system, the object detection technology of You Only Look Once (YOLO) allocates the position of PTHs; a semi-automatic clustering mechanism distinguishes normal and defective PTHs for collecting training data. A convolution neural network based on the ResNet framework is established for detecting PTH defects. A retrain mechanism is designed for retracting misclassified PTHs and updating the recognition model. The generative adversarial network (GAN) is employed to deal with the insufficiency of negative training samples. The detection model can achieve 98.96% accuracy with continuous retraining and data augmentation. Further, a filtering mechanism based on template analysis eliminates ambiguous outputs of GAN and improves the accuracy of the detection model. This study integrates these deep learning techniques to establish a PTH defect detection system tested in a PCB manufactory against real PTHs and gained an overall prediction accuracy of 99.48%.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (NSTC 110-2221-E-390-018, MOST 109-2221-E-390-016)
This publication has 24 references indexed in Scilit:
- A Survey on Unsupervised Anomaly Detection Algorithms for Industrial ImagesIEEE Access, 2023
- CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly LocalizationIEEE Access, 2022
- Deep learning based solder joint defect detection on industrial printed circuit board X-ray imagesComplex & Intelligent Systems, 2022
- CS-ResNet: Cost-sensitive residual convolutional neural network for PCB cosmetic defect detectionExpert Systems with Applications, 2021
- Transfer Learning With CNN for Classification of Weld DefectIEEE Access, 2021
- PCB Defect Detection Using Deep Learning Methods2021
- TsanKit: artificial intelligence for solder ball head-in-pillow defect inspectionMachine Vision and Applications, 2021
- Detection of PCB Surface Defects With Improved Faster-RCNN and Feature Pyramid NetworkIEEE Access, 2020
- An efficient similarity measure approach for PCB surface defect detectionPattern Analysis and Applications, 2017
- Xception: Deep Learning with Depthwise Separable Convolutions2017