Journal
SENSORS
Volume 21, Issue 15, Pages -Publisher
MDPI
DOI: 10.3390/s21154968
Keywords
deep learning; autoencoder; detect detection; PCB defeat detection; printed circuit board manufacturing
Funding
- National Research Foundation of Korea [NRF-2017M3A9E2056461]
- Gachon University research fund [GCU-2018-0324]
- National Research Foundation of Korea [2017M3A9E2056461] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
As technology evolves, PCB surface inspection becomes increasingly important. The proposed advanced PCB inspection system based on a deep autoencoder is able to identify defect locations by decoding defective images, and image augmentation techniques are applied to enhance model training performance.
As technology evolves, more components are integrated into printed circuit boards (PCBs) and the PCB layout increases. Because small defects on signal trace can cause significant damage to the system, PCB surface inspection is one of the most important quality control processes. Owing to the limitations of manual inspection, significant efforts have been made to automate the inspection by utilizing high resolution CCD or CMOS sensors. Despite the advanced sensor technology, setting the pass/fail criteria based on small failure samples has always been challenging in traditional machine vision approaches. To overcome these problems, we propose an advanced PCB inspection system based on a skip-connected convolutional autoencoder. The deep autoencoder model was trained to decode the original non-defect images from the defect images. The decoded images were then compared with the input image to identify the defect location. To overcome the small and imbalanced dataset in the early manufacturing stage, we applied appropriate image augmentation to improve the model training performance. The experimental results reveal that a simple unsupervised autoencoder model delivers promising performance, with a detection rate of up to 98% and a false pass rate below 1.7% for the test data, containing 3900 defect and non-defect images.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available