Detection of Defects in Printed Circuit Boards with Machine Learning and Deep Learning Algorithms
Avrupa Bilim ve Teknoloji Dergisi, sa.41, ss.183-186, 2022 (Hakemli Dergi)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2022
- Doi Numarası: 10.31590/ejosat.1178188
- Dergi Adı: Avrupa Bilim ve Teknoloji Dergisi
- Derginin Tarandığı İndeksler: Index Copernicus, Sobiad Atıf Dizini
- Sayfa Sayıları: ss.183-186
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Erzincan Binali Yıldırım Üniversitesi Adresli: Evet
Özet
Printed Circuit Boards (PCBs) are electronic boards that hold electronic components together and provide the electrical connection between these components. Printed circuit boards offer many advantages over traditional wired circuits, such as durability, less heat, minimal wiring, and ease of assembly. Correct design and production of printed circuit boards significantly affect the quality and efficiency of printed circuit boards. In this study, a defect detection system based on machine learning and deep learning algorithms is proposed to help produce printed circuit boards accurately and minimize the error rate. In the proposed system, missing hole, mouse bite, open circuit, short, spur, and spurious copper defects on the printed circuit have been determined. According to the results obtained, According to the results obtained, success accuracies of 74.62% were obtained with YOLO-v4, 47.83% with HOG+SVM, and 39.86% with HOG+KNN. It has been seen that the algorithms discussed in the study are applicable in the detection of defects in printed circuit boards.