Defect Detection in Metal-Ceramic Substrate Based on Image Processing and Machine Learning

電気学会 電子図書館 Verified independent store

→

カテゴリ: 論文誌(論文単位)グループ名: 【D】産業応用部門（英文）発行日: 2024/07/01タイトル(英語): Defect Detection in Metal-Ceramic Substrate Based on Image Processing and Machine Learning著者名: Min Zou (Graduate School of Engineering Science, Akita University), Kota Matsunaga (Faculty of Engineering Science, Akita University), Yuji Ueda (Dowa Power Device Co., Ltd.), Tsuyoshi Sugawara (Dowa Power Device Co., Ltd.), Hideyo Osanai (Dowa Power Devi著者名(英語): Min Zou (Graduate School of Engineering Science, Akita University), Kota Matsunaga (Faculty of Engineering Science, Akita University), Yuji Ueda (Dowa Power Device Co., Ltd.), Tsuyoshi Sugawara (Dowa Power Device Co., Ltd.), Hideyo Osanai (Dowa Power Device Co., Ltd.), Yoichi Kageyama (Graduate School of Engineering Science, Akita University)キーワード: defect detection，feature extraction，CNN，classification，deep learning要約(英語): Automatic detection of defects in a substrate is important in the manufacturing process. Defect detection in metal-ceramic substrates relies on manual assembly lines, which are laborious and time consuming. This study develops a novel defect detection method that automatically localizes the substrate area without a background and enhances the defect area by combining images acquired using a platform with different illumination patterns. In this study, we use a defect image dataset to train convolutional neural networks (CNNs) for defect discrimination. Seven evaluation metrics, i.e., accuracy, F1-score, area under the curve, and prediction time of all the patch images in the test set, are comprehensively considered to select the optimal parameter configuration. A developed ResNet-50-based model achieves the highest defect discrimination accuracy of 99.8%. Based on extensive experiments and their results, this study provides clear guidance for devising a feature extraction method based on multidirection filter processing and optimization of CNNs for classification tasks. Finally, a framework for defect detection in a metal-ceramic substrate for practical use in the power device industry is developed.本誌: IEEJ Journal of Industry Applications Vol.13 No.4 （2024） Special Issue on “JIASC 2023”本誌掲載ページ: 379-388 p原稿種別: 論文／英語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejjia/13/4/13_23006878/_article/-char/ja/ Show more