期刊
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
卷 66, 期 12, 页码 9641-9650出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2019.2896165
关键词
Automatic optical inspection; computer vision; image classification; machine learning; neural networks
资金
- Italian Department of Continental S.P.A.
This paper introduces an intelligent system able to perform quality control assessment in an industrial production line. Deep learning techniques are employed and proved successful in a real application for the inspection of welding defects on an assembly line of fuel injectors. Starting from state-of-the-art deep architectures and using the transfer learning technique, it is possible to train a network with about 7 million parameters using a reduced number of injector's images, obtaining an accuracy of 97.22%. The system is also configured in order to exploit new data, collected during operation, to extend the existing dataset and to improve further its performance. The developed system shows that deep neural networks can successfully perform quality inspection tasks that are usually demanded to humans.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据