期刊
SMART AND SUSTAINABLE MANUFACTURING SYSTEMS
卷 2, 期 1, 页码 137-164出版社
AMER SOC TESTING MATERIALS
DOI: 10.1520/SSMS20180033
关键词
smart manufacturing; transfer learning; defect detection; casting defect detection; weld defect detection; automated surface inspection; convolutional neural networks
资金
- Smart Manufacturing Systems Design and Analysis Program at the National Institute of Standards and Technology (NIST), United States Department of Commerce
- NIST [70NANB17H031]
Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large, openly available image datasets before fine-tuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds the state-of-the art performance of the Grupo de Inteligencia de Maquina database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multitask learning, and multi-class learning influence the performance of the trained system.
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