Journal Published Online: 25 October 2018
Volume 2, Issue 1

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

CODEN: SSMSCY

Abstract

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 Máquina 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.

Author Information

Ferguson, Max
Civil and Environmental Engineering, Stanford University, Stanford, CA, USA
Ak, Ronay
Systems Integration Division, National Institute of Standards and Technology, Gaithersburg, MD, USA
Lee, Yung-Tsun Tina
Systems Integration Division, National Institute of Standards and Technology, Gaithersburg, MD, USA
Law, Kincho H.
Civil and Environmental Engineering, Stanford University, Stanford, CA, USA
Pages: 28
Price: Free
Related

ASTM License Agreement

Reprints and Permissions
Reprints and copyright permissions can be requested through the
Copyright Clearance Center
Details
Stock #: SSMS20180033
ISSN: 2520-6478
DOI: 10.1520/SSMS20180033
Copyright © 1996 - 2024 ASTM. All Rights Reserved. ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA, 19428-2959 USA