Skip to main content

Research Repository

Advanced Search

Deep learning-based defect inspection in sheet metal stamping parts

Singh, Aru Ranjan; Bashford-Rogers, Thomas; Hazra, Sumit; Debattista, Kurt

Authors

Aru Ranjan Singh

Sumit Hazra

Kurt Debattista



Abstract

Defect inspection is a crucial step in sheet metal stampingmanufacturing. However, current inspection methods largely consist of visual inspection by trained operatives but are unreliable and prone to error. Computer vision techniques have the potential advantage of utilising low cost hardware to enable accurate classification of defects particularly through using techniques such as deep learning. Currently, the use of convolutional neural networks (CNN) is one of the best methods in the field of computer vision for classification tasks. Despite the advantages, vision-based deep learningmodels for detecting defects in sheet material are currently limited to flat sheet materials and certain classes of surface defects such as scratches and delamination. This research proposes a practical deep learningapproach for classification of cracks in realistically formed sheet metal stampingcomponents and suggests a route towards reliable and automated inspections in sheet metal stamping. This study used ResNet18, a state-of-the-art deep learningmodel to classify split defects in “Nakajima” stamped components. The model was able to achieve a 99.9 % accuracy on validation set, which implies that this technique could be suitable for automated defect detection on stamped metal parts.

Citation

Singh, A. R., Bashford-Rogers, T., Hazra, S., & Debattista, K. (2022). Deep learning-based defect inspection in sheet metal stamping parts. In NUMISHEET 2022 Proceedings of the 12th International Conference and Workshop on Numerical Simulation of 3D Sheet Metal Forming Processes (411-419). https://doi.org/10.1007/978-3-031-06212-4_38

Conference Name NUMISHEET 2022 12th International Conference and Workshop on Numerical Simulation of 3D Sheet Metal Forming Processes
Conference Location Sheraton Centre Toronto Hotel, Toronto, Ontario, Canada
Start Date Jul 10, 2022
End Date Jul 14, 2022
Acceptance Date Apr 7, 2022
Online Publication Date Jul 1, 2022
Publication Date 2022
Deposit Date Sep 21, 2022
Publicly Available Date Jul 2, 2024
Publisher Springer
Pages 411-419
Series Title The Minerals, Metals & Materials Series
Series ISSN 2367-1181
Book Title NUMISHEET 2022 Proceedings of the 12th International Conference and Workshop on Numerical Simulation of 3D Sheet Metal Forming Processes
Chapter Number 38
ISBN 9783031062117; 9783031062124
DOI https://doi.org/10.1007/978-3-031-06212-4_38
Keywords Deep learning, Sheet metal stamping, Industrial inspection, Image classification
Public URL https://uwe-repository.worktribe.com/output/9997140
Publisher URL https://link.springer.com/chapter/10.1007/978-3-031-06212-4_38
Related Public URLs https://www.springer.com/series/15240

https://www.tms.org/portal/Meetings___Events/2021/NUMISHEET2021/default.aspx
Additional Information First Online: 1 July 2022