A Labelled training and testing dataset for autonomous non-destructive evaluation for Resistance SPOT welding

10.13139/OLCF/1559947

This dataset contains all the training and testing data generated from 90 videos (over seven sets of welding material stack-ups). A new method is developed to assemble sufficient datasets from these videos for neural network training. These data also contains the ground truth on the weld nuggets, derived from the post-weld measurement and video conversion ratios. More specific technical details can be found in the manuscript: Jian Zhou, Dali Wang, Jian Chen, Zhili Feng. (2019), Autonomous non-destructive evaluation of resistance Spot Welded Joints.

Published: 2019-09-04 11:08:07 Download Dataset

Dataset Properties

Field Value
Authors
  • wang, dali Oak Ridge National Laboratory
  • Zhou, Jian Oak Ridge National Laboratory
  • Chen, Jian Oak Ridge National Laboratory
  • Feng, Zhili Oak Ridge National Laboratory
Project Identifier 311L0207
Dataset Type IP Still Images or Photos
Subjects
  • 42 ENGINEERING
Keywords
  • Non-destructive evaluation
  • SPOT welding
  • Deep neural network
  • Autonomous detection
Originating Organizations Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organizations Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office (EE-3V)
DOE Contract 34715860

Acknowledgements

Papers using this dataset are requested to include the following text in their acknowledgements:

*Support for 10.13139/OLCF/1559947 is provided by the U.S. Department of Energy, project 311L0207 under Contract 34715860. This research used resources of the Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility.