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

dali wang | Oak Ridge National Laboratory

Jian Zhou | Oak Ridge National Laboratory

Jian Chen | Oak Ridge National Laboratory

Zhili Feng | Oak Ridge National Laboratory

Description

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.

Funding Information

DOE Contract Number

AC05-00OR22725

Originating Research Organization

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization

Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office (EE-3V)

Details

DOI

https://doi.org/10.13139/OLCF/1559947

Release Date

September 4, 2019

Subject

42 ENGINEERING

Keywords

Non-destructive evaluation, SPOT welding, Deep neural network, Autonomous detection

Dataset

Dataset Type

IP Still Images or Photos

Other Contract Number(s)

34715860

Other ID Number(s)

311L0207

Cite This Dataset:

wang, d., Zhou, J., Chen, J., Feng, Z. (2019). A Labelled training and testing dataset for autonomous non-destructive evaluation for Resistance SPOT welding. Oak Ridge National Laboratory. https://doi.org/10.13139/OLCF/1559947.

Acknowledgements

This research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Advanced Scientific Computing Research programs in the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.