Autonomous nondestructive evaluation of resistance spot welded joints

Zhou, Jian; Wang, Dali; Chen, Jian; Feng, Zhili; Clarson, Blair; Baselhuhn, Amberlee

doi:10.1016/j.rcim.2021.102183

Autonomous nondestructive evaluation of resistance spot welded joints

Journal Article · Fri May 21 00:00:00 EDT 2021 · Robotics and Computer-Integrated Manufacturing

DOI:https://doi.org/10.1016/j.rcim.2021.102183· OSTI ID:1813251

Zhou, Jian ^[1]; ^[2]; ^[2]; ^[2]; Clarson, Blair ^[3]; Baselhuhn, Amberlee ^[3]

Rutgers Univ., New Brunswick, NJ (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
General Motors Global RD, Warren, MI (United States)

The application of non-destructive evaluation approaches has attracted strong interests in modern automotive industries. Here, we present an autonomous deep-computing framework to analyze raw videos from infrared systems and to predict weld nugget shape and size with unprecedented accuracy and speed. In a comprehensive training and testing experiment with 90 videos (seven sets of welding material stack-ups), a new method was developed to assemble sufficient datasets for neural network training. Our framework successfully predicts all the nugget shapes with F1 scores that range from 0.84 to 0.92. The total training time on Nvidia DGX station takes less than 10 min for each set of welding material stack-up. The real inference time of an individual dataset (with 30 video frames) takes about 0.005 s. The procedure and methods developed in the study can be applied to other image-based weld property prediction, as well as other manufacturing processes. Furthermore, our well-trained neural networks take limited memory resources (2.3 MB) and are suitable for embedded microprocessors for in-situ welding quality control as edge computing within an intelligent welding framework.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy (NE); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1813251

Alternate ID(s):: OSTI ID: 1784371

Journal Information:: Robotics and Computer-Integrated Manufacturing, Journal Name: Robotics and Computer-Integrated Manufacturing Vol. 72; ISSN 0736-5845

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (14)

Quality evaluation in resistance spot welding by analysing the weld fingerprint on metal bands by computer vision Ruisz, Johannes; Biber, Jürgen; Loipetsberger, Mario The International Journal of Advanced Manufacturing Technology, Vol. 33, Issue 9-10 https://doi.org/10.1007/s00170-006-0522-6	journal	June 2006
Welding defects detection based on deep learning with multiple optical sensors during disk laser welding of thick plates Zhang, Yanxi; You, Deyong; Gao, Xiangdong Journal of Manufacturing Systems, Vol. 51 https://doi.org/10.1016/j.jmsy.2019.02.004	journal	April 2019
Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding Dinham, Mitchell; Fang, Gu Robotics and Computer-Integrated Manufacturing, Vol. 29, Issue 5 https://doi.org/10.1016/j.rcim.2013.01.004	journal	October 2013
Computer vision technology for seam tracking in robotic GTAW and GMAW Xu, Yanling; Fang, Gu; Lv, Na Robotics and Computer-Integrated Manufacturing, Vol. 32 https://doi.org/10.1016/j.rcim.2014.09.002	journal	April 2015
An on-line shape-matching weld seam tracking system Ding, Yaoyu; Huang, Wei; Kovacevic, Radovan Robotics and Computer-Integrated Manufacturing, Vol. 42 https://doi.org/10.1016/j.rcim.2016.05.012	journal	December 2016
Weld bead recognition using laser vision with model-based classification Ye, Guoliang; Guo, Jianwen; Sun, Zhenzhong Robotics and Computer-Integrated Manufacturing, Vol. 52 https://doi.org/10.1016/j.rcim.2018.01.006	journal	August 2018
In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning Pandiyan, Vigneashwara; Murugan, Pushparaja; Tjahjowidodo, Tegoeh Robotics and Computer-Integrated Manufacturing, Vol. 57 https://doi.org/10.1016/j.rcim.2019.01.006	journal	June 2019
A tactual weld seam tracking method in super narrow gap of thick plates Lei, Ting; Huang, Yu; Shao, Wenjun Robotics and Computer-Integrated Manufacturing, Vol. 62 https://doi.org/10.1016/j.rcim.2019.101864	journal	April 2020
A Smart Monitoring System for Automatic Welding Defect Detection Sassi, Paolo; Tripicchio, Paolo; Avizzano, Carlo Alberto IEEE Transactions on Industrial Electronics, Vol. 66, Issue 12 https://doi.org/10.1109/TIE.2019.2896165	journal	December 2019
Weld Quality Inspection Based on Online Measured Indentation From Servo Encoder in Resistance Spot Welding Xinmin, Lai; Xiaoyun, Zhang; Yansong, Zhang IEEE Transactions on Instrumentation and Measurement, Vol. 56, Issue 4 https://doi.org/10.1109/TIM.2007.900423	journal	August 2007
On-line Quality Estimation in Resistance Spot Welding Li, Wei; Hu, S. Jack; Ni, Jun Journal of Manufacturing Science and Engineering, Vol. 122, Issue 3 https://doi.org/10.1115/1.1286814	journal	December 1999
Artificial neural network approach for estimating weld bead width and depth of penetration from infrared thermal image of weld pool Ghanty, P.; Vasudevan, M.; Mukherjee, D. P. Science and Technology of Welding and Joining, Vol. 13, Issue 4 https://doi.org/10.1179/174329308X300118	journal	May 2008
Nondestructive evaluation of resistance spot-welded Al-steel joints Carlson, Blair E.; Haselhuhn, Amberlee S.; Chen, Jian MRS Bulletin, Vol. 44, Issue 8 https://doi.org/10.1557/mrs.2019.179	journal	August 2019
Spot weld analysis with 2D ultrasonic Arrays Denisov, A. A.; Shakarji, C. M.; Lawford, B. B. Journal of Research of the National Institute of Standards and Technology, Vol. 109, Issue 2 https://doi.org/10.6028/jres.109.015	journal	March 2004

Similar Records

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

Dataset · Wed Sep 04 00:00:00 EDT 2019 · OSTI ID:1559947

Learning the Temporal Effect in Infrared Thermal Videos With Long Short-Term Memory for Quality Prediction in Resistance Spot Welding

Conference · Wed Jun 01 00:00:00 EDT 2022 · OSTI ID:2224211

Predicting Nugget Size of Resistance Spot Welds Using Infrared Thermal Videos With Image Segmentation and Convolutional Neural Network

Journal Article · Thu Aug 05 00:00:00 EDT 2021 · Journal of Manufacturing Science and Engineering · OSTI ID:1819527

Related Subjects

42 ENGINEERING
Artificial intelligence
Autonomous prediction
Deep neural network
Nondestructive evaluation
Spot welding

Autonomous nondestructive evaluation of resistance spot welded joints

Citation Formats

References (14)

Similar Records

Related Subjects