In resistance spot welding (RSW), data inconsistency is a well-known issue. Such inconsistent data are usually treated as noise and removed from the original dataset before conducting analyses or constructing prediction models. This may not be desirable for all design and manufacturing applications since data that are often considered noise can contain important information in determining weldment design, and proper welding conditions. In this paper, we present the Meta2 prediction framework to provide cost-effective opportunities for proper welding material and condition selection from the noisy RSW quality data. The Meta2 framework employs bootstrap aggregating with support vector regression (SVR) to improve the prediction accuracy on the noisy RSW data with computational efficiency. Hyper-parameters for SVR are selected by particle swarm optimization (PSO) with meta-modeling to reduce the computational cost. Experiments on three artificially generated noisy datasets and a real RSW dataset indicate that Meta2 is capable of providing satisfactory solutions with a noticeably reduced computational cost. The authors find Meta2 promising as a potential prediction model algorithm for this type of noisy data.
Skip Nav Destination
Article navigation
October 2017
Research-Article
Prediction Modeling Framework With Bootstrap Aggregating for Noisy Resistance Spot Welding Data
Kyoung-Yun Kim
Kyoung-Yun Kim
Department of Industrial and
Systems Engineering,
Wayne State University,
4815 Fourth Street,
Detroit, MI 48202
e-mail: kykim@eng.wayne.edu
Systems Engineering,
Wayne State University,
4815 Fourth Street,
Detroit, MI 48202
e-mail: kykim@eng.wayne.edu
Search for other works by this author on:
Junheung Park
Kyoung-Yun Kim
Department of Industrial and
Systems Engineering,
Wayne State University,
4815 Fourth Street,
Detroit, MI 48202
e-mail: kykim@eng.wayne.edu
Systems Engineering,
Wayne State University,
4815 Fourth Street,
Detroit, MI 48202
e-mail: kykim@eng.wayne.edu
1Corresponding author.
Manuscript received December 28, 2016; final manuscript received May 8, 2017; published online August 24, 2017. Assoc. Editor: Robert Gao.
J. Manuf. Sci. Eng. Oct 2017, 139(10): 101003 (11 pages)
Published Online: August 24, 2017
Article history
Received:
December 28, 2016
Revised:
May 8, 2017
Citation
Park, J., and Kim, K. (August 24, 2017). "Prediction Modeling Framework With Bootstrap Aggregating for Noisy Resistance Spot Welding Data." ASME. J. Manuf. Sci. Eng. October 2017; 139(10): 101003. https://doi.org/10.1115/1.4036787
Download citation file:
Get Email Alerts
Related Articles
Impact Welding of Aluminum Alloys 6061 and 5052 by Vaporizing Foil
Actuators: Heat-Affected Zone Size and Peel Strength
J. Manuf. Sci. Eng (October,2015)
Modeling of Friction Self-Piercing Riveting of Aluminum to Magnesium
J. Manuf. Sci. Eng (June,2016)
Parameter Identification of Ship Maneuvering Model Based on Support Vector Machines and Particle Swarm Optimization
J. Offshore Mech. Arct. Eng (June,2016)
Thermal Mechanical Modeling of the Plunge Stage During Friction-Stir Welding of Dissimilar Al 6061 to TRIP 780 Steel
J. Manuf. Sci. Eng (October,2015)
Related Proceedings Papers
Related Chapters
Concluding Remarks and Future Work
Ultrasonic Welding of Lithium-Ion Batteries
Motion Analysis for Multilayer Sheets
Ultrasonic Welding of Lithium-Ion Batteries
Defining Joint Quality Using Weld Attributes
Ultrasonic Welding of Lithium-Ion Batteries