This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Weldability Prediction of AHSS Stackups Using Artificial Neural Network Models
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 16, 2012 by SAE International in United States
Annotation ability available
Typical automotive body structures use resistance spot welding for most joining purposes. New materials, such as Advanced High Strength Steels (AHSS) are increasingly used in the construction of automotive body structures to meet increasingly higher structural performance requirements while maintaining or reducing weight of the vehicle. One of the challenges for implementation of new AHSS materials is weldability assessment. Weld engineers and vehicle program teams spend significant efforts and resources in testing weldability of new sheet metal stack-ups. In this paper, we present a methodology to determine the weldability of sheet metal stack-ups using an Artificial Neural Network-based tool that learns from historical data. The paper concludes by reviewing weldability results predicted by using this tool and comparing with actual test results.
CitationSohmshetty, R., Ramachandra, R., Coon, T., Kim, K. et al., "Weldability Prediction of AHSS Stackups Using Artificial Neural Network Models," SAE Technical Paper 2012-01-0529, 2012, https://doi.org/10.4271/2012-01-0529.
- Resistance Spot Welding - American Welding Society (Feb 1999)
- American Welding Society Specification for Automotive Weld Quality - RSW of Steel
- Heaton, J., “Introduction to Neural Networks for Java,” 2nd edition, 2007.
- CinDi lab of Wayne State University, “Literature review of java based Artificial Neural Networks”
- Resistance Spot Welding Simulation - Ford Internal Technical report.
- Rodrigues, Jõao, Nogueira, António, Salvador, Paulo, “Improving the Traffic Prediction Capability of Neural Networks using Sliding Window and Multi-task Learning Mechanisms,” 2010 Second International Conference on Evolving Internet.
- Heider, Dominik, Verheyen, Jens, and Hoffmann, Daniel, “Predicting Bevirimat resistance of HIV-1 from genotype,” BMC bioinformatics 2010, 11:37. doi:10.1186/1471-2105-11-37.
- Ivo, M. L. Ferreira, Gil, Paulo J. S., “Decision Support Tool for Conceptual Design using Neural Networks”
- Baş, Cem, Arslan, Güvenç, Muluk, Zehra F., “ON MULTIPLE RESPONSE OPTIMIZATION: DESIRABILITY FUNCTIONS AND ARTIFICIAL NEURAL NETWORKS,” 24th Mini EURO Conference, June 23-26, 2010, Izmir, Turkey
- Ramos-Pollán, R., Franco, J.M., Sevilla, J., Guevara-López, M.A., González de Posada, N., Loureiro, J., Ramos, I., “Grid infrastructures for developing mammography CAD systems,” 32nd Annual International Conference of the IEEE EMBS Buenos Aires, Argentina, August 31 - September 4, 2010, pp 3467-3470.
- Encog online document (http://www.heatonresearch.com/dload/ebook/IntroductionToEncogJava.pdf)