Model Optimization of Artificial Neural Networks for Performance Predicting in Spot Welding of the Body Galvanized DP Steel Sheets,
This paper focused on the performance predicting problems in the spot welding of the body galvanized DP steel sheets. Artificial neural networks (ANN) were used to describe the mapping relationship between welding parameters and welding quality. After analyzing the limitation existed in standard BP networks, the original model was optimized based on lots of experiments. Lots of experimental data about welding parameters and corresponding spot weld quality were provided to the ANN for study. The results showed that the improved BP model can predict the influence of welding currents on nugget diameters, weld indentation and the shear loads ratio of spot welds. The forecasting precision was so high that can satisfy the practical need of engineering and have some application value.
KeywordsArtificial Neural Network Artificial Neural Network Model Welding Parameter Welding Current Spot Welding
Unable to display preview. Download preview PDF.
- 1.Ivezic, N., Alien, J.D.: Neural network-based resistance spot welding control and quality prediction. Intelligent Processing and Manufacturing of Materials (1999)Google Scholar
- 2.Zhongdian, Z., Yan, L., Xingping, H.: Artificial neural network estimating of spot welding mechanical property, Hanjie Xuebao (1997)Google Scholar
- 4.Marya, M., Gayden, X.Q.: Development of requirements for resistance spot welding dual-phase (DP600) steels. Welding Journal (2005)Google Scholar
- 5.Zhongdian, Z., et al.: Selection of the learning rate when modeling ANN using BP algorithm. Welding (2004)Google Scholar
- 6.Peixian, J.: The study and application of different improved BP algorithms. Nanjing Hangkonghangtian Daxue Xuebao (1994)Google Scholar