Abstract—Resistance welding is the most commonly used method for joining purpose of steel sheets. Aims to increase efficiency and maintain or reduce the weight of vehicles, Advanced High Strength Steels (AHSS) have been used to build up material for vehicle structures. This research aims to exploit the ability of prediction by using Support Vector Machines (SVM) and comparing to Artificial Neural Network (ANN) model. The experiment result showed that Support Vector Machines has a positive and better predict result compared to ANN. The predict accuracy of SVM is 92% while ANN shows 88.9%.

Index Terms—Resistance spot welding, support vector machines, artificial neural network, prediction.

H. T. Tran and H. J. Yang are with the Department of Computer Science, Chonnam National University, South Korea (e-mail: fami.hut89@gmail.com, hjyang@jnu.ac.kr).
K. Y. Kim is with the Department of Industrial and Systems Engineering, Wayne State University, USA (e-mail: kykim@eng.wayne.edu).

 

Cite:H. T. Tran, K. Y. Kim, and H. J. Yang, "Weldability Prediction of AHSS Stackups Using Support Vector Machines," International Journal of Computer and Electrical Engineering vol. 6, no.3, pp. 207-210, 2014.