Neural network modeling of arc spot welding

This study presents neural network (NN) for the prediction of ultimate capacity of arc spot welding. The proposed NN model is based on experimental results. The ultimate capacity of arc spot welding is modeled in terms of weld strength, average welding thickness and diameter. The results of the proposed NN model are later compared with results of existing codes and are found to more accurate. Moreover, the proposed NN model is presented in explicit form as a mathematical function. Parametric studies are also carried out to analyze the effect of each variable. The proposed NN model is a unified formulation valid for governing shear failures. (C) 2007 Elsevier B.V. All rights reserved.