Forecasting of the Fatigue Life of Metal Weld Joints Based on Combined Genetic Neural Network

Abstract

For metal weld joints, due to the complex non-linear relationship among the factors which influence the fatigue performance, so it is hard to establish an accurate theoretical model to forecast its fatigue life. Based on the self-learning ability and approximation of non-linear mapping capability of the artificial neural network (ANN) and the powerful ability of global optimization of the genetic algorithm (GA), the paper through optimizing the ANN by GA, establishes combined genetic neural network (GA–ANN). The method establishes the mapping relationship between the fatigue life of metal weld joints and a variety of influencing factors, having greatly increased the computational efficiency for the fatigue life of metal weld joints, also had a higher forecast accuracy. The superiority of this method had been tested by the forecast of the fatigue life of weld joints in different process parameters, the new method to forecast the fatigue life of metal weld joints is proposed.