A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding contitions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership fuction parameters and a least squares methods to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization by means of an optimization data set and verified by means of a test data set that was different (independent) from training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.Keywords: Dissimilar metal welding, finite element analysis, fuzzy neural network, genetic algorithm, residual stress, subtractive clustering.Man Gyun Na, Jin Weon Kim and Dong Hyuk Lim
