Modeling and optimization of the spring-back in creep forming process of tailor machined blanks for aluminum alloy 7075 using adaptive neuro-fuzzy inference system and particle swarm algorithm

The forming of tailor machined blanks due to the different thicknesses is more complex than the monolithic sheets. The presence of two sections with different thicknesses leads to different formability behaviors and consequently their different spring-backs. Therefore, it is important to examine the spring-back in the thin and thick sections of tailor machined blanks in order to minimize the spring-back value. In this paper, an adaptive neural-fuzzy inference system is used to model the effect of important parameters to predict the percent of spring-back corresponding to the thin and thick sections on the creep age formed tailor machined blanks. In addition, the obtained model is used to optimize the creep forming process using particle swarm optimization algorithm. In order to model the process behavior, some experiments have been performed on the creep forming of tailor machined blanks. The accuracy of the obtained model is investigated using different figures as well as by the specific criteria , , , and .