Abstract

In this paper, a new method is introduced for optimization of a two-stage forging process of an airfoil blade. Geometrical dimensions of preform shape and cavity of the intermediate die were selected as input variables and uniformity of strain distribution, flash volume, and lateral forces were considered as objective functions. Design parameters of the intermediate die cavity were defined by Lagrange interpolation method. Then, using the design of experiments and implementation of proposed tests by the finite element method, the objective function values were obtained and afterwards artificial neural network modeling were applied for extracting the effectiveness of the input variables on the objectives. Finally, optimal amount of preform and intermediate die parameters was achieved using a multi-objective genetic algorithm based on a fuzzy method. Also, by using physical modeling of the optimal conditions, experimental tests of the forging process were executed. Results show that the trained artificial neural network model estimates the process with good accuracy and also, comparison of optimized and non-optimized two-stage forging reveals that in the former condition, flash volume and strain non-uniformity reduced more by 51% and 42%, respectively.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call