Optimization of shape rolling sequences by integrated artificial intelligent techniques

The present work introduces an expert system that automatically selects and designs rolling sequences for the production of square and round wires. The design strat- egy is aimed at reducing the overall number of passes assuming a series of process constraints, e.g., available roll cage power and torque, rolls groove filling behaviors, etc. The method is carried out into two steps: first a genetic algorithm is used to select the proper rolling sequence allowing to achieve a desired finished product; then, an optimization roll pass design tool is utilized for proper design of roll passes. Indeed, an artificial neural network (ANN) is utilized to predict the main geometrical character- istics of the rolled semi-finished product and technological requirements. The ANN was trained with a non-linear finite element (FE) model. The proposed methodology was ap- plied to some industrial cases to show the validity of the proposed approach in terms of reduction of number of passes and search robustness.