Prediction of the Bending Capability of Rolled Metal Sheet by Genetic Programming

The paper proposes genetic programming (GP) to predict the bending capability of rolled titanzinc metal sheet. In this study ZnTiCu alloy with ∼ 0.1% Cu and ∼ 0.1% Ti was used for production of metal sheet. Three groups of independent input variables were measured: (1) chemical composition of the ZnTiCu alloy during casting (percentage of Cu, Ti, and Fe), (2) parameters of hot rolling (temperature of ingot before rolling, time of rolling, temperature of plate after rolling, time of cooling), and (3) parameters of cold rolling (temperature of plate before rolling, temperature of sheet after rolling). Therefore, nine input variables (parameters) influence the bending capability of the sheet metal. On the basis of the experimental data, several models for prediction of the bending capability of titanzinc metal sheet were developed by the simulated evolution. The influence of individual input variables on bending capability was also studied. The most accurate model was verified with an independent testing data set. The results showed that GP is a powerful tool for predicting the bending capability of metal sheet.