International Journal of Materials Engineering and Technology
-->
Abstract: An orthogonal
experiment was performed for the optimization of chemical composition of
heat-treated chromium white cast iron. The prediction capacities of the models
for the regression analysis and artificial neural network (ANN) were
investigated. The results show that Cr significantly influences the
wear-resistant performance. The theoretical optimal composition is 7%Cr, 3.5%Si,
0.6%Mn and 0.5%Cu. The predicted and simulated results indicate that the ANN can
be used to establisharobustmodelforanorthogonal experiment. In addition, it is proved that
this ANN model is more accurate than regression analysis.
Keywords and phrases: wear-resistant performance, chromium white cast iron, orthogonal design, artificial neural network.