This study applies the finite element method (FEM) in conjunction with an abductive network to predict the surface parameters for strain hardening material of asperity flattening in metal forming process. To verify the prediction of FEM simulation for surface parameters, the experimental data are compared with the results of current simulation. Contact area ratio, surface roughness, skewness and kurtosis are investigated for different process and material parameters, such as normal pressure, bulk strain rate, yielding stress, strength coefficient and strain hardening exponent of surface asperity flattening in metal forming, by finite element analysis. The abductive network is then utilized to synthesize the data sets obtained from numerical simulations, and the prediction model is established for predicting surface parameters. The predicted results of the surface parameters from the prediction model are in good agreement with the results obtained from the FEM simulation.