A kriging modeling method is proposed to conduct the temperature uncertainty analysis of an injection mechanism in squeeze casting. A mathematical model of temperature prediction with multi input and single output is employed to estimate the temperature spatiotemporal distributions of the injection mechanism. The kriging model applies different weights to the independent variables according to spatial location of sample points and their correlation, thus reducing the estimation variance. The predicted value of the kriging model is compared with the sample data at the corresponding position to investigate the influence of the temperature uncertainty of the injection mechanism on the injection process including friction. The results indicate that the significant error is observed at a few sample points in the early injection due to the impact of the uncertainty facts. The variance mean and standard deviation obtained by the model calibrated by experimental samples reduce largely in comparison to those obtained from the initial kriging model. This study indicates that model calibration produces more accurate prediction.
Keywords: friction; injection mechanism; kriging modeling; numerical simulation; squeeze casting; uncertainty.