Results of model regression ANOVA

Table 4 presents the BBD (Box-Behnken Design, a response surface experimental design method) test plan and result data related to 3D printing. It covers four key factors, namely A (layer thickness, in mm), B (printing speed, in mm/s), C (substrate temperature, in °C), and D (printing temperature, in °C), along with the corresponding response value Y (dimensional error, in mm). Through this set of data, the aim is to explore the influence of different factors and their interactions on the 3D printing results, which is helpful for analyzing how each factor acts independently and jointly on the final printed part, providing strong data support and reference basis for optimizing 3D printing process parameters and improving printing quality.Table 5 is the regression variance analysis (ANOVA) of this model. The model built for 3D printing-related data is highly significant (p < 0.0001), with an R2 of 0.9946 and an adjusted R2 of 0.9892. This indicates that the model has an excellent fitting degree and can well explain the changes in the dependent variable. Among the factors, the four main factors A, B, C, and D have highly significant effects on the results (p < 0.0001), with factor A having the greatest influence; in terms of interaction, AB, AD, and BC are significant, while AC, BD, and CD are not significant; in the quadratic terms, A2, B2, and D2 are significant, while C2 is not significant. Additionally, the model's misfit term is not significant (p = 0.5022), further verifying the model's reliability and providing a strong basis for precisely regulating 3D printing process parameters.