Shrinkage greatly influences the mechanical and fatigue properties of compacted graphite iron and it is necessary in order to study the causes of shrinkage in compacted graphite iron and to predict it effectively. In this paper, a kind of cylindrical necking test sample was designed to evaluate the shrinkage in compacted graphite iron, and a method to calculate the size of shrinkage was proposed. By observing the microstructure around the shrinkage zone, it is concluded that concentrated shrinkage mainly appears in the solidification region where the dendritic gap is closed, and the isolated shrinkage mainly occurs in the final solidification region, and the supersaturated carbon elements are gathered on the surface of the shrinkage. The cause of shrinkage in compacted graphite iron is caused by its solidification method, where the austenite dendrites and the eutectic clusters are generated close to the melt zone during the solidification process, leading to the inability to feed the shrinkage. Based on the thermodynamic analysis, the equations between the volume change of each phase, solid phase rate, and time during solidification of compacted graphite iron were established to theoretically explain the formation mechanism of the shrinkage. Taking nine parameters such as the chemical elements and characteristic values of thermal analysis as the input nods, a four-layer BP neural network model for predicting the size of shrinkage in compacted graphite iron was constructed, and the R-squared of the model reached 97%, which indicates it could be used to predict the shrinkage tendency.

Two-dimensional metallography cannot be used to determine how graphite volume is partitioned among three-dimensional connected structures in compacted graphite iron (CGI), even when the conventional graphite fractions are similar. This study therefore uses archived micro-CT data to determine whether 75FeSi additions in thermal analysis specimens alter the three-dimensional distribution of graphite volume. Three spherical specimens were cast from an industrial CGI melt with 0, 0.15, and 0.30 wt.% 75FeSi placed at the bottom of the specimen cavity. Center coupons were examined using a ZEISS Xradia 620 Versa X-ray microscope, and the retained reconstructed volumes had 3.0 µm isotropic voxels. We decoded the archived Dragonfly volumetric datasets, removed inactive historical labels, and calculated number-weighted and volume-weighted size, concentration, and shape descriptors. Graphite volume fraction remained within 8.56–8.83%, whereas connected object number density changed from 9764 mm⁻³ without additional 75FeSi to 5739 and 6854 mm⁻³ at 0.15 and 0.30 wt.%, respectively. Number-weighted median diameter remained near 13 µm, but volume-weighted D90 increased from 185.0 to 454.7 and 501.9 µm. The largest connected object contained 3.42%, 20.30%, and 31.39% of graphite volume, respectively. The main contribution is a specimen-level three-dimensional graphite volume-partitioning signature that separates graphite amount from graphite connectivity and upper-tail concentration. The results show that similar total graphite fractions can correspond to different internal graphite architectures, which conventional planar measurements cannot resolve.