Khachatur V. Manukyan

Sintering is widely used to manufacture ceramics for structural, electronic, and energy applications, but coupled densification and grain growth, material-dependent kinetics, and sparse measurements complicate predictive modeling and process design. Without reliable simulation, processing schedules are commonly developed through repeated furnace trials and post-process characterization. Here, we present Sinter-PiNDiff, a retrainable sintering physics-integrated neural differentiable framework for predicting density and grain-size evolution across ceramic systems. Two neural networks learn material-dependent densification and grain-growth coefficients within coupled sintering rate equations, while a smooth density-saturation factor attenuates densification as theoretical density is approached. The common governing structure, network architecture, and training procedure were fitted independently to published measurements for MgO, Al-doped ZnO, and CaO-doped ThO₂. Condition-wise held-out tests evaluate predictions at unseen temperatures and compositions. Sinter-PiNDiff achieved the lowest mean error in all twelve material–metric comparisons with multilayer-perceptron and residual-network baselines. For MgO, Al-doped ZnO, and CaO-doped ThO₂, respectively, density normalized root-mean-square errors were 14.6%, 10.8%, and 14.4%, and grain-size normalized root-mean-square errors were 8.6%, 12.1%, and 19.3%. Removing the evolving density from both neural-network inputs increased both density and grain-size trajectory errors in all three systems and increased ten of the twelve aggregate errors examined, supporting density-dependent kinetic feedback. Deep ensembles estimated model disagreement, although empirical coverage showed that the resulting bands were not calibrated and did not capture all model–data discrepancies. These results establish Sinter-PiNDiff as a retrainable framework for sparse-data prediction and uncertainty-informed selection of sintering conditions.

Irradiation induced structural changes of actinide oxide materials is a key consideration in their development and use as nuclear fuels. This study reported on the synthesis of ThO₂ and Th_1-xU_xO₂ (x = 0.15, 0.50) thin films, fabricated using electrospray-assisted solution combustion synthesis, and their responses to ion irradiation. Krypton ion irradiations, up to a fluence of 1 × 10¹⁶ ions/cm², were carried out to simulate radiation damage induced by fission products in a reactor environment. Structural and chemical changes induced by irradiation were analyzed using high-resolution scanning transmission electron microscopy (STEM), energy-dispersive X-ray spectroscopy (EDS), and electron energy-loss spectroscopy (EELS). It was determined that the extent and nature of irradiation-induced damage are strongly correlated with the uranium content. ThO₂ films were most susceptible to radiation-induced damage, with significant cavity formation and delamination from the substrate at high fluence. Of the compositions studied, Th_0.85U_0.15O₂ films showed the highest stability, characterized by moderate grain growth and the absence of voids or severe defect structures. In contrast, Th_0.5U_0.5O₂ films accumulated extensive damage, including the formation of a nanocrystalline central region. EELS analysis indicated that oxygen displacement is the primary driver of structural degradation in Th_0.5U_0.5O₂ films. α-particle spectroscopy confirmed minimal actinide loss across all compositions, underscoring the mechanical robustness of the films. These findings provide insight into the irradiation-induced damage mechanisms in ThO₂ and Th_1-xU_xO₂ systems, supporting their development as potential materials for nuclear fuels and irradiation-tolerant thin film targets in nuclear physics measurements.