Materials used in aircraft engines, gas turbines, nuclear reactors, re-entry vehicles, and hypersonic structures are subject to severe environmental conditions that present significant challenges. With their remarkable properties, such as high melting temperatures, strong resistance to oxidation, corrosion, and ablation, minimal creep, and advantageous thermal cycling behavior, ceramic matrix composites (CMCs) show great promise as a material to meet the strict requirements in these kinds of environments. Furthermore, the addition of boron nitride nanoparticles with continuous fibers to the CMCs can offer thermal resistivity in harsh conditions, which will improve the composites’ strength and fracture toughness. Therefore, in extreme situations, it is crucial to understand the thermal resistivity period of composite materials. To forecast the ablation performance of composites, we developed six machine learning regression methods in this study: decision tree, random forest, support vector machine, gradient boosting, extreme gradient boosting, and adaptive boosting. When evaluating model performance using metrics including R2 score, root mean square error, mean absolute error, and mean absolute percentage error, the gradient boosting and extreme gradient boosting machine learning regression models performed better than the others. The effectiveness of machine learning models as a useful tool for forecasting the ablation behavior of ceramic matrix composites was effectively explained by this study.

In recent years, there has been increasing interest in new materials such as ceramic matrix composites (CMCs) for power generation and aerospace propulsion applications through hydrogen combustion. This study employed a deep artificial neural network (DANN) model to predict the ablation performance of CMCs in the hydrogen torch test (HTT). The study was conducted in three phases to increase the accuracy of the model’s predictions. Initially, to predict the thermal behavior of ceramic composites, two linear machine learning models were used known as Lasso and Ridge regression. In the second step, four decision tree-based ensemble machine learning models, namely random forest, gradient boosting regression, extreme gradient boosting regression, and extra tree regression, were used to improve the prediction accuracy metrics, including root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R² score), and mean absolute percentage error (MAPE), relative to the previously introduced linear models. Finally, to forecast the thermal stability of CMCs with time, an optimized DANN model with two hidden layers having rectified linear unit activation function was developed. The data collection procedure involved preparing CMCs with continuous Yttria-Stabilized Zirconia (YSZ) fibers and silicon carbide (SiC) matrix using a polymer infiltration and pyrolysis (PIP) technique. The samples were exposed to a hydrogen flame at a high heat flux of 183 W/cm² for a duration of 10 min. A good agreement between the DANN model’s predictions and experimental data with an R² score of 0.9671, RMSE of 16.45, an MAE of 14.07, and an MAPE of 3.92% confirmed the acceptability of the developed neural network model in this study.

Hydrogen energy offers high energy density and carbon-free combustion, making it a promising fuel for next-generation propulsion and power generation systems. Hydrogen offers approximately three times more energy per unit mass than natural gas, and its combustion yields only water as a byproduct, making it an exceptionally clean and efficient energy source. Materials used in hydrogen-fueled combustion engines must exhibit high thermal stability as well as resistance to corrosion caused by high-temperature water vapor. This study introduces a novel ceramic matrix composite (CMC) designed for such harsh environments. The composite is made of yttria-stabilized zirconia (YSZ) fiber-reinforced silicoboron carbonitride [Si(B)CN]. CMCs were fabricated via the polymer infiltration and pyrolysis (PIP) method. Multiple PIP cycles, which help to reduce the porosity of the composite and enhance its properties, were utilized for CMC fabrication. The Si(B)CN precursor formed an amorphous ceramic matrix, where the presence of boron effectively suppressed crystallization and enhanced oxidation resistance, offering superior performance than their counter part. Thermogravimetric analysis (TGA) confirmed negligible mass loss (≤3%) after 30 min at 1350 °C. The real-time ablation performance of the CMC sample was assessed using a hydrogen torch test. The material withstood a constant heat flux of 185 W/cm² for 10 min, resulting in a front-surface temperature of ~1400 °C and a rear-surface temperature near 700 °C. No delamination, burn-through, or erosion was observed. A temperature gradient of more than 700 °C between the front and back surfaces confirmed the material’s effective thermal insulation performance during the hydrogen torch test. Post-hydrogen torch test X-ray diffraction indicated enhanced crystallinity, suggesting a synergistic effect of the oxidation-resistant amorphous Si(B)CN matrix and the thermally stable crystalline YSZ fibers. These results highlight the potential of YSZ/Si(B)CN composites as high-performance materials for hydrogen combustion environments and aerospace thermal protection systems.

Ceramic matrix composites (CMCs) are promising thermal-protection materials for hydrogen-fueled gas turbines, where components are exposed to high temperatures, steam-rich combustion products, and pressure-driven heat transfer. This study investigates yttria-stabilized zirconia (YSZ) fiber-reinforced polymer-derived ceramic composites fabricated by polymer infiltration and pyrolysis (PIP) using Durazane-1800 as the preceramic precursor. Eight-layer YSZ preforms were rigidized, vacuum-infiltrated, cured, and pyrolyzed at 950 °C in nitrogen; repeated PIP cycles were used to increase matrix densification. Under hydrogen torch exposure at a heat flux of 180–190 W/cm², the front-face temperature of the CMC coupon reached approximately 1400 °C while the back-face temperature stabilized near 600 °C during a 10 min test, with no observed delamination or burn-through. Post-test SEM/EDS and XRD characterization indicated oxidation of the SiCN matrix and the deposition of a silica-rich substance on the material surface. In a hydrogen-combustion rig, the CMC liner reduced the external wall temperature relative to the unlined wall by approximately 32 °C at 1 atm and 17 °C at 5 atm. Transient thermal simulations reproduced the measured temperature trends with differences of approximately 3.8–7.8% for selected temperatures at 1 atm and 6.2% for the liner back-face temperature at 5 atm. Increasing the number of PIP cycles from two to seven increased fracture strength from 7.87 to 19.77 MPa and flexural modulus from 4.05 to 24.34 GPa. These results demonstrate the potential of YSZ-reinforced polymer-derived CMCs as thermal barriers for hydrogen-combustion environments and identify porosity control as a key requirement for improved high-pressure performance.