12 March 2024 in Aerospace Science and Technology
1 January 2024 in Physics of Fluids
Conducting large-scale numerical computations to obtain flow field during the hypersonic vehicle engineering design phase can be excessively costly. Although deep learning algorithms enable rapid flow field prediction with high-precision, they require a significant investment in training samples, contradicting the motivation of reducing the cost of acquiring flow field. The combination of feature extraction algorithms and regression algorithms can also achieve high-precision prediction of flow fields, which is more suitable to tackle three-dimensional flow prediction with a small dataset. In this study, we propose a reduced-order model (ROM) for the three-dimensional hypersonic vehicle flow prediction utilizing proper orthogonal decomposition to extract representative features and Gaussian process regression with improved automatic kernel construction (AKC-GPR) to perform a nonlinear mapping of physical features for prediction. The selection of variables is based on sensitivity analysis and modal assurance criterion. The underlying relationship is unveiled between flow field variables and inflow conditions. The ROM exhibits high predictive accuracy, with mean absolute percentage error (MAPE) of total field less than 3.5%, when varying altitudes and Mach numbers. During angle of attack variations, the ROM only effectively reconstructs flow distribution by interpolation with a MAPE of 7.02%. The excellent small-sample fitting capability of our improved AKC-GPR algorithm is demonstrated by comparing with original AKC-GPRs with a maximum reduction in a MAPE of 35.28%. These promising findings suggest that the proposed ROM can serve as an effective approach for rapid and accurate vehicle flow predicting, enabling its application in engineering design analysis.
20 April 2024 in International Journal of Aerospace Engineering
Two problems exist in the study of the trajectory optimization problem of powered hypersonic gliding vehicles (HGVs) due to insufficient consideration of the overall design constraints as well as the strong couplings among relevant disciplines: (1) the engine and thrust models are not compatible with the existing HGV; (2) configuration parameters of the HGV are not included as design variables during trajectory optimization (i.e., propulsion discipline is decoupled in the process of the HGV configuration design), thus failing to fully explore the effect of power to improve the performance of the HGV. Therefore, the application of multidisciplinary design optimization (MDO) in the overall design of powered HGVs should be investigated. First, a MDO task analysis and a multidisciplinary model analysis are carried out for the powered HGV. Second, the multidisciplinary optimization problem is defined, and the couplings between disciplines of the powered HGV are analyzed so that a six-discipline model is established that is suitable for the overall design process, including the parameterized configuration geometry, aerodynamics, propulsion, mass properties, trajectory, and aerodynamic heat/thermal protection system (TPS). Finally, a surrogate model is used to replace the time-consuming accurate model, and numerical optimization examples verify the effectiveness of the method. The optimization results show that the method has a good convergence speed, which increases the gliding range of the optimized vehicle by 8.37%. In addition, by decoupling the propulsion discipline, the validation shows that the coupled propulsion discipline during the overall design can increase the range of the powered HGV by 3.87% compared to the powered HGV optimized with the decoupled propulsion discipline. The work done in this paper provides a new design idea for the overall design of a powered HGV.
23 September 2025 in Aerospace Science and Technology
1 April 2026 in Physics of Fluids
With the growing demand for hypersonic vehicle design, efficient aerodynamic optimization is increasingly important. Surrogate-based optimization offers a promising means for low-cost and rapid design, yet its accuracy is often sensitive to sample size, and the high computational cost of generating sufficient high-fidelity data limits practical efficiency. Although wall-quantity-based models can reduce reliance on training samples, they frequently suffer from low predictive accuracy under small-sample conditions and lack effective synergy with aerodynamic coefficient models, restricting their predictive capability. To address these challenges, this study proposes a variable-fidelity modeling method that integrates wall-quantity information. The framework combines a ConvNeXt-based wall-quantity prediction model with transfer learning to provide low-fidelity data, together with an improved Gaussian process regression algorithm incorporating automatic kernel construction to capture correlations across fidelity levels. Validation results demonstrate that the proposed method approximates optimal reference values using only 24 low-fidelity and ten high-fidelity samples, with a computational cost of 355.56 central processing unit (CPU) core-hours. Compared with a conventional high-fidelity-only approach requiring 20 samples and 497.78 CPU core-hours, the proposed method reduces computational cost by 28.57% while maintaining accuracy. These findings highlight its effectiveness in achieving efficient and high-precision aerodynamic optimization under small-sample conditions.