Data-driven prediction of laminar flow and turbulent flow in marine and aerospace engineering has received extensive research and demonstrated its potential in real-time prediction recently. However, usually large amounts of high-fidelity data are required to describe and accurately predict the complex physical information, while reality, only limited high-fidelity data are available due to the high experimental/computational cost. Therefore, this work proposes a novel multi-fidelity learning method based on the Fourier neural operator by jointing abundant low-fidelity data and limited high-fidelity data under transfer learning paradigm. First, as a resolution-invariant operator, the Fourier neural operator is first and gainfully applied to integrate multi-fidelity data directly, which can utilize the limited high-fidelity data and abundant low-fidelity data simultaneously. Then, the transfer learning framework is developed for the current task by extracting the rich low-fidelity data knowledge to assist high-fidelity modeling training, to further improve data-driven prediction accuracy. Finally, three engineering application problems are chosen to validate the accuracy of the proposed multi-fidelity model. The results demonstrate that our proposed method has high effectiveness when compared with other high-fidelity models and has the high modeling accuracy of 99% for all the selected physical field problems. Additionally, the low-fidelity model without transfer learning has the modeling accuracy of 86%. Significantly, the proposed multi-fidelity learning method has the potential of a simple structure with high precision for fluid flow problems, which can provide a reference for the construction of the subsequent model.

This study investigates the underwater explosion resistance of aluminum alloy octet-truss lattice sandwich structures using shock tube experiments and LS-DYNA simulations. A systematic analysis reveals key mechanisms influencing protective performance. The sandwich configuration mitigates back plate displacement through quadrilateral inward deformation, exhibiting phased deformation responses between face plates and back plates mediated by lattice interactions. Increasing the lattice relative density from 0.1 to 0.3 reduces maximum back plate displacement by 22.2%. While increasing the target plate thickness to 1.5 mm reduces displacement by 47.6%, it also decreases energy absorption efficiency by 20% due to limited plastic deformation. Fluid–structure interaction simulations correlate well with 3D-DIC deformation measurements. The experimental results demonstrate the exceptional impact energy absorption capacity of the octet-truss lattice and highlight the importance of stiffness-matching strategies for enhanced energy dissipation. These findings provide valuable insights for optimizing the design of underwater protection structures.

Origami and kirigami are effective approaches to fabricate lightweight cellular metamaterials with extraordinary mechanical properties. However, the novel designs of such metamaterials are still limited. In this paper, a novel metamaterial similar to typical Kelvin foams is proposed and fabricated via origami and kirigami methods, and its mechanical properties are investigated. Quasi-static compression tests are first conducted to analyze the deformation characteristics and stress–strain responses. Numerical simulations are then carried out to simulate the tests. Furthermore, two methods including adjusting the wall thickness and introducing openings are adopted to alter the relative density of the metamaterials, and their influences on the plateau stress and specific energy absorption (SEA) are explored. Finally, analytical studies are conducted to predict the plateau stress, and good agreement between the analytical, numerical, and experimental results are obtained. The results reveal that the kinetic energy is primarily dissipated by unfolding the constitutive elements along the creases, and three typical stages of linear-like elastic, plateau, and densification are generated in the stress–strain curves. Increasing the wall thickness significantly improves the plateau stress and SEA. Introducing smaller openings has minor influences on the plateau stress, while the stress level drops remarkably when the opening size exceeds a critical value. By adopting an appropriate opening size, the increment of the SEA can be up to 29% in comparison with non-opening counterparts. The findings of the present study provide an alternative to fabricating cellular materials with outstanding performance.

Strong shock waves generated during the pyrotechnic separation process of aerospace vehicles can cause high-frequency damage or even structural failure to the vehicle’s structure. Existing structural designs for shock attenuation typically rely on shock response spectra methods, which require multiple finite element calculations to determine the optimal geometric parameters, leading to relatively low efficiency. In this work, we propose a spectral response prediction method for spacecraft structures using the Deep Operator Network (DeepONet). This method preserves the physical relationships between input variables, modularizes geometric and positional input data, and outputs the spectral response. We integrate this neural model to analyze the impact of spacecraft structural parameters on shock resistance performance, revealing that circumferential reinforcement has the most significant influence on shock resistance. Then, we conduct a detailed analysis of the DeepONet model, noting that models with a higher number of neurons per layer train more quickly but are prone to overfitting. Additionally, we find that focusing on specific frequency bands for spectral response prediction yields more accurate results.

Three-dimensional lattice structures display outstanding mechanical attributes and deformation behaviors, making them viable options in aerospace engineering due to their effectiveness as lightweight load-supporting elements and vibration dampening systems. Inspired by the sturdy framework of Arapaima scales, celebrated for their exceptional mechanical qualities, this research presents a new energy-dissipating three-dimensional lattice configuration. A thorough examination of the compressive responses of this pioneering structure is performed using a diverse methodology that includes theoretical computations, empirical assessments, and computational modeling. Mathematical derivations clarifying the elastic modulus of the structure are developed through detailed stress analysis frameworks. Utilizing selective laser melting technology with 304 stainless steel, three variants of three-dimensional lattice structures are produced: the bio-inspired design, a negative Poisson ratio configuration, and a design incorporating BCC cellular units. A detailed finite element analysis was conducted to explore the deformation process and predict potential failure points. The theoretical estimation, simulation results and experimental data of the elastic modulus are consistent. The findings demonstrate the superior mechanical characteristics and notable energy absorption potential embedded in the innovative three-dimensional lattice structure. These results not only validate the effectiveness of this configuration but also lay a critical groundwork for future innovations in structural designs within the aerospace field.