The Data-Driven Performance Prediction of Lattice Structures: The State-of-the-Art in Properties, Future Trends, and Challenges

Aerospace, Год журнала: 2025, Номер 12(5), С. 390 - 390

Опубликована: Апрель 30, 2025

Lattice structures, with their unique design, offer properties like a programmable elastic modulus, an adjustable Poisson’s ratio, high specific strength, and large surface area, making them the key to achieving structural lightweighting, improving impact resistance, vibration suppression, maintaining thermal efficiency in aerospace field. However, functional prediction inverse design remain challenging due cross-scale effects, extensive spatial freedom, computational costs. Recent advancements AI have driven progress predicting lattice structure functionality. This paper begins introduction types, properties, applications. Then development process for performance-prediction methods of structures is summarized. The current applications methods, which are data-driven related material performance under conditions coupled multi-physical fields, analyzed, this analysis further extends relation summarizes application mechanical, energy absorption, acoustic, structures; elaborates on these optimization field; details relevant theory references field analysis. Finally, problems research demonstrated, future direction envisioned.

Язык: Английский

---

Experiment and numerical investigation on beetle elytra inspired lattice structure: Enhanced mechanical properties and customizable responses

Thin-Walled Structures, Год журнала: 2024, Номер 203, С. 112241 - 112241

Опубликована: Июль 18, 2024

Язык: Английский

---

Simple arithmetic operation in latent space can generate a novel three-dimensional graph metamaterials

npj Computational Materials, Год журнала: 2024, Номер 10(1)

Опубликована: Окт. 8, 2024

Recent advancements in artificial intelligence (AI)-based design strategies for metamaterials have revolutionized the creation of customizable architectures spanning nano- to macro-scale dimensions. However, their increasing complexity poses challenges generating diverse metamaterials, hindering widespread adoption. Here, we introduce an innovative strategy three-dimensional graph through simple arithmetic operations within latent space. By leveraging carefully designed hidden representations disentangled space and diffusion processes, our method unravels complexity, with comprehensive understanding. This versatile methodology facilitates ranging from repetitive lattices functionally graded materials. We believe that this represents a foundational step advancing comprehension intricate space, offering potential establish unified model various traditional generative models realm metamaterials.

Язык: Английский

---

A deep learning model to extract the interphase’s characteristics in microstructures using macroscopic responses

Extreme Mechanics Letters, Год журнала: 2024, Номер 71, С. 102203 - 102203

Опубликована: Июль 14, 2024

Язык: Английский

---

Mechanical properties and prescribed design of a star-shaped re-entrant honeycomb based on multi-objective optimization

Materials Today Communications, Год журнала: 2024, Номер 40, С. 110091 - 110091

Опубликована: Авг. 1, 2024

Язык: Английский

---