摘要
The work devises a novel velocity-prediction lightweight diffusion model (VPLDM) for three-dimensional aircraft aerodynamic inverse design under high-dimensional variable constraints. The model uses a lightweight diffusion modeling paradigm based on a multilayer perceptron, and reconstructs the noise predictions of traditional diffusion models into velocity predictions, which improves the design efficiency and design accuracy. Trained on a dataset of three-dimensional aircraft, the model is able to generate new samples from random vectors that meet the constraints of specific aerodynamic performance indicators. VPLDM achieves higher design accuracy while demonstrating approximately 4 times higher sampling efficiency compared to Denoising Diffusion Probabilistic Model. The model can also generate aircraft schemes with significantly different geometries in the design space, which confirms the typical non-uniqueness of solutions to the aerodynamic inverse design problem for aircraft. All generated shapes satisfy the desired aerodynamic characteristics, demonstrating the role of VPLDM in the three-dimensional aircraft aerodynamic inverse design.
| 源语言 | 英语 |
|---|---|
| 期刊论文编号 | 113125 |
| 期刊 | Engineering Applications of Artificial Intelligence |
| 卷 | 163 |
| DOI | |
| 出版状态 | 已出版 - 1 1月 2026 |
学术指纹
探究 'A velocity-prediction lightweight diffusion model for three-dimensional aircraft aerodynamic inverse design' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver