BlendedNet
收藏资源简介:
BlendedNet是一个公开的高分辨率表面空气动力学数据集,包含999个独特的混合翼身(BWB)几何形状,每个几何形状在约9个不同的空气动力学情况下进行模拟,总共产生了8830个成功收敛的情况。该数据集使用高保真雷诺平均纳维-斯托克斯(RANS)模拟生成,并采用Spalart-Allmaras湍流模型,每个案例使用900万至1400万个体积单元。该数据集可用于BWB飞机的空气动力学分析,并支持数据驱动代理模型方法的研究。BlendedNet旨在解决BWB飞机空气动力学设计中的数据稀缺问题,并为未来研究提供综合基准。数据集在哈佛Dataverse上公开发布。
BlendedNet is a publicly available high-resolution surface aerodynamics dataset comprising 999 unique Blended Wing Body (BWB) geometries. Each geometry was simulated under approximately 9 distinct aerodynamic conditions, resulting in a total of 8830 successfully converged simulation cases. This dataset was generated using high-fidelity Reynolds-Averaged Navier-Stokes (RANS) simulations with the Spalart-Allmaras turbulence model, with each case utilizing 9 to 14 million volume cells. It can be used for aerodynamic analysis of BWB aircraft and supports research on data-driven surrogate modeling methods. BlendedNet aims to address the data scarcity issue in the aerodynamic design of BWB aircraft and provides a comprehensive benchmark for future research. The dataset is publicly released on Harvard Dataverse.




