军事知识服务平台
基于点云表征的典型气动构型压力系数分布预测
摘要 表面压力系数分布的高效准确预测对飞行器设计快速迭代具有重要意义,数据驱动的深度学习方法在该领域已经展现出显著优势.但现有方法在复杂外形表征的通用性和网格密度的泛化性方面存在局限,一定程度上限制了其工程适用性.针对上述挑战,本文采用点云数据表征几何输入,凭借其天然适用于统一表征不同二维/三维气动构型的优势,构建表面压力系数分布预测模型.通过对点云坐标的扩维实现特征增强,并运用对称函数"Max-pooling"提取几何的全局特征,实现了从点云坐标到压力系数的映射.研究以翼型和机翼等典型气动构型为测试算例,结果证明该模型预测精度高,对外形的泛化性好.对于CST参数扰动翼型,模型预测误差最多可降低为传统参数化建模方法的1/3;对于外形差异显著的UIUC翼型,当参数化建模方法失效时,点云模型预测平均误差仍可控制在约1.5%;此外,对于机翼测试算例,预测误差也能保持在2.5%以下.最后,本文证明该模型具有较好的点云密度泛化性,对不同离散密度的几何点云预测鲁棒性强.该工作突破了变构型压力系数分布的准确、快速预测,为飞行器表面分布载荷预测大模型设计奠定架构基础.
Abstract:
Data-driven approaches have shown great advantage in rapidly and accurately predicting pressure coefficient distributions,which is of crucial importance to efficient aircraft design.Nevertheless,most data-driven approaches still encounter limitations in characterizing diverse aerodynamic configurations and adapting to varying grid densities,which have hindered their engineering applicability.In response to these challenges,this work adopts point clouds,a specific type of geometric data structure that is inherently suitable for uniformly characterizing diverse 2D/3D geometric shapes as the input for deep learning-based prediction of pressure coefficient distribution.By augmenting the dimensions of point cloud co-ordinates for local feature enhancement and utilizing the symmetric function"max pooling"to extract global features,the proposed aerodynamic model establishes the mapping between point cloud coordinates and pressure coefficients.Basic aerodynamic configurations like airfoils and wings are employed as test cases,the results demonstrate that the proposed model achieves both high accuracy and robust generalizability across variable geometries.For class-shape transformation-perturbed airfoils,the prediction error can be reduced to one-third of that of the conventional parameterization-based model.For airfoils selected in the University of Illinois Urbana-Champaign airfoil dataset,among which airfoil profiles are widely distributed,the average error of the proposed approach remains approximately 1.5%,whereas the parameterization-based model may fail.For wings,the prediction error still stays below 2.5%.Finally,the model exhibits strong robustness and generalizability across different point cloud densities.In conclusion,this work makes a breakthrough in predicting pressure coefficient distribution for variable geometric configurations,establishing the foundational framework for designing a large model capable of predicting distributed aerodynamic loads in aerospace applications.
刊 名 力学学报(英文版) ISTICEISCI
年,卷(期): 2026, 42(7)
机标分类号: V218 TP391.41 TP273
在线出版日期: 2026年8月18日