| 超临界翼型设计中的多响应代理模型 |
| |
| 引用本文： | 吴宽展,;刘学军,;吕宏强.超临界翼型设计中的多响应代理模型[J].航空计算技术,2014(4):17-22. |
| |
| 作者姓名： | 吴宽展 ;刘学军 ;吕宏强 |
| |
| 作者单位： | [1] 南京航空航天大学计算机科学与技术学院,江苏南京210016; [2] 南京航空航天大学航空宇航学院,江苏南京210016 |
| |
| 基金项目： | 国家自然科学基金项目资助（61170152） |
| |
| 摘 要： | 为考虑超临界翼型设计中代理模型多响应之间的相关性,研究了基于多输出高斯过程回归的代理模型。通过实验数据验证了升力系数、阻力系数及力矩系数之间显著的相关性,建立了超临界翼型设计中的基于多输出高斯过程的多响应代理模型,并与kriging模型、BP和RBF两种人工神经网络模型进行了对比。结果表明,当超临界翼型设计中多输出端口之间存在显著的相关性时,多输出高斯过程相比kriging、BP和RBF能有效显著提高预测精度,并获得更加稳定的预测性能。
|
| 关 键 词： | 翼型设计 多输出高斯过程 kriging模型 多响应代理模型 超临界翼型 |
Multi-output Surrogate Model in Supercritical Airfoil Design |
| |
| Institution: | WU Kuan-zhan, LIU Xue-jun, LV Hong-qiang ( 1. College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics ,Nanjing 210016, China ; 2. College of Aerospace Engineering, Nanfing University of A eronautics and Astronautics, Nanjing 21 O016, China ) |
| |
| Abstract: | To consider the correlations between the multi-responses in surrogate model for supercritical airfoil design , this paper studies the surrogate model based on the multi -output Gaussian process （MOGP） regression and verifies the significant correlations between lift coefficient ,drag coefficient and moment coefficient through experimental data .We establish the MOGP-based surrogate model for super-critical airfoil design and compare our model with kriging and other two neural network model , BP and RBF.The results show that the MOGP can significantly improve the prediction accuracy and stability com-pare with kriging ,BP and RBF when the outputs are significantly correlated in supercritical airfoil design . |
| |
| Keywords: | airfoil design MOGP kriging model multi-response surrogate model supercritical airfoil |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
