本文应用响应面方法完成了某叶片扩压器的优化设计.通过改变叶片数和出口安装角构造扩压器,进行CFD分析,建立样本数据.基于不同的样本数,用响应面方法寻求的最佳设计点在大致相同的区域,而且与CFD分析结果相比误差很小.表明,响应面方法可以通过较少的样本准确拟合设计变量与响应变量的关系,在流体机械性能预测和多变量优化设计问题中有很好的应用前景.
参考文献
| [1] | Shyy W;Tucker P K;Vaidyanathan R.Response Surface and Neural Network Techniques for Rocket Engine Injector Optimization[A].,1999:99-2455. |
| [2] | Papila N;Shyy W;Haftka R.Assessment of Neural Net and Polynomial-Based Techniques for Aerodynamic Applications[A].,1999:99-3167. |
| [3] | Vaidyanathan R;Papila N;Shyy W.Neural Network and Response Surface Methodology for Rocket Engine Component Optimization[A].Paper No.2000-4880,Long Beach,CA,2000 |
| [4] | Papila N;Shyy W;Griffin L.Preliminary Design Optimization for a Supersonic Turbine for Rocket Propulsion[A].Huntsville,AL,2000 |
| [5] | Madsen JI.;Haftka RT.;Shyy W. .Response surface techniques for diffuser shape optimization[J].AIAA journal,2000(9):1512-1518. |
| [6] | Papila N;Shyy W;Griffin L.Shape Optimization of Supersonic Turbines Using Response Surface and Neural Network Methods[A].,2001 |
| [7] | Nateri K Madavan;Man Mohan Rai;Frank W Huber .Neural Net-Based Redesign of Transonic Turbines for Improved Unsteady Aerodynamic Performance[Z].NASA/TM-1998-208754 |
| [8] | S. Pierret;R. A. Van den Braembussche .Turbomachinery blade design using a Navier-stokes solver and artificial neural network[J].Journal of turbomachinery,1999(2):326-332. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%