流场特性预测的两类高效方法  

Two effective methods for flow-field performance forecast

作　　者：王保国[1] 吴俊宏[1] 刘淑艳[1] 钱耕[1] 刘艳明[1] 

机构地区：[1]北京理工大学宇航学院,北京100081

出　　处：《航空动力学报》2010年第8期1763-1767,共5页Journal of Aerospace Power

基　　金：国家自然科学基金(50376004);高等学校博士学科点专项基金(20030007028)

摘　　要：在多因素多水平试验设计方法建立数据库的基础上,提出了预测流场特性的两类高效方法:一类是响应面方法;一类是小波神经网络方法.典型算例表明,两类方法都可以高效率的获取流场特性参数,而且在预测的精度与计算的效率上,小波神经网络方法较响应面方法更具有优势.Based on database established by multi-factor and multi-level design methods,two effective methods of flow-field performance forecast were proposed.One is response surface method,and the other is wavelet neural networks method.The typical examples indicate that two methods can forecast flow-field performance effectively.The results also show that wavelet neural networks method is superior to response surface method in terms of efficiency and precision.

关 键 词：小波神经网络法 响应面法 均匀试验设计 流场预测 流场特性 

分 类 号：V231.3[航空宇航科学与技术—航空宇航推进理论与工程]