面向声爆/气动力的飞行器布局设计知识挖掘

Knowledge mining of aircraft configuration design for sonic boom/aerodynamics

声爆抑制是发展新一代超声速民机必须突破的关键技术。飞行器总体布局参数对其声爆特性有重要影响。数据挖掘(DM)可以从大量的数据中通过算法搜索隐藏的信息,是飞行器设计知识提取的有力工具。选取后掠角、展弦比、梢根比、上反角、机身长细比5个总体布局参数作为设计变量,目标函数定义为远场感知噪声级,同时计算升、阻力系数作为气动力衡量指标。基于总变差分析(ANOVA)、决策树算法、自组织映射(SOM)网络组成的数据挖掘体系提取低声爆设计知识库。获得所选设计变量与声爆/气动力的相关度,并实现对设计变量的分层与降维。后掠角有最高设计优先级,长细比、上反角重要程度次之,展弦比与梢根比为低敏感变量。对于算例中的飞行器,在合理区间内选择较大的后掠角、上反角能够使声爆最小化的同时,设计适于超声速巡航的小展弦比布局。

Sonic boom suppression is a key technology in the development of a new generation of supersonic civil aircraft.The configuration parameters of aircraft have an important influence on its sonic boom characteristics.Data mining(DM)can search hidden information from a large amount of data through algorithms,thus becoming a powerful tool to extract aircraft design knowledge.Five configuration parameters,including the sweep angle,aspect ratio,taper ratio,dihedral angle and fuselage slenderness ratio,are selected as design variables.The objective function is defined as the perceived noise level,and the lift and drag coefficients are calculated as aerodynamic measurement indexes.The knowledge base of low sonic boom design is extracted based on the data mining system composed of analysis of variance(ANOVA),decision tree and self-organizing feature map(SOM).The method obtains the correlation between the selected design variables and sonic boom/aerodynamic force,realizing the stratification and dimensionality reduction of design variables.The sweep angle has the first design priority,the slenderness ratio and the dihedral angle the second,and the aspect ratio and taper ratio are low sensitive variables.For the aircraft of the example in this paper,choosing a larger sweep angle and dihedral angle in a reasonable range can minimize the sonic boom and design a small aspect ratio configuration suitable for supersonic cruises.