摘要
变弯度机翼结构是各大科研机构研究热点,为提高连续变后缘结构变形精度,需要设计出更加合理的结构。针对刚柔组合式的连续变弯度后缘结构,建立相应的数学模型,使用拉丁超立方抽样的方法对参数进行分层抽样,利用相关向量机算法搭建模型,借助差分进化算法对该模型进行优化,分析各变量对于变形误差的相关系数,对整体设计影响较大的变量进行判断。结果表明:经过优化的刚柔组合式蒙皮,相比初始状态提高了约67%的变形精度。
Variable camber wing structure is a hot topic in many scientific research institutions.In order to improve the deformation accuracy of the continuously variable trailing edge structure,it is necessary to design a more reasonable structure.The corresponding mathematical model is established for the rigid-flexible coupling continuously variable bending trailing edge structure.The Latin hypercube sampling method is used to perform the stratified sam pling of the parameters.The correlation vector machine algorithm is adopted to build the model,and the the model is optimized by the differential evolution algorithm.The correlation coefficient of each variable to the deformation error is analyzed,and the variables that have a greater impact on the overall design are determined.The results show that the deformation accuracy of the optimized rigid-flexible coupling skin is improved by about 67%compared with the initial state.
作者
徐儒鹏
张子健
张国鑫
薛景锋
宋坤苓
XU Rupeng;ZHANG Zijian;ZHANG Guoxin;XUE Jingfeng;SONG Kunling(Key Lab of Light-duty Gas-turbine,Institute of Engineering Thermophysics,Chinese Academy of Sciences,Beijing 100190,China;Chinese Aeronautical Establishment,Beijing 100024,China;School of Aeronautics and Astronautics,University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《航空工程进展》
2025年第4期40-47,共8页
Advances in Aeronautical Science and Engineering
关键词
变弯度机翼后缘
刚柔组合式蒙皮
拉丁超立方
相关向量机回归
差分进化算法
variable camber wing trailing edge
rigid-flexible coupling skin
Latin hypercube
correlation vector machine regression
differential evolution algorithm
