航空学报 > 2014, Vol. 35 Issue (7): 1865-1873   doi: 10.7527/S1000-6893.2013.0487

改进的RBF神经网络在翼梢小翼优化设计中的应用

白俊强1, 王丹1, 何小龙1, 李权2, 郭兆电2   

  1. 1. 西北工业大学 航空学院, 陕西 西安 710072;
    2. 中国航空工业集团公司 第一飞机设计研究院, 陕西 西安 710089
  • 收稿日期:2013-09-17 修回日期:2013-12-05 出版日期:2014-07-25 发布日期:2014-01-08
  • 通讯作者: 白俊强,Tel.:029-88492174E-mail:junqiang@nwpu.edu.cn E-mail:junqiang@nwpu.edu.cn
  • 作者简介:白俊强男,博士,教授,博士生导师。主要研究方向:飞行器总体设计。Tel:029-88492174E-mail:junqiang@nwpu.edu.cn;王丹女,博士研究生。主要研究方向:飞行器总体设计。Tel:13772122144E-mail:wangdan_hong@163.com;何小龙男,硕士研究生。主要研究方向:飞行器总体设计。Tel:029-88492174E-mail:173126638@qq.com;李权男,博士,工程师。主要研究方向:飞机气动设计、飞机多学科优化设计。Tel:029-86832360E-mail:lqq0309@163.com;郭兆电男,研究员,副总师。主要研究方向:飞行器总体气动设计。Tel:029-86832260E-mail:gzd0913@afai.cn
  • 基金资助:

    国家“863”计划(2012AA01A304)

Application of an Improved RBF Neural Network on Aircraft Winglet Optimization Design

BAI Junqiang1, WANG Dan1, HE Xiaolong1, LI Quan2, GUO Zhaodian2   

  1. 1. School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China;
    2. AVIC The First Aircraft Institute, Xi'an 710089, China
  • Received:2013-09-17 Revised:2013-12-05 Online:2014-07-25 Published:2014-01-08
  • Supported by:

    National High-tech Research and Development Program of China (2012AA01A304)

摘要:

为了提高径向基函数(RBF)神经网络模型的预测精度,在其基础上提出了一种自适应RBF神经网络模型。该预测模型在RBF神经网络模型表达式中引入自适应向量(向量维数与样本点自变量维数相同),采用优化搜索方式确定自适应向量值,从而提高模型预测的准确度和普适性。与其他RBF神经网络模型的改进相比,本文直接从改变基函数的形式入手,使用较少的参数优化达到对网络模型的自适应构造;该方法本质上改变了基函数网络中心与宽度对网络模型预测的作用以及样本点自变量向量的各个维对因变量的影响度,其对目标问题具有自适应性。将本文的自适应RBF神经网络模型应用在基于机身+机翼+翼梢小翼模型的翼梢小翼优化设计中,在约束弯矩的情况下进行巡航减阻优化设计,设计结果验证了该预测模型的可行性,表明其具有一定的工程实用价值。

关键词: RBF神经网络, 自适应向量, 高斯基函数, 翼梢小翼, 优化设计

Abstract:

A self-adaptive radial basis function (RBF) neural network is proposed in order to improve the prediction accuracy of the original RBF. A self-adaptive vector with the same dimension as the sample vector is introduced into the traditional RBF network. In contrast to other RBF neural network models, the current approach achieves the self-adaptive construction of the network by altering the form of the basis function directly, which reduces the number of variables to be optimized. This adaptive approach substantially changes the impact of the center and width of the RBF neural network on its prediction as well as the influence of each variable of the independent vector on the dependent vector. Thus the introduced vector enables the adaptability of the RBF neural network with respect to variant problems. Moreover, the accuracy and the universality of the prediction model are also improved due to the optimization of the self-adaptive vector. The proposed self-adaptive RBF neural network is applied to a winglet optimization design of a wing-body-winglet configuration. The optimization objective is to minimize the cruise drag with wing-root bending moment restriction. The optimization result confirms the effectiveness and the capability for engineering application of the self-adaptive RBF neural network.

Key words: RBF neural network, self-adaptive vector, Gauss basis function, winglet, optimization design

中图分类号: