基于模糊神经网络的气动参数拟合  

Aerodynamic Parameter Fitting Basis on Fuzzy Neural Network

作　　者：李世玲[1] 张富堂[2] 李治[1] 魏可惠[2] 

机构地区：[1]西南交通大学电气工程学院,成都610031 [2]中国工程物理研究院电子工程所,绵阳621900

出　　处：《系统仿真学报》2001年第4期488-490,520,共4页Journal of System Simulation

摘　　要：鉴于模糊神经网络可以充当万能逼近器，以任意精度逼近任何非线性函数，本文用模糊神经网络对气动参数进行高精度拟合。在飞行器轨迹计算中用拟合得到的计算公式计算气动参数，可大大节省计算机时和存贮单元，提高计算精度，仿真实验亦表明了这一方法的有效性和可行性，这在飞行器的轨迹计算中是值得采用和推广的方法。It is approved that fuzzy neural network can be used as an universal approximator, it can approximate any nonlinear function at arbitrary precision. This paper uses it to make a high-precise fit of aerodynamic parameters. If the formula formed by fitting is used to calculate aircraft's flight trajectory, a great deal of storage unit and machine-time are saved. Precision can be improved in this way. It is a good method which is worthy of promoting and popularizing in calculating of aircraft's flight trajectory. The validity of this method has been demonstrated by a numerical simulation.

关 键 词：模糊神经网络 气动参数拟合 非线性函数 飞行器 

分 类 号：V47[航空宇航科学与技术—飞行器设计]