UKF-WNN及其在准定常失速气动力建模中的应用  

UKF-WNN and its applications to the quasi-steady stall aerodynamic force modeling

作　　者：赵亮[1] 刘晓东[1] 雷静 

机构地区：[1]空军工程大学工程学院 [2]解放军93897部队

出　　处：《空气动力学学报》2010年第3期353-357,共5页Acta Aerodynamica Sinica

摘　　要：提出一种利用无轨迹卡尔曼滤波估计小波网络参数的算法,该算法可克服算法存在的收敛速度慢、计算量大、局部极小等缺点。以飞机的准定常失速现象的气动力建模为应用背景,分别运用BP算法,扩展卡尔曼滤波算法和无轨迹卡尔曼滤波算法训练小波网络。仿真结果表明,无轨迹卡尔曼滤波算法较之BP算法和扩展卡尔曼滤波算法具有更快的训练速度和更高的预测精度,可以胜任复杂的非线性气动现象的建模任务。A WNN algorithm using the UKF to estimate the parameters, which can get over the BP algorithm＇s shortcomings of slow convergence speed, computation complexity and local minimum, is proposed. And taking the aerodynamic modeling of quasi-steady stall phenomenon for ATTAS aircraft as applying background, WNN is trained using the BP, EKF and UKF, respectively. The simulation results indicate that the algorithm proposed has faster training speed and higher prediction accuracy, and the method is also feasible for modeling of complex nonlinear aerodynamic phenomenon.

关 键 词：小波 神经网络 卡尔曼滤波 气动力 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]