基于UPF的WNN学习算法及其应用

Research on WNN Learning Algorithm Based on UPF and Its Application

为改善小波网络(WNN)的非线性建模能力,提出一种基于改进无迹粒子滤波(UPF)的WNN学习算法。算法先引入最小偏度策略减少无迹变换(UT)的Sigma采样个数,改进无迹Kalman滤波(UKF);再用改进UKF算法选取粒子滤波的重要性密度函数,构成新型UPF;最后,将SUPF作为WNN的学习算法进行训练和测试。实验表明,基于新采样策略UPF与基本UPF的WNN模型精度总体接近,但速度更快,效率更高,某型军用飞机气动力建模也验证了算法的有效性与可行性。

To improve the nonlinear modeling capability of Wavelet Neural Network(WNN),a learning algorithm of WNN based on modified Unscented Particle Filter(UPF)is proposed.In the algorithm,a minimal skew strategy is firstly introduced to reduce the number of Sigma sampling points of Unscented Transform(UT),improving Unscented Kalman Filter(UKF),and then the improved UKF is used to select the importance density function of Particle Filter(PF),forming a new UPF(SUPF),finally,SUPF is taken as learning algorithm of WNN for training and test.The simulation results indicate that the accuracy of WNN model using UPF based on new sampling strategy is approximately close to that of simple UPF,but the former has faster rate and higher efficiency,which validate its feasibility and effectiveness.