基于改进岭回归的气象雷达风力涡轮机杂波抑制算法

研究了一种改进的岭回归算法,用于精确估计被风力涡轮机杂波(WTC)污染的气象信号谱矩信息。该算法针对回归模型中数据存在较强的共线性时,导致参数估计值不稳定且估计精确度较低的问题,在距离-多普勒(RDR)基础上,引入加权岭回归模型,并采用广义交叉验证(GCV)获取岭回归模型中的最优回归参数,代入回归模型进而求解被WTC污染的气象信号谱距信息。仿真实验结果验证了该算法的有效性,并在低信噪比条件下对比RDR算法估计精度和稳定性更优。

Wind turbine clutter suppression of weather radar based on improved ridge regression

An improved ridge regression algorithm is developed to accurately estimate the spectral moment information of weather signals polluted by wind turbine clutter(WTC).Aiming at the problem that the strong collinearity of the data in the regression model leads to unstable parameter estimation and low estimation accuracy,and based on the range-Doppler regression,a weighted ridge regression model is introduced,and the optimal regression parameters in the ridge regression model are obtained by generalized cross validation(GCV),and then the spectral moment information of weather signal contaminated by WTC can be solved by plugging into the regression model.Simulation results show that the proposed algorithm is effective and has better accuracy and stability under the condition of low SNR.