基于IPSO算法的KK分布模型参数估计

Parameter estimation of KK distribution model based on IPSO algorithm

目的提出一种IPSO(Improved Particle Swarm Optimization)算法,估计服从KK分布的海杂波建模参数,以改善复杂海况下海杂波幅度统计模型的建模精度。方法通过设计目标损失函数、更新公式等方法,获得了IPSO算法,然后利用IPSO算法对模型参数进行最优或次优取值估计。结果与结论仿真和实测海杂波数据集实验表明,所提方法克服了KK分布的多参数难于通过解析法求解参数的问题,有效解决了非线性分布海杂波模型的重“拖尾”拟合精度偏低的问题,且该算法能够更快地收敛到理想取值。

Purposes—To improve the modeling accuracy of the statistical model of sea clutter under complex sea conditions by proposing an Improved Particle Swarm Optimization(IPSO)algorithm to estimate the parameters of the sea clutter model obeying KK distribution.Methods—IPSO algorithm is obtained by designing objective loss function and updating formula.Then the improved algorithm is used to estimate the optimal or suboptimal values of the model parameters to improve the modeling accuracy.Results and Conclusions—The dataset experiments of imitative and measured sea clutter show that not only does the proposed method overcome the problem that it is difficult to solve the parameters of the multiple parameters of KK distribution with the analytical method,and effectively solve the problem of low fitting accuracy of heavy tail of nonlinear-distributed sea clutter model,but also the algorithm can converge to the ideal value faster.