ID 原文 译文
48216 针对KK分布的参数估计,首先介绍了半经验估计法,然后提出了一种基于粒子群优化的估计方法。 Aimed at KK distribution parameter estimation, the first half experience estimation method is introduced, and then puts forward a method based on particle swarm optimization.
48217 该方法将杂波数据统计直方图与KK分布概率密度函数在部分采样点上的差异作为代价函数,通过粒子群优化搜索参数的最优值。 This method will clutter statistical histogram and KK distribution probability density function on the part of the sample point difference as a cost function, through the optimal value of the particle swarm optimization search parameters.
48218 通过蒙特卡罗方法对半经验估计法在权重参数不同时的性能进行了仿真, By monte carlo method half-and-half experience estimate method at the same time in the weight parameters not performance are simulated,
48219 然后分析了杂波数据样本点数的多少等因素对所提算法精度的影响, and then analyzed how much clutter data sample points and other factors that affect the precision of the proposed algorithm,
48220 最后基于实测合成孔径雷达图像杂波数据对该算法进行了验证。 based on the measured synthetic aperture radar image clutter data for the algorithm is verified.
48221 仿真结果表明,该算法对KK分布参数具有良好的估计性能,KK分布与K分布等相比,对合成孔径雷达图像杂波数据具有更强的拟合能力。 The simulation results show that the proposed algorithm for KK distributed parameter has good estimation performance, KK distribution compared with K distribution, noise of synthetic aperture radar image data has the stronger ability of fitting.
48222 将智能算法应用在T-S模糊模型的辨识方面,是模糊系统辨识的一种新途径。 The intelligent algorithm applied in the identification of t-s fuzzy model, is a new way of fuzzy system identification.
48223 文中对几种智能优化算法,如遗传算法(genetic algorithm,GA)、粒子群(particle swarm optimization,PSO)算法、菌群优化(bacterial foraging optimization,BFO)算法等的优化原理和在模糊辨识方面的应用现状进行了综述和分析, This paper several intelligent optimization algorithms, such as genetic algorithm (based algorithm, GA) and particle swarm (particle swarm optimization, PSO) optimization algorithm, flora (bacterial foraging optimization, BFO) algorithm, such as the optimization principle and the application status were reviewed in terms of fuzzy identification and analysis,
48224 并给出了它们在T-S模糊模型辨识中对参数进行优化的过程。 and gives them in T - S fuzzy model identification for parameter optimization of the process.
48225 最后将这些优化方法用于一非线性动态系统的建模,并对仿真结果进行了对比和详细的分析,为进一步了解这几种优化方法在模糊模型辨识参数优化方面的作用提供了仿真实验依据。 Finally the optimal method for a nonlinear dynamic system of modeling, and the simulation results were compared and detailed analysis, several optimization methods in order to further understand this in the role of the fuzzy model identification parameter optimization provides the simulation experiments.