毁伤概率评估的加权蒙特卡洛方法  

A Weighted Monte Carlo method for Evaluating Damage Probability

作　　者：戴毅[1] 苗育红[1] 周江华[2] 

机构地区：[1]第二炮兵工程学院603教研室,陕西西安710025 [2]中国科学院光电研究院,北京100080

出　　处：《计算机仿真》2008年第3期115-118,166,共5页Computer Simulation

摘　　要：由于经典蒙特卡洛方法的仿真效率不高,文中利用概率论和数理统计的基本原理,可以推导得到加权蒙特卡洛方法。加权蒙特卡罗方法不但能有效的缩小了样本方差,还能提高目标事件出现概率,相当于提高了样本的抽样效率,从而提高了仿真效率。与此同时,文中分别利用经典蒙特卡洛和加权蒙特卡洛这两种方法对典型目标进行了仿真计算,仿真计算最终证明了加权蒙特卡洛方法的仿真效率明显优于经典蒙特卡洛方法,能使仿真工作量成数量级的衰减。Because simulation efficiency is not high by using the classical Monte Carlo method, based on the principle of the probability theory and the statistic theory, a weighted Monte Carlo method can be deduced. The method not only reduces sample variance, but also enhances the probability of object event appearing. It is equal to improve sampling efficiency and simulation efficiency. In this paper, at the same time, using simulation of classical Monte Carlo method and weighted Monte Carlo method , according to the results of simulation and calculation of the typical object, it can be proved that the simulation efficiency of the weighted Monte Carlo method is higher than that of the classical Monte Carlo method obviously, and the simulation work can be reduced by order of magnitude.

关 键 词：蒙特卡洛方法 抽样 毁伤概率 仿真效率 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]