利用密度演化方法,提出了随机变量概率分布估计的一个新方法.在此方法中,构造一个与基本随机变量相关的虚拟随机过程,使得基本随机变量成为该随机过程的截口随机变量.利用独立随机抽样的样本值,即可获取虚拟随机过程的瞬时概率密度函数,进而获得随机变量的概率密度函数估计.以约束混凝土极限应变的试验与理论预测值之比值为例,进行了概率密度函数估计.
A new method for probability density estimation based on the probability density evolution method is proposed in this paper. A virtual stochastic process is constructed so that the basic random variable becomes the value of the stochastic process at certain instants of time. The instantaneous probability density function of the virtual stochastic process is evaluated, and then the probability density function of the basic random variable is obtained by employing the independent random samples, As an example, the ratios of the experimental value to the analytical value of ultimate strain of confined concrete are taken as random variables whose probability density function is estimated with the proposed method.