基于灰色系统理论的不确定度模型

针对难以用传统的统计理论来估计不确定度的问题，以灰色系统理论为基础，提出了一种估计扩展不确定度的新方法，对正态分布，瑞利分布，三角分布及均匀分布等进行了计算机仿真实验。结果表明所提出的方法是切实可行的。

Uncertainty Model Based on Grey System Theory

Evaluation of measuring uncertainty by conventional statistics theory requires a number of measurements and a known or typical probability distribution. It is difficult to estimate the uncertainty of a measurand if the number of measurements is small and the probability distribution is unclear under some complicated conditions such as trial manufacturing of neo products, destructive or costly experimentations and some pollution analysis. To solve these problems, a novel method to evaluate expanded uncertainty by a whitened weighting function is proposed in this paper. The first advantage of this method is that it permits the number of measurements very small and the probability distribution unknown and the second the expanded uncertainty can be easily obtained without calculating the standard uncertainty and the coverage factor. The feasibility of the method was validated by computer simulation experiments under the conditions of different distributions such as normal, Rayleigh, triangle and uniform.