基于主观推断的可靠性评估方法

Reliability Assessment Based on Subjective Inferences

通过主观推断得到的可靠性信息一般是不完全先验信息 ,这些信息通常以可靠度均值或可信区间的形式存在。以贝塔分布作为先验信息的分布类型 ,介绍了用最大熵原理将不完全信息转化为完全型先验信息的计算方法 ,并用贝叶斯方法进行了成败型产品的可靠性评估 。

The reliability information which comes from subjective analysis is often incomplete prior. This information can be generally assumed to exist in the form of either a stated prior mean of R (reliability) or a stated prior credibility interval on R. An efficient approach is developed to determine a complete beta prior distribution from the subjective information according to the principle of maximum entropy, and then the reliability of survival/failure product is assessed via Bayes theorem. Numerical examples are presented to illustrate the methods.