一、引言以机械结构为主的系统,在建立可靠度模型时,应尽可能多地采用在现场数据中所包含的故障机理信息,以期得到一种既切合实际而又便于分析的可靠度模型。关于可靠度函数,已经归纳出一些标准形式,如正态分布;对数正态分布;威布尔分布;伽玛分布;指数分布等。为使数据处理方便也已研究出了很多其它方法。它们的特点是仅把系统或其构成部件看成只存在故障和正常两个状态,这种简单的故障机理,应用于电子部件已经取得了很大的成绩。但是要使这些分布同样适用于所有的机械系统,确存在着一定 I. INTRODUCTION In the system of mechanical structure, when establishing the reliability model, the fault mechanism information contained in the field data should be used as much as possible so as to obtain a reliability model which is practical and easy to analyze . As for the reliability function, some standard forms have been concluded, such as normal distribution, log normal distribution, Weibull distribution, gamma distribution, exponential distribution and the like. A number of other approaches have also been developed to facilitate data processing. They are characterized by only the system or its components as only the fault and the normal two states, this simple fault mechanism, applied to electronic components has made great achievements. But to make these distributions equally applicable to all mechanical systems, there really exists