本文以曲轴为例,说明了在Goodman图基础上建立“帐篷-堤坝”统计模型的方法。这种统计模型考虑了零件的工作应力和材料强度,从而可预测零件的疲劳可靠性,来代替传统的安全系数。文中列出了该模型的四种不同解法,并通过计算实例表明,所提供的模型是发动机零件可靠性预测的有力工具。 In this paper, a crankshaft is taken as an example to illustrate the method of establishing “tent-dyke” statistical model based on Goodman diagram. This statistical model takes into account the working stress and material strength of the part, which can predict the fatigue reliability of parts to replace the traditional safety factor. Four different solutions of the model are listed in the paper. The calculation examples show that the model provided is a powerful tool for the reliability prediction of engine parts.