根据高长寿命产品的试验数据特征,采用退化轨迹拟合、两点分布和区间估计思想,分位数置信限一失效阈值干涉、可靠度预估响应模拟,分别给出了小样本和大样本试样下的零部件可靠性置信限评估方法。运用Copula理论拟合零部件失效间的动态相关性,从而对应性地建立了系统级可靠性置信限综合评估模型。该模型改善了独立性系统可靠性置信限评估方法预估结果过于保守的情形。算例验证了该类模型的可行性和有效性。
According to the characteristics of test data of long-lived products, fitting degradation path, two-point distribution, interval estimation were combined, and based on the interference between quantile confidence limits and failure threshold, reliability estimated response simulation, the methods to assess the reliabilities of components were presented under the small sample and large samples respectively. Copulas theories were used to fit the dynamic correlation among failures of components, then the reliability comprehensive evaluation models were established on the level of systems, which can improve the excessive conservatism resulted from independence. Finally, an example is given to demonstrate the feasibility and effectiveness of the proposed models.