考虑专家信息的威布尔型产品定时截尾可靠性验收试验方案设计  

Type I censored reliability acceptence test plan for Weibull distributed products by considering expert information

作　　者：谭尧 赵骞 王文峰 郭波[1] 蒋平[1] TAN Yao;ZHAO Qian;WANG Wenfeng;GUO Bo;JIANG Ping(College of Systems Engineering, National University of Defense Technology, Changsha 410005, China;College of Information Communication, National University of Defense Technology, Xi’an 710106, China;Unit 93209 of the PLA, Beijing 100085, China)

机构地区：[1]国防科技大学系统工程学院,湖南长沙410005 [2]国防科技大学信息通信学院,陕西西安710106 [3]中国人民解放军93209部队,北京100085

出　　处：《系统工程与电子技术》2022年第4期1409-1416,共8页Systems Engineering and Electronics

基　　金：国家自然科学基金(71871218,72071208)资助课题。

摘　　要：可靠性验收试验是检验产品是否达到可靠性要求而进行的试验。试验方案的确定需要保证使用方风险和生产方风险可控。当前GJB899A中定时截尾试验方案往往需要较长的试验时间,短时试验方案又存在两类风险较大的问题,实际应用颇受诟病。根本原因在于GJB899A的试验方案确定只考虑了系统试验数据,而忽视了其多源信息。因此,本文针对复杂系统验收试验前存在多种形式专家信息,考虑系统寿命服从威布尔分布的情况,结合专家信息来计算产品在给定试验方案下的两类风险,进一步推导得到试验时间较短、风险可控的试验方案。文章最后给出了案例分析,通过对比,验证了所提方法的有效性。The reliability acceptance test is to check whether the product meets the reliability requirement.It is essential to choose a test plan with controllable customer’s and producer’s risks.However,the reliability acceptance test adopted from GJB899A oftentimes leads to either long test duration or high customer’s and producer’s risks,which hinds its real-world application.The primary reason lies in that,only the test data collected from the systems are taken into account,whereas the information from experts is ignored.Considering there are various types of expert information and the system life follows the Weibull distribution,the two types of risks of the product can be calculated.Then the test plan with shorter test time and controllable risks can be determined.The proposed method is applied to a numerical case study and the results verify the effectiveness of the method.

关 键 词：威布尔分布 专家信息 生产方风险 使用方风险 可靠性验收试验 

分 类 号：TN306[电子电信—物理电子学]