可靠性测试 - 成功率合规测试计划

[中文适用范围]： 本国际标准旨在定义一种程序，用于验证物品或系统的可靠性是否符合规定要求。该要求被设定为成功率百分比或失败率百分比。本文档可用于测试多个物品（进行多次试验）并分类为通过或失败的情况。也可用于对一个或多个物品进行重复测试。该程序基于成功率或失败率在每次试验中相同（即统计独立事件）的假设。本文档包含了固定试验/故障终止测试计划以及截断序贯概率比测试计划（SPRT）。本文档包含大量现成的SPRT计划及其特征表，适用于供应商和客户相等或非相等的风险情况。在恒定的失败率/强度可靠性符合性测试的情况下，适用IEC 61124。 [外文原描述]： IEC 61123:2019 is intended to define a procedure to verify if a reliability of an item/system complies with the stated requirements. The requirement is assumed to be specified as the percentage of success (success ratio) or the percentage of failures (failure ratio). This document can be used where a number of items are tested (number of trials performed) and classified as passed or failed. It can also be used where one or a number of items are tested repeatedly. The procedures are based on the assumption that the probability of success or failure is the same from trial to trial (statistically independent events). Plans for fixed trial/failure terminated tests as well as truncated sequential probability ratio tests (SPRTs) are included. This document contains extensive tables with ready-to-use SPRT plans and their characteristics for equal and non-equal risks for supplier and customer. In the case of the reliability compliance tests for constant failure rate/intensity, IEC 61124 applies. This second edition cancels and replaces the first edition published in 1991. This edition constitutes a technical revision. This edition includes the following significant technical changes with respect to the previous edition: The sequential probability ratio test (SPRT) [1, 2][1] has been significantly developed in recent years [3, 4, 5]. This edition contains shorter and accurate tests, a wide range of test plans, and significant additional characteristic data, as follows: the tests are significantly truncated (the maximum trial numbers are low) without substantially increasing the expected number of trials to decision (ENT); the true producer’s and consumer’s risks (α', β') are given and very close to the nominal (α, β); the range of the test parameters is wide (failure ratio, risks and discrimination ratio); the test plans include various risk ratios (not restricted to equal risks only); the values of ENT are accurate and given in the relevant region (for practical use); guidelines for extension of the test sets (interpolation and extrapolation) are included. In Annex C, the use of the cumulative binomial distribution function of Excel that simplifies the procedure of designing has been added (Clause C.3). Keywords: verify if a reliability of an item/system complies with the stated requirements