基于LSE改进EM算法的屏蔽数据下并联系统贮存可靠性分析  

Storage reliability analysis of parallel system based on LSE improving EM algorithm

作　　者：余珊珊 张永进 张燕军[2] 展佳慧 Yu Shanshan;Zhang Yongjin;Zhang Yanjun;Zhan Jiahui(School of Mathematical Sciences and Engineering,Anhui University of Technology,Maanshan 243002,China;College of Mechanical Engineering,Yangzhou University,Yangzhou 225127,China)

机构地区：[1]安徽工业大学数理科学与工程学院,安徽马鞍山243002 [2]扬州大学机械工程学院,江苏扬州225127

出　　处：《南京理工大学学报》2022年第3期313-320,共8页Journal of Nanjing University of Science and Technology

基　　金：国家自然科学基金(32072785);安徽省自然科学基金(1808085MG220);安徽省高校省级自然科学研究基金(KJ2021A0386)。

摘　　要：考虑产品贮存检测中存在系统失效数据信息被屏蔽的问题,针对并联系统,提出了一种基于最小二乘估计(LSE)改进期望最大化(EM)算法的贮存可靠性分析方法。鉴于产品开始进入贮存时非完全可靠的初始失效情形,建立了指数寿命分布下并联系统的贮存可靠性模型。考虑系统未失效数据中含有屏蔽数据,用改进的EM算法更新检测数据并给出了系统初始可靠度和失效率的LSE。通过算例分析验证了模型的有效性和方法的合理性。Considering the problem that system failure data information is shielded in product storage detection,a storage reliability analysis method based on least squares estimation(LSE)and improved expectation maximization(EM)algorithm is proposed for parallel systems.Considering the products are not always perfect at the beginning of storage,a storage reliability model of parallel systems with exponential life distribution is developed.Assumeing that the non-failure data of the system contain masked data,the improved EM algorithm is used to update the testing data,and then the LSEs for the initial reliability and failure rate of the system are investigated.The effectiveness of the model and the rationality of the method are verified by an example.

关 键 词：最小二乘估计 期望最大化算法 屏蔽数据 并联系统 指数分布 

分 类 号：TB114[理学—概率论与数理统计] N945.1[理学—数学]