基于幂律退化轨道的小样本性能可靠性评定

结合航空航天领域高可靠、长寿命产品试验小子样的特点,运用性能退化可靠性理论和Bayes方法,对系统可靠性的统计推断方法进行了研究.首先对基于Bayes方法幂律退化轨道参数的计算模型进行研究,然后结合随机变量函数的分布的计算,推导出系统可靠性后验估计和置信下限估计的计算公式.在理论推导的基础上,结合工程实例说明该方法的有效性.     

小子样场合下估算母体百分位值置信下限和可靠度置信下限的Bootstrap方法

将Bootstrap方法引入到小子样场合下母体百分位值置信下限的计算中,并与传统的单侧容限系数法和新单侧容限系数法进行了大量的对比计算,算例表明Bootstrap方法明显优于其他两种方法,在较高可靠度和置信度要求下母体百分位值置信下限不会出现负值的情况,而且计算得到的结果更接近真值。发展了一种半参数Bootstrap方法用于计算可靠度的置信下限,模拟计算表明半参数Bootstrap方法很好地克服了置信度较高时,新旧单侧容限系数计算出的可靠度置信下限过低的局限性,而且半参数Bootstrap方法的计算结果均有较高的精度。     

基于设备试验数据的系统可靠性评估

提出了基于下层设备可靠性试验数据评估系统可靠性的方法.通过此方法可以得到系统在一定置信度下平均故障间隔时间的置信下限.最后通过实例说明如何利用该方法评估系统的可靠性.     

基于MCMC的PLP未来强度的Bayesian预测分析

在无信息先验分布下，将Gibbs抽样与Metropolis-Hastings算法相结合的方法应用于幂律过程的未来强度的Bayesian预测。该预测方法能将时间截尾数据和失效截尾数据统一分析，并给出在未来某一时刻处强度函数的MCMC样本，利用该样本可以方便地获得关于未来某一时处刻强度函数及其函数的各种后验分析。一个经典工程数值算例说明了预测方法的可行性、合理性与有效性。     

基于Markov Chain Monte Carlo的幂律过程的Bayesian分析

在多种合理的无信息先验分布下,基于Markov Chain Monte Carlo方法,提出了一种简单且易于抽样的幂律过程的Bayesian分析方法.所提方法将失效、时间截尾数据统一分析,能快捷地获取幂律过程模型参数的Markov Chain Monte Carlo样本,利用该样本不但能直接给出模型参数函数的后验分布,还能给出单样预测和双样预测的分析.一个经典工程数值算例说明了所提方法的可行性、合理性与有效性.该方法具有一定的优越性,可为小子样可靠性增长分析提供一种值得参考的方法.      

高温合金松弛过程回归分析方法

基于线性过程回归分析理论,建立了高温合金应力松弛过程回归分析方法,给出了松弛过程的回归方程和高置信水平、高可靠度的单侧置信下限曲线.高温合金松弛过程回归分析方法可以将应力松弛过程作为一个整体进行回归分析,充分利用了不同时刻剩余应力试验数据间的纵向信息,具有信息量大、精度高的特点.而且当试样数量较少时,传统方法得到的剩余应力置信下限曲线可能会发生畸变,而该方法则可以避免这一现象的发生.工程应用表明,在试样数相同的情况下,该方法比传统方法具有更高的精度,而在精度相同的情况下,则可减少大量试样.      

某燃气发生器壳体的结构可靠性分析与评估

对某燃气发生器壳体的可靠性进行了分析，应用应力和强度均服从正态分布时结构可靠度的置信下限公式，得到了壳体在整个工作期间内的可靠度的置信下限，说明壳体温度的变化对其结构可靠度的影响不可忽视。     

求解具有多层试验数据成败型单元混联系统可靠性近似限的信息论方法

研究了求解具有多层成败型试验数据时,系统可靠性置信下限近似解的信息论方法,给出了各层试验数据综合的方法和步骤,推导了各层数据信息论方法折合及综合的计算公式。根据单元试验信息提供的信息量与系统折合试验应提供的信息量相等的原则,将多层试验数据逐级折合为系统的等效成败型数据,导出了等效成败型数据信息论方法折合的基本公式;结合可靠性工程的基本原理,根据单个成败型单元可靠性评定的经典精确置信限方法,给出了系统可靠性置信下限的近似解。并以实例形式说明了该方法的具体应用。     

论加速可靠性增长试验(Ⅲ)分组数据的图方法

基于Arrhenius－幂律模型，给出了分析恒定应力加速可靠性增长试验分组数据的图方法。它们包括：增长趋势、幂律模型的拟合优度、相同故障机理及拟合加速方法的图检验；幂律模型参数、加速方程系数、加速系数、激活能及正常与加速应用水平下MTBF的图估计，并用实例说明这些方法。     

离子推力器极少数据可靠性评估方法

针对只有两台离子推力器进行寿命试验,试验结果为极少失效数据的情况,建立了一种离子推力器整机可靠性评估方法.通过引入区间统计量的概念,充分开发从最后一个失效数据继续试验到没有发生产品失效这一重要试验信息,由高斯-马尔科夫定理计算出寿命分布参数的最佳线性无偏估计,并给出离子推力器可靠度和寿命的单侧置信下限.最后,对美国NASA研制的型号为XIPS-13的离子推力器进行可靠性评估,得出了其寿命需求10000h的可靠度单侧置信下限为0.87及给定可靠度为0.9时的寿命单侧置信下限为9024.6h,该方法精度较高,便于工程应用.      

一种针对液体火箭发动机可靠性的双线评估方法

针对液体火箭发动机可靠性评估过程中试验数据利用不充分、主观性强、与设计改进关联不足等现状,给出了一种可靠性双线评估方法,在有限试车条件下提升可靠性评估结果的准确性,并从风险控制角度识别出发动机的薄弱环节.该方法采用两条主线开展可靠性评估,第一条线以发动机部组件试验数据为输入,以发动机工作时序为线索,识别发动机故障模式,...     

Reliability estimation of mechanical seals based on bivariate dependence analysis and considering model uncertainty

The reliability estimation of mechanical seals is of crucial importance due to their wide applications in pumps in various mechanical systems. Failure of mechanical seals might cause leakage, and might lead to system failure and other relevant consequences. In this study, the reliability estimation for mechanical seals based on bivariate dependence analysis and considering model uncertainty is proposed. The friction torque and leakage rate are two degradation performance indicators of mechanical seals that can be described by the Wiener process, Gamma process, and inverse Gaussian process. The dependence between the two indicators can be described by different copula functions. Then the model uncertainty is considered in the reliability estimation using the Bayesian Model Average (BMA) method, while the unknown parameters in the model are estimated by Bayesian Markov Chain Monte Carlo (MCMC) method. A numerical simulation study and fatigue crack study are conducted to demonstrate the effectiveness of the BMA method to capture model uncertainty. A degradation test of mechanical seals is conducted to verify the proposed model. The optimal stochastic process models for two performance indicators and copula function are determined based on the degradation data. The results show the necessity of using the BMA method in degradation modeling.     

基于无失效数据的某型发动机可靠性参数Bayes估计

针对装备寿命服从指数分布的情形,以失效率参数作为随机变量构建估计模型。考虑失效率的先验分布为 Gamma分布,在失效率的超参数均服从一定的均匀分布时,提出了失效率的多层 Bayes和期望 Bayes(ExpectedBayes,E-Bayes)估计方法,建立了失效率的多层 Bayes和 E-Bayes估计模型;结合某型装备发动机的无失效储存数据,计算了失效率的多层 Bayes和 E-Bayes估计值,推导了可靠度的多层 Bayes和 E-Bayes估计值。通过比较分析,可靠度的 2种估计结果都是稳健的,而后者略小于前者,且后者的极差比前者减小 81.4%。结果表明,采用 EBayes估计更易于计算,得到的结果更为准确稳健,且更适用于工程应用实际。     

Using PoF models to predict system reliability considering failure collaboration

Existing Physics-of-Failure-based (PoF-based) system reliability prediction methods are grounded on the independence assumption, which overlooks the dependency among the compo-nents. In this paper, a new type of dependency, referred to as failure collaboration, is introduced and considered in reliability predictions. A PoF-based model is developed to describe the failure behavior of systems subject to failure collaboration. Based on the developed model, the Bisection-based Reliability Analysis Method (BRAM) is exploited to calculate the system reliabil-ity. The developed methods are applied to predicting the reliability of a Hydraulic Servo Actuator (HSA). The results demonstrate that the developed methods outperform the traditional PoF-based reliability prediction methods when applied to systems subject to failure collaboration.     

发动机无失效数据可靠性评估研究

在定时截尾寿命试验特别是高可靠性、小子样试验中的无失效数据,引入了逆Weibull寿命分布函数,提出采用不完全Beta分布作为故障概率的先验分布,给出分布参数的最小二乘估计以及故障概率的Bayes估计和多层Bayes估计,从而得到可靠度的估计。最后针对实际问题进行了计算,结果表明Bayes估计稳定合理且容易计算,假定发动机寿命服从逆Weibull分布时的计算结果具有较高精度和较小的偏差。     

Study on segmented distribution for reliability evaluation

In practice, the failure rate of most equipment exhibits different tendencies at different stages and even its failure rate curve behaves a multimodal trace during its life cycle. As a result, traditionally evaluating the reliability of equipment with a single model may lead to severer errors. However, if lifetime is divided into several different intervals according to the characteristics of its failure rate, piecewise fitting can more accurately approximate the failure rate of equipment. There-fore, in this paper, failure rate is regarded as a piecewise function, and two kinds of segmented dis-tribution are put forward to evaluate reliability. In order to estimate parameters in the segmented reliability function, Bayesian estimation and maximum likelihood estimation (MLE) of the seg-mented distribution are discussed in this paper. Since traditional information criterion is not suit-able for the segmented distribution, an improved information criterion is proposed to test and evaluate the segmented reliability model in this paper. After a great deal of testing and verification, the segmented reliability model and its estimation methods presented in this paper are proven more efficient and accurate than the traditional non-segmented single model, especially when the change of the failure rate is time-phased or multimodal. The significant performance of the segmented reli-ability model in evaluating reliability of proximity sensors of leading-edge flap in civil aircraft indi-cates that the segmented distribution and its estimation method in this paper could be useful and accurate.     

可靠性全局灵敏度求解的Meta-IS-AK算法

可靠性全局灵敏度（GRS）可以衡量输入变量对结构系统失效概率的平均影响,但目前仍然缺乏具有广泛适应性的高效算法。针对此问题,本文将在元重要抽样和可靠性全局灵敏度的贝叶斯算法基础上建立一种新的高效算法。所提算法首先利用已有的贝叶斯算法,将可靠性全局灵敏度转换成由无条件失效概率及输入变量失效域条件下的概率密度函数（PDF）表达的形式,然后分3步来完成算法的组织。第1步是利用元重要抽样的迭代策略抽取失效域的重要抽样样本;第2步是在已有的元重要抽样法中嵌入自适应Kriging模型,高效计算出无条件失效概率;第3步是利用Metropolis-Hastings准则,将失效域的重要抽样样本转化成为原始密度函数在失效域的样本点,进而同时求得各个输入变量在失效域中的条件概率密度函数,并最终求得可靠性全局灵敏度。由于所提算法充分利用了已有的可靠性全局灵敏度贝叶斯算法的维度独立性、元重要抽样法对隐式多失效域的适应性以及元重要抽样法中嵌入式Kriging模型的高效性,因此所提算法具有广泛的适用范围和较高的效率,该结论得到了算例结果的充分验证。     

Reliability assessment of engine electronic controllers based on Bayesian deep learning and cloud computing

The reliability of an Engine Electronic Controller (EEC) attracts attention, which has a critical impact on aircraft engine safety. Reliability assessment is an important part of the design phase. However, the complex composition of EEC and the characteristic of the Phased-Mission System (PMS) lead to the difficulty of assessment. This paper puts forward an advanced approach, considering the complex products and uncertain mission profiles to evaluate the Mean Time Between Failures (MTBF) in the design phase. The failure mechanisms of complex components are deduced by Bayesian Deep Learning (BDL) intelligent algorithm. And copious samples of reliability simulation are solved by cloud computing technology. Based on the result of BDL and cloud computing, simulations are conducted with the Physics of Failure (PoF) theory and Failure Behavior Model (FBM). This reliability assessment approach can evaluate MTBF of electronic products without reference to physical tests. Finally, an EEC is applied to verify the effectiveness and accuracy of the method.     

论加速可靠性增长试验 (Ⅶ )步进应力试验方案的统计分析

对幂律-线性化模型步进应力加速可靠性增长试验方案，给出了模型参数，加速系数及MTBF的极大似然估计，极大后验估计，Bayes估计及其计算方法，对这些方案给出了Monte Carlo模拟方法，并用数值例说明了这些方法。     

基于贝叶斯网络的分层系统可靠性分析

由于分层系统的系统结构复杂,且系统不同层次可靠性信息具有不均衡性的特点,使得分层系统的可靠性建模较为困难.考虑二态情况,通过引入贝叶斯网络描述分层系统元素间的失效关系,并考虑了系统元素间级联失效问题,结合贝叶斯多源信息融合方法,以贝叶斯网络模型为基础整合了系统各层元素的可靠性信息,构成了一种较为通用的二态分层系统可靠性分析方法.算例结果表明:该方法在贝叶斯网络模型计算过程中能够融合系统各层元素可靠性信息并有效处理级联失效问题,提高了系统可靠性后验均值估计的准确性,减小了系统可靠性结论的后验方差.