Component reliability assessment using quantitative and qualitative data

The estimation of a component failure rate depends on the availability of plant specific numerical data. The purpose of this study was development of a new method that explicitly includes numerical and linguistic information into the assessment of a specific failure rate. The basis of the method is the Bayesian updating approach. A prior distribution is selected from a generic database, whereas likelihood is assessed using the principles of fuzzy set theory. The influence of component operating conditions on component failure rate is modeled using a fuzzy inference system. Results of fuzzy reasoning are then used for building an appropriate likelihood function for the Bayesian inference.The method was applied on a high voltage transformer. Results show that with the proposed method, one can estimate the specific failure rate and analyze possible measures to improve component reliability. The method can be used for specific applications including components for which there is not enough numerical data for specific evaluation.     

多方程线性模型系统的贝叶斯预报分析

多方程线性模型系统的贝叶斯预报分析是贝叶斯线性模型理论的重要组成部分。通过模型系统的统计结构,证明了矩阵正态-Wishart分布是模型参数的共轭先验分布;根据模型的样本似然函数和参数的先验分布推导了参数的后验分布;然后,从数学上严格推断了模型的预报分布密度函数,证明了模型预报分布为矩阵t分布。研究结果表明：由于参数先验分布的作用辟,样本的预报分布与其原统计分布有着本质性的差异,前者为矩阵正态分布,而后者为矩阵t分布。     

E-Bayesian estimation of reliability characteristics of two-parameter bathtub-shaped lifetime distribution with application

This article presents the expected Bayesian (E-Bayesian) estimation of the scale parameter, reliability and failure rate functions of two-parameter bathtub-shaped lifetime distribution under type-II censoring data with. Squared error loss function and gamma distribution as a conjugate prior distribution for the unknown parameter are used to obtain the E-Bayesian estimators. Also, three different prior distributions for the hyperparameters for the E-Bayesian estimators are considered. Some properties of the E-Bayesian estimators are studied. Using minimum mean square error criteria, a simulation study is conducted to compare the performance of the E-Bayesian estimators and the corresponding Bayes and maximum likelihood estimators. A real data set is analysed to show the applicability of the different proposed estimators. The numerical results show that the E-Bayesian estimators perform better than the classical and Bayesian estimators.     

Mixture priors for Bayesian performance monitoring 2: variable-constituent model

This paper uses mixture priors for Bayesian assessment of performance. In any Bayesian performance assessment, a prior distribution for performance parameter(s) is updated based on current performance information. The performance assessment is then based on the posterior distribution for the parameter(s). This paper uses a mixture prior, a mixture of conjugate distributions, which is itself conjugate and which is useful when performance may have changed recently. The present paper illustrates the process using simple models for reliability, involving parameters such as failure rates and demand failure probabilities. When few failures are observed the resulting posterior distributions tend to resemble the priors. However, when more failures are observed, the posteriors tend to change character in a rapid nonlinear way. This behavior is arguably appropriate for many applications. Choosing realistic parameters for the mixture prior is not simple, but even the crude methods given here lead to estimators that show qualitatively good behavior in examples.     

Finding a minimally informative Dirichlet prior distribution using least squares

In a Bayesian framework, the Dirichlet distribution is the conjugate distribution to the multinomial likelihood function, and so the analyst is required to develop a Dirichlet prior that incorporates available information. However, as it is a multiparameter distribution, choosing the Dirichlet parameters is less straightforward than choosing a prior distribution for a single parameter, such as p in the binomial distribution. In particular, one may wish to incorporate limited information into the prior, resulting in a minimally informative prior distribution that is responsive to updates with sparse data. In the case of binomial p or Poisson λ, the principle of maximum entropy can be employed to obtain a so-called constrained noninformative prior. However, even in the case of p, such a distribution cannot be written down in the form of a standard distribution (e.g., beta, gamma), and so a beta distribution is used as an approximation in the case of p. In the case of the multinomial model with parametric constraints, the approach of maximum entropy does not appear tractable. This paper presents an alternative approach, based on constrained minimization of a least-squares objective function, which leads to a minimally informative Dirichlet prior distribution. The alpha-factor model for common-cause failure, which is widely used in the United States, is the motivation for this approach, and is used to illustrate the method. In this approach to modeling common-cause failure, the alpha-factors, which are the parameters in the underlying multinomial model for common-cause failure, must be estimated from data that are often quite sparse, because common-cause failures tend to be rare, especially failures of more than two or three components, and so a prior distribution that is responsive to updates with sparse data is needed.     

基于贝叶斯信息融合的测量不确定度评定与实时更新

基于贝叶斯信息融合与统计推断原理,建立不确定度动态评定模型,对测量不确定度进行实时更新。引入最大熵原理和爬山搜索优化算法,确定先验分布概率密度函数及样本信息似然函数,结合贝叶斯公式求出后验分布概率密度函数,实现不确定度的优化估计。仿真及实例分析表明,基于贝叶斯和最大熵方法评定及更新的测量不确定度更加接近理论值。     

蒙特卡罗方法在贝叶斯统计质量控制中的应用

对小批量生产下的质量控制问题进行研究,在方差已知时的贝叶斯均值控制模型中,推导了蒙特卡罗方法确定模型中质量特性参数后验分布的过程,并且与基于共轭先验分布的理论方法进行比较,通过实例发现,基于蒙特卡罗确定质量特性参数统计值的方法与理论的共轭先验分布方法能达到相同的控制效果,并且蒙特卡罗方法不需要假设质量特性参数的先验分布,在实际的生产中具有较好的普适性。     

Bayesian analysis for estimating statistical parameter distributions of elasto-viscoplastic material models

High temperature design methods rely on constitutive models for inelastic deformation and failure typically calibrated against the mean of experimental data without considering the associated scatter. Variability may arise from the experimental data acquisition process, from heat-to-heat material property variations, or both and need to be accurately captured to predict parameter bounds leading to efficient component design. Applying the Bayesian Markov Chain Monte Carlo (MCMC) method to produce statistical models capturing the underlying uncertainty in the experimental data is an area of ongoing research interest. This work varies aspects of the Bayesian MCMC method and explores their effect on the posterior parameter distributions for a uniaxial elasto-viscoplastic damage model using synthetically generated reference data. From our analysis with the uniaxial inelastic model we determine that an informed prior distribution including different types of test conditions results in more accurate posterior parameter distributions. The parameter posterior distributions, however, do not improve when increasing the number of similar experimental data. Additionally, changing the amount of scatter in the data affects the quality of the posterior distributions, especially for the less sensitive model parameters. Moreover, we perform a sensitivity study of the model parameters against the likelihood function prior to the Bayesian analysis. The results of the sensitivity analysis help to determine the reliability of the posterior distributions and reduce the dimensionality of the problem by fixing the insensitive parameters. The comprehensive study described in this work demonstrates how to efficiently apply the Bayesian MCMC methodology to capture parameter uncertainties in high temperature inelastic material models. Quantifying these uncertainties in inelastic models will improve high temperature engineering design practices and lead to safer, more effective component designs.     

Bayesian calculation of cost optimal burn-in test durations for mixed exponential populations

The burn-in process is a part of the production process whereby manufactured products are operated for a short period of time before release. In this paper, a Bayesian method is developed for calculating the optimal burn-in duration for a batch of products whose life distribution is modeled as a mixture of two (denoted ‘strong’ and ‘weak’) exponential sub-populations. The criteria used is the minimization of a total expected cost function reflecting costs related to the burn-in process and to product failures throughout a warranty period. The expectation is taken with respect to the mixed exponential failure model and its parameters. The prior distribution for the parameters is constructed using a beta density for the mixture parameter and independent gamma densities for the failure rate parameters of the sub-populations. It is assumed that the optimal burn-in time is selected in advance and remains fixed throughout the burn-in process. When additional failure information is available prior to the burn-in process, the minimization of posterior total cost is used as the criteria for selecting the optimal burn-in time. Expressions for the joint posterior distribution and cost are provided for the case of both complete and truncated data. The method is illustrated with an example.     

A Monte Carlo method for calculating Bayesian uncertainties in internal dosimetry

This paper presents a novel Monte Carlo method (WeLMoS, Weighted Likelihood Monte-Carlo sampling method) that has been developed to perform Bayesian analyses of monitoring data. The WeLMoS method randomly samples parameters from continuous prior probability distributions and then weights each vector by its likelihood (i.e. its goodness of fit to the measurement data). Furthermore, in order to quality assure the method, and assess its strengths and weaknesses, a second method (MCMC, Markov chain Monte Carlo) has also been developed. The MCMC method uses the Metropolis algorithm to sample directly from the posterior distribution of parameters. The methods are evaluated and compared using an artificially generated case involving an exposure to a plutonium nitrate aerosol. In addition to calculating the uncertainty on internal dose, the methods can also calculate the probability distribution of model parameter values given the observed data. In other words, the techniques provide a powerful tool to obtain the estimates of parameter values that best fit the data and the associated uncertainty on these estimates. Current applications of the methodology, including the determination of lung solubility parameters, from volunteer and cohort data, are also discussed.     

Distribution of time between failures of machining center based on type I censored data

This paper applies a type I censor likelihood function to make the fitting of Weibull distribution of time between failures of machining center (MC). The paper also gives Goodness-of-fit tests by Hollander's method and proves that the time between MC failures follows the Weibull distribution. The conclusion not only deeply analyzes the MC failure law, but also establishes the basis of calculation for the mean time between failures of MC with censored lifetime data.     

Determining the optimal maintenance action for a deteriorating repairable system

This paper develops a decision model for risk management of the deterioration of a repairable system. When a failure occurs in a deteriorating system, an optimal maintenance decision that includes the possibility of system replacement, as compared to mere deterioration reduction, should be made. There are many uncertainties associated with deterioration, however, so the decision may require a probabilistic analysis. Here, a well-known nonhomogeneous Poisson process with a power law intensity function is used to model the uncertain behavior of the deteriorating system. A Bayesian statistical approach is adopted to allow for the uncertainty of the parameters of the power law intensity function, which imposes a conjugate prior distribution of the parameters. A power law maintenance cost function and the failure cost are analyzed to determine the magnitude of failure risk reduction by minimizing the expected cost incurred from the maintenance action and future failures. A numerical example is given.     

Formulating informative, data-based priors for failure probability estimation in reliability analysis

Priors play an important role in the use of Bayesian methods in risk analysis, and using all available information to formulate an informative prior can lead to more accurate posterior inferences. This paper examines the practical implications of using five different methods for formulating an informative prior for a failure probability based on past data. These methods are the method of moments, maximum likelihood (ML) estimation, maximum entropy estimation, starting from a non-informative ‘pre-prior’, and fitting a prior based on confidence/credible interval matching. The priors resulting from the use of these different methods are compared qualitatively, and the posteriors are compared quantitatively based on a number of different scenarios of observed data used to update the priors. The results show that the amount of information assumed in the prior makes a critical difference in the accuracy of the posterior inferences. For situations in which the data used to formulate the informative prior is an accurate reflection of the data that is later observed, the ML approach yields the minimum variance posterior. However, the maximum entropy approach is more robust to differences between the data used to formulate the prior and the observed data because it maximizes the uncertainty in the prior subject to the constraints imposed by the past data.     

Model validation under epistemic uncertainty

This paper develops a methodology to assess the validity of computational models when some quantities may be affected by epistemic uncertainty. Three types of epistemic uncertainty regarding input random variables - interval data, sparse point data, and probability distributions with parameter uncertainty - are considered. When the model inputs are described using sparse point data and/or interval data, a likelihood-based methodology is used to represent these variables as probability distributions. Two approaches - a parametric approach and a non-parametric approach - are pursued for this purpose. While the parametric approach leads to a family of distributions due to distribution parameter uncertainty, the principles of conditional probability and total probability can be used to integrate the family of distributions into a single distribution. The non-parametric approach directly yields a single probability distribution. The probabilistic model predictions are compared against experimental observations, which may again be point data or interval data. A generalized likelihood function is constructed for Bayesian updating, and the posterior distribution of the model output is estimated. The Bayes factor metric is extended to assess the validity of the model under both aleatory and epistemic uncertainty and to estimate the confidence in the model prediction. The proposed method is illustrated using a numerical example.     

An additive Chen-Weibull distribution and its applications in reliability modeling

In this article, we introduce a new lifetime distribution with increasing and bathtub-shaped failure rates. Some statistical properties of the proposed distribution are studied. We use the method of maximum likelihood for estimating the model parameters and reliability characteristics and discuss the interval estimates using asymptotic confidence intervals and bootstrap confidence intervals on one hand, and we provide Bayes estimators and highest posterior density intervals for the parameters via Hamiltonian Monte Carlo simulation method on the other hand. We demonstrate the superiority of the proposed distribution by fitting two reliability data sets well-known from references.     

基于改进MCMC方法的有限元模型修正研究

针对马尔可夫链蒙特卡罗(MCMC)模型修正方法在待修正参数维数较高时不易收敛和计算效率低下的问题,建立了融合自适应算法和相关向量机的快速模型修正方法。基于广义无偏见先验分布,推导了待修正参数的后验分布;在标准MCMC方法的基础上,引入延缓拒绝算法以提高新样本接受概率;引入自适应算法以自主调整建议分布的带宽。通过相关向量机建立待修正参数与有限元模型理论计算值之间的回归模型,以提高模型修正的计算效率。数值模拟和试验结构的模型修正结果表明,该方法的收敛速度较快,计算效率优于传统的一阶优化模型修正方法,为解决不确定性模型修正中的计算效率提供了一种新手段。     

基于拒绝抽样算法的结构体系可靠度更新

该文着重研究基于观测信息的结构体系可靠度更新模型及其拒绝抽样算法。基于Bayesian理论建立考虑观测信息的结构体系失效概率更新模型,根据观测信息事件类型建立不等式和等式观测信息条件下随机变量的似然函数并推导其后验概率密度函数;基于观测信息域确定随机变量后验样本的拒绝抽样策略,探究拒绝抽样算法的抽样效率,推导更新后结构体系失效概率估计值及其标准差的计算公式;将上述方法应用于刚架结构发生塑性失效时体系可靠度更新计算。研究表明:考虑观测信息的结构体系条件失效概率更新模型可转化为随机变量后验概率密度在失效域上的积分,构造满足观测信息域的先验样本作为随机变量后验样本的抽样策略是可行的,该抽样策略可以处理多随机变量、多观测信息条件下结构体系可靠度更新;与抗力相关随机变量检测值增大及验证荷载值提高均可以降低更新后结构体系的失效概率,与抗力相关的随机变量还需控制其检测误差的标准差,以降低观测信息的不确定性。     

On robust methods for failure rate estimation

An effective method is developed for estimating failure rates for plant-specific risk studies from scarce data. A new technique is used for determining empirical prior distributions first, and individual component estimates are then determined as posterior distributions.This parametric robust empirical Bayes (PREB) method is applied to globe valve data and compared to other methods with a variety of numerical data. The results demonstrate the superiority of the PREB method over alternative techniques, especially for small samples. Connections to Stein's and fiducial estimation are discussed, and methodological recommendations are given for generic or design-specific risk studies and failure rate coupling studies.     

Accounting for Parameter Uncertainty in Simulation Input Modeling

We formulate and evaluate a Bayesian approach to probabilistic input modeling for simulation experiments that accounts for the parameter and stochastic uncertainties inherent in most simulations and that yields valid predictive inferences about outputs of interest. We use prior information to construct prior distributions on the parameters of the input processes driving the simulation. Using Bayes' rule, we combine this prior information with the likelihood function of sample data observed on the input processes to compute the posterior parameter distributions. In our Bayesian simulation replication algorithm, we estimate parameter uncertainty by independently sampling new values of the input-model parameters from their posterior distributions on selected simulation runs; and we estimate stochastic uncertainty by performing multiple (conditionally) independent runs with each set of parameter values. We formulate performance measures relevant to both Bayesian and frequentist input-modeling techniques, and we summarize an experimental performance evaluation demonstrating the advantages of the Bayesian approach.     

基于预测模型的虚拟试验不确定性分析方法

 工程系统中不可避免地存在各种参数不确定性,利用数值计算模型对系统进行虚拟试验时应进行不确定性分析.大型耗时计算模型的不确定性分析将面临严重的的计算复杂性问题,为此,针对工程应用中耗时计算模型,提出一种基于贝叶斯预测模型的不确定性分析仿真方法,采用概率分布为参数不确定性建模,研究系统响应预测不确定性的概率特征.泰勒杆撞击实例验证了该方法的高效性.