Active learning accelerated Monte-Carlo simulation based on the modified K-nearest neighbors algorithm and its application to reliability estimations

This paper proposes an active learning accelerated Monte-Carlo simulation method based on the modified K-nearest neighbors algorithm.The core idea of the proposed method is to judge whether or not the output of a random input point can be postulated through a classifier implemented through the modified K-nearest neighbors algorithm.Compared to other active learning methods resorting to experimental designs,the proposed method is characterized by employing Monte-Carlo simulation for sampling inputs and saving a large portion of the actual evaluations of outputs through an accurate classification,which is applicable for most structural reliability estimation problems.Moreover,the validity,efficiency,and accuracy of the proposed method are demonstrated numerically.In addition,the optimal value of K that maximizes the computational efficiency is studied.Finally,the proposed method is applied to the reliability estimation of the carbon fiber reinforced silicon carbide composite specimens subjected to random displacements,which further validates its practicability.

Inference for accelerated bivariate dependent competing risks model based on Archimedean copulas under progressive censoring

Dependent competing risks model is a practical model in the analysis of lifetime and failure modes.The dependence can be captured using a statistical tool to explore the re-lationship among failure causes.In this paper,an Archimedean copula is chosen to describe the dependence in a constant-stress accelerated life test.We study the Archimedean copula based dependent competing risks model using parametric and nonparametric methods.The parametric likelihood inference is presented by deriving the general expression of likelihood function based on assumed survival Archimedean copula associated with the model parameter estimation.Combining the nonparametric estimation with progressive censoring and the non-parametric copula estimation,we introduce a nonparametric reliability estimation method given competing risks data.A simulation study and a real data analysis are conducted to show the performance of the estimation methods.

Reliability estimation and remaining useful lifetime prediction for bearing based on proportional hazard model

As the central component of rotating machine,the performance reliability assessment and remaining useful lifetime prediction of bearing are of crucial importance in condition-based maintenance to reduce the maintenance cost and improve the reliability.A prognostic algorithm to assess the reliability and forecast the remaining useful lifetime(RUL) of bearings was proposed,consisting of three phases.Online vibration and temperature signals of bearings in normal state were measured during the manufacturing process and the most useful time-dependent features of vibration signals were extracted based on correlation analysis(feature selection step).Time series analysis based on neural network,as an identification model,was used to predict the features of bearing vibration signals at any horizons(feature prediction step).Furthermore,according to the features,degradation factor was defined.The proportional hazard model was generated to estimate the survival function and forecast the RUL of the bearing(RUL prediction step).The positive results show that the plausibility and effectiveness of the proposed approach can facilitate bearing reliability estimation and RUL prediction.

Combination of structural reliability and interval analysis

In engineering applications, probabilistic reliability theory appears to be presently the most important method, however, in many cases precise probabilistic reliability theory cannot be considered as adequate and credible model of the real state of actual affairs. In this paper, we developed a hybrid of probabilistic and non-probabilistic reliability theory, which describes the structural uncertain parameters as interval variables when statistical data are found insufficient. By using the interval analysis, a new method for calculating the interval of the structural reliability as well as the reliability index is introduced in this paper, and the traditional probabilistic theory is incorporated with the interval analysis. Moreover, the new method preserves the useful part of the traditional probabilistic reliability theory, but removes the restriction of its strict requirement on data acquisition. Example is presented to demonstrate the feasibility and validity of the proposed theory.

An Evaluation of the Reliability of Complex Systems Using Shadowed Sets and Fuzzy Lifetime Data

In this paper, we consider the problem of the evaluation of system reliability using statistical data obtained from reliability tests of its elements, in which the lifetimes of elements are described using an exponential distribution. We assume that this lifetime data may be reported imprecisely and that this lack of precision may be described using fuzzy sets. As the direct application of the fuzzy sets methodology leads in this case to very complicated and time consuming calculations, we propose simple approximations of fuzzy numbers using shadowed sets introduced by Pedrycz （1998）. The proposed methodology may be simply extended to the case of general lifetime probability distributions.

General Conditions for Online Estimation and Optimization of Reliability Characteristics

A novel approach to estimate reliability properties of systems or components individually during operation is presented. It is distinguished between slow and fast reliability states based on an equivalent system representation. Conditions for their observability and control are given and objectives for optimal reliability-based control are discussed in general.

DISTRIBUTED MONITORING SYSTEM RELIABILITY ESTIMATION WITH CONSIDERATION OF STATISTICAL UNCERTAINTY

Taking into account the whole system structure and the component reliability estimation uncertainty, a system reliability estimation method based on probability and statistical theory for distributed monitoring systems is presented. The variance and confidence intervals of the system reliability estimation are obtained by expressing system reliability as a linear sum of products of higher order moments of component reliability estimates when the number of component or system survivals obeys binomial distribution. The eigenfunction of binomial distribution is used to determine the moments of component reliability estimates, and a symbolic matrix which can facilitate the search of explicit system reliability estimates is proposed. Furthermore, a case of application is used to illustrate the procedure, and with the help of this example, various issues such as the applicability of this estimation model, and measures to improve system reliability of monitoring systems are discussed.

Progress in Theoretical Research on Reliability for China's Space Engineering

With the support of the Fundamental Reliability Theoretical Research (FRTR) Foundation of the Quality Control Bureau of Ministry of Astronautics (MOA), PRC, 9 Chinese institutes and universities have worked for years on reliability statistics problems pending to be solved in space research and development. This paper gives a brief review of our main research results, including (1) Results on Normal Distributions; (2) Results on Weibull Distributions; (3) Results on the Synthesisof System Reliability-Theoretical Method; (4) Results on the Synthesis of System Reliability-Approximation Method: Binomial Distribution, Exponential Distribution, Weibull Distribution, Parallel System, General Cases; (5) Structual Reliability; (6) Zero-Failure Reliability Estimation; (7) Storage Life and Others. All these results can be acquired from the Quality Control Bureau of the Ministry of Aero-Space Industry (MAS).

Improving Energy and Power Efficiency Using NComputing and Approaches for Predicting Reliability of Complex Computing Systems

Opting to follow the computing-design philosophy that the best way to reduce power consumption and increase energy efficiency is to reduce waste, we propose an architecture with a very simple ready-implementation by using an NComputing device that can allow multi-users but only one computer is needed. This intuitively can save energy, space as well as cost. In this paper, we propose a simple and realistic NComputing architecture to study the energy and power-efficient consumption of desktop computer systems by using the NComputing device. We also propose new approaches to estimate the reliability of k-out-of-n systems based on the delta method. The k-out-of-n system consisting of n subsystems works if and only if at least k-of-the-n subsystems work. More specificly, we develop approaches to obtain the reliability estimation for the k-out-of-n systems which is composed of n independent and identically distributed subsystems where each subsystem （or energy-efficient usage application） can be assumed to follow a two-parameter exponential lifetime distribution function. The detailed derivations of reliability estimation of k-out-of-n systems based on the biased-corrected estimator, known as delta method, the uniformly minimum variance unbiased estimate （UMVUE） and maximum likelihood estimate （MLE） are discussed. An energy-management NComputing application is discussed to illustrate the reliability results in terms of the energy consumption usages of a computer system with qua（t-core, 8 GB of RAM, and a GeForce 9800GX-2 graphics card to perform various complex applications. The estimated reliability values of systems based on the UMVUE and the delta method differ only slightly. Often the UMVUE of reliability for a complex system is a lot more difficult to obtain, if not impossible. The delta method seems to be a simple and better approach to obtain the reliability estimation of complex systems. The results of this study also show that, in practice, the NComputing architecture improves both energy cost saving and energy efficient living spaces.

Multiple dependent reliability estimation of large range MEMS accelerometers in high temperature environment

In the past,only one performance parameter was considered in the reliability estimation of micro-electro-mechanical system (MEMS) accelerometers,resulting in a one-sided reliability evaluation. Aiming at the failure condition of large range MEMS accelerometers in high temperature environment,the corresponding accelerated degradation test is designed. According to the degradation condition of zero bias and scale factor,multiple dependent reliability estimation of large range MEMS accelerometers is carried out. The results show that the multiple dependent reliability estimation of the large range MEMS accelerometers can improve the accuracy of the estimation and get more accurate results.

Reliability analysis of extended generalized inverted exponential distribution with applications

A general version of the inverted exponential distribution is introduced, studied and analyzed. This generalization depends on the method of Marshall-Olkin to extend a family of distributions. Some statistical and reliability properties of this family are studied. In addition, numerical estimation of the maximum likelihood estimate（MLE） parameters are discussed in details. As an application, some real data sets are analyzed and it is observed that the presented family provides a better fit than some other known distributions.

Estimation of Reliability for Stress-Strength Cascade Model

The study endeavors to provide statistical inference for a (1 + 1) cascade system for exponential distribution under joint effect of stress-strength attenuation factors. Estimators of reliability function are obtained using Maximum Likelihood Estimator (MLE) and Uniformly Minimum Variance Unbiased Estimator (UMVUE) of the parameters. Asymptotic distribution of the parameters is also obtained. Comparison between estimators is made using data obtained through simulation experiment.

Reliability Bounds based on Universal Generating Function and Discrete Stress-strength Interference Model

A method for estimating the component reliability is proposed when the probability density functions of stress and strength can not be exactly determined. For two groups of finite experimental data about the stress and strength, an interval statistics method is introduced. The processed results are formulated as two interval-valued random variables and are graphically represented component reliability are proposed based on the by using two histograms. The lower and upper bounds of universal generating function method and are calculated by solving two discrete stress-strength interference models. The graphical calculations of the proposed reliability bounds are presented through a numerical example and the confidence of the proposed reliability bounds is discussed to demonstrate the validity of the proposed method. It is showed that the proposed reliability bounds can undoubtedly bracket the real reliability value. The proposed method extends the exciting universal generating function method and can give an interval estimation of component reliability in the case of lake of sufficient experimental data. An application example is given to illustrate the proposed method

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.

Reliability estimation of rotary lip seal in aircraft utility system based on time-varying dependence degradation model and its experimental validation

With several attractive properties, rotary lip seals are widely used in aircraft utility system, and their reliability estimation has drawn more and more attention. This work proposes a reliability estimation approach based on time-varying dependence analysis. The dependence between the two performance indicators of rotary lip seals, namely leakage rate and friction torque, is modeled by time-varying copula function with polynomial to denote the time-varying parameters, and an efficient copula selection approach is utilized to select the optimal copula function. Parameter estimation is carried out based on a Bayesian method and the reliability during the whole lifetime is calculated based on a Monte Carlo method. Degradation test for rotary lip seal is conducted and the proposed model is validated by test data. The optimal copula function and optimal order of polynomial are determined based on test data. Results show that this model is effective in estimating the reliability of rotary lip seals and can achieve a better goodness of fit.

Implementation and Analysis of Probabilistic Methods for Gate-Level Circuit Reliability Estimation

The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more susceptible to soft errors. Therefore, it is imperative to study the reliability of circuits under the soft error. This paper implements three probabilistic methods (two pass, error propagation probability, and probabilistic transfer matrix) for estimating gate-level circuit reliability on PC. The functions and performance of these methods are compared by experiments using ISCAS85 and 74-series circuits.

Evaluation of aileron actuator reliability with censored data

For the purpose of enhancing reliability of aileron of Airbus new-generation A350 XWB,an evaluation of aileron reliability on the basis of maintenance data is presented in this paper.Practical maintenance data contains large number of censoring samples, information uncertainty of which makes it hard to evaluate reliability of aileron actuator.Considering that true lifetime of censoring sample has identical distribution with complete sample, if censoring sample is transformed into complete sample, conversion frequency of censoring sample can be estimated according to frequency of complete sample.On the one hand, standard life table estimation and product limit method are improved on the basis of such conversion frequency, enabling accurate estimation of various censoring samples.On the other hand, by taking such frequency as one of the weight factors and integrating variance of order statistics under standard distribution, weighted least square estimation is formed for accurately estimating various censoring samples.Large amounts of experiments and simulations show that reliabilities of improved life table and improved product limit method are closer to the true value and more conservative; moreover, weighted least square estimate（WLSE）, with conversion frequency of censoring sample and variances of order statistics as the weights, can still estimate accurately with high proportion of censored data in samples.Algorithm in this paper has good effect and can accurately estimate the reliability of aileron actuator even with small sample and high censoring rate.This research has certain significance in theory and engineering practice.

Nonparametric Inference for the Stress-Strength Model under Right Censoring

The stress-strength model is widely applied in reliability. Observations are often subject to right censoring due to some practical limitations. In such circumstances, the statistical inference for the stress-strength model is demanding, although lacking. We propose a nonparametric method for the inference of the stress-strength model when the observations are subject to right censoring. The asymptotic properties are also established. The practical utility of the proposed method is assessed through both simulated and real data sets.