Parameter estimation in multi–component systems with failure interaction

In multi–component systems, failure of a component often affects one or more of the remaining components of the system. This type of interaction between components is called ‘failure interaction’. In this paper we consider two failure interaction models and study the problem of estimating the parameters of these models.     

Preservation of reliability classes under the formation of coherent systems

The preservation of reliability aging classes under the formation of coherent systems is a relevant topic in reliability theory. Thus, it is well known that the new better than used class is preserved under the formation of coherent systems with independent components. However, surprisingly, the increasing failure rate class is not preserved in the independent and identically distributed case, that is, the components may have the (negative) aging increasing failure rate property, but the system does not have this property. In this paper, we study conditions for the preservation of the main reliability classes under the formation of general coherent systems. These results can be applied both for systems with independent or dependent components. We consider both the case of systems with identically distributed components and the case of systems with components having different distributions. Copyright © 2013 John Wiley & Sons, Ltd.     

Multi-state Systems with Graduate Failure and Equal Transition Intensities

We consider unrecoverable homogeneous multi-state systems with graduate failures, where each component can work at M + 1 linearly ordered levels of performance. The underlying process of failure for each component is a homogeneous Markov process such that the level of performance of one component can change only for one level lower than the observed one, and the failures are independent for different components. We derive the probability distribution of the random vector X, representing the state of the system at the moment of failure and use it for testing the hypothesis of equal transition intensities. Under the assumption that these intensities are equal, we derive the method of moments estimators for probabilities of failure in a given state vector and the intensity of failure. At the end we calculate the reliability function for such systems. Received: May 18, 2007., Revised: July 8, 2008., Accepted: September 29, 2008.     

Optimal burn-in for maximizing reliability of repairable non-series systems

Burn-in is a manufacturing process applied to products to eliminate early failures in the factory before the products reach the customers. Various methods have been proposed for determining an optimal burn-in time of a non-repairable system or a repairable series system, assuming that system burn-in improves all components in the system. In this paper, we establish the trade-off between the component reliabilities during system burn-in and develop an optimal burn-in time for repairable non-series systems to maximize reliability. One impediment to expressing the reliability of a non-series system is in that successive failures during system burn-in cannot be described precisely because a failed component is not detected until the whole system fails. For approximating the successive failures of a non-series system during system burn-in, we considered two types of repair: minimal repair at the time of system failure, and repair at the time of component or connection failure. The two types of repair provide bounds on the optimal system burn-in time of non-series systems.     

Comparisons of series and parallel systems with components sharing the same copula

The paper is devoted to study stochastic comparisons of series and parallel systems with vectors of component lifetimes sharing the same copula. We show that, under some conditions on the common copula, the series system with heterogeneous components is worse than the series system with homogeneous components having a common reliability function, which is equal to the average of the reliability functions of the heterogeneous components. However, we show that this property is not necessarily true for arbitrary copulas. We obtain similar properties for parallel systems and for general coherent systems. For these purposes, we introduce in our analysis the notion of the mean function of a copula. Copyright © 2009 John Wiley & Sons, Ltd.     

Stochastic ordering properties for systems with dependent identically distributed components

In this paper, we obtain ordering properties for coherent systems with possibly dependent identically distributed components. These results are based on a representation of the system reliability function as a distorted function of the common component reliability function. So, the results included in this paper can also be applied to general distorted distributions. The main advantage of these results is that they are distribution‐free with respect to the common component distribution. Moreover, they can be applied to systems with component lifetimes having a non‐exchangeable joint distribution. Copyright © 2012 John Wiley & Sons, Ltd.     

基于马尔科夫过程的储备系统稳态性能分析

由于储备系统组成部件在存储期间的失效概率各不相同,当部件状态趋于稳定时,各个状态对系统性能的影响也存在差异。为了识别关键部件及其状态对系统性能的影响程度,本文以重要度为主要指标,应用马尔科夫过程研究储备系统在稳态时的性能变化模式。首先基于综合重要度研究系统性能的变化规律,并结合冷储备系统和温储备系统的状态转移矩阵推导出马尔科夫过程中稳态值的计算方法;其次基于稳态综合重要度获得系统稳态时的性能变化模式;最后以双臂机器人为例,分析部件处于不同状态时对系统性能的影响模式,比较了不同部件综合重要度的变化,验证了提出方法的有效性。     

A continuity theorem and some counterexamples for the theory of maintained systems

The reliability of maintained systems is considered. A “continuity theorem” is presented which states that the stochastic behavior of a maintained system depends continuously on the stochastic behavior of its components. Examples of maintained systems with IFR component lifetimes and exponential repair times are presented for which time until first system failure is not NBU.     

利用隐蔽的系统寿命数据估计元件的可靠性

考虑由一个成败型元件和一个指数寿命型元件组成的串联系统。本文利用隐蔽的系统一次性检测数据估计元件的可靠性，给出元件可靠性的极大似然估计和区门估计，给出了算例。     

Stochastic Properties of Components in a Used Coherent System

Some coherent systems are such that failure of the system does not mean that all components fail. This paper investigates the stochastic behavior and reliability properties of the residual lifetime of live components in coherent systems under the assumption that the system fails at time t. We also investigate the stochastic properties of inactivity time of failed components in coherent systems where failure of some components does not cause the failure of the complete system.     

冷备系统可靠性评定的统计方法

贮备是提高系统可靠性可行且有效的途径.关于冷备系统的可靠性评定问题,前人仅在设备均为指数型部件的情况给出了WCF方法.文中对实际中常用的指数-威布尔混合型冷备系统,提出了两种可靠性评定方法:WCF方法和Fiducial方法,并在中小样本下对两种方法进行了模拟研究,说明了这两种方法的实用性.     

Nonparametric inference for sequential <Emphasis Type="Italic">k</Emphasis>-out-of-<Emphasis Type="Italic">n</Emphasis> systems

The k-out-of-n model is commonly used in reliability theory. In this model the failure of any component of the system does not influence the components still at work. Sequential k-out-of-n systems have been introduced as an extension of k-out-of-n systems where the failure of some component of the system may influence the remaining ones. We consider nonparametric estimation of the cumulative hazard function, the reliability function and the quantile function of sequential k-out-of-n systems. Furthermore, nonparametric hypothesis testing for sequential k-out-of-n-systems is examined. We make use of counting processes to show strong consistency and weak convergence of the estimators and to derive the asymptotic distribution of the test statistics.     

Joint Reliability Function of Coherent Systems with Shared Heterogeneous Components

In this paper, we consider two coherent systems having shared components. We assume that in the two systems there are three different types of components; components of type one that just belong to the first system, components of type two that lie only in the second system and components of type three that are shared by the two systems. We use the concept of joint survival signature to assess the joint reliability function of the two systems. Using this concept, some representations for the joint reliability function of the system lifetimes are obtained under two different scenarios of component failures. In the first scenario, we assume that the components of the systems fail according to different counting processes such as non-homogeneous Poisson processes. In the second scenario, it is assumed that the component lifetimes of each type are exchangeable while the three types of component lifetimes can be independent or dependent. To illustrate the theoretical results, two systems with shared components are studied numerically and graphically.

     

Nonparametric predictive reliability of series of voting systems

Nonparametric Predictive Inference (NPI) for system reliability reflects the dependence of reliabilities of similar components due to limited knowledge from testing. NPI has recently been presented for reliability of a single voting system consisting of multiple types of components. The components are all assumed to play the same role within the system, but with regard to their reliability components of different types are assumed to be independent. The information from tests is available per type of component. This paper presents NPI for systems with subsystems in a series structure, where all subsystems are voting systems and components of the same type can be in different subsystems. As NPI uses only few modelling assumptions, system reliability is quantified by lower and upper probabilities, reflecting the limited information in the test data. The results are illustrated by examples, which also illustrate important aspects of redundancy and diversity for system reliability.     

System reliability and component importance when components can be swapped upon failure

Resilience of systems to failures during functioning is of great practical importance. One of the strategies that might be considered to enhance reliability and resilience of a system is swapping components when a component fails, thus replacing it by another component from the system that is still functioning. This paper studies this scenario, particularly with the use of the survival signature to quantify system reliability, where it is assumed that such a swap of components requires these components to be of the same type. We examine the effect of swapping components on a reliability importance measure for the specific components, and we also consider the joint reliability importance of two components. Such swapping of components may be an attractive means toward more resilient systems and could be an alternative to adding more components to achieve redundancy of repair and replacement activities.     

Reliability assessment for load‐sharing systems with exponential components using statistical expansion as a correction

Among recent system models, one specific type of system is generally used to model the dependence among components. Components are connected parallel in such systems as they fail one by one and are supposed to share the system work load. The model is thus referred to as the load‐sharing system model. Despite the availability of extensive reliability assessment methods for different systems, load‐sharing systems have not received enough attention from the scholars who have studied reliability assessment so far. Load‐sharing systems are generally designed for high levels of reliability. Therefore, tests for such systems can be expensive and time consuming. Limitation on resources always leads to small test sample sizes. This increases the difficulties associated with obtaining an accurate and robust system reliability assessment result. This paper proposes a novel assessment method for a certain type of load‐sharing system with components following exponential lifetime distributions. Based on the parameter estimation of the system reliability model, we introduce the Winterbottom‐Cornish‐Fisher asymptotic expansion method for implementing a correction of normal approximation. We demonstrate the accuracy of our method through a series of examples and simulation studies.     

Multistate components assignment problem with optimal network reliability subject to assignment budget

The typical assignment problem for finding the optimal assignment of a set of components to a set of locations in a system has been widely studied in practical applications. However, this problem mainly focuses on maximizing the total profit or minimizing the total cost without considering component’s failure. In practice, each component should be multistate due to failure, partially failure, or maintenance. That is, each component has several capacities with a probability distribution and may fail. When a set of multistate components is assigned to a system, the system can be treated as a stochastic-flow network. The network reliability is the probability that d units of homogenous commodity can be transmitted through the network successfully. The multistate components assignment problem to maximize the network reliability is never discussed. Therefore, this paper focuses on solving this problem under an assignment budget constraint, in which each component has an assignment cost. The network reliability under a components assignment can be evaluated in terms of minimal paths and state-space decomposition. Subsequently an optimization method based on genetic algorithm is proposed. The experimental results show that the proposed algorithm can be executed in a reasonable time.     

成败型元件串并联系统及并串联系统可靠性置信下限近似解的讨论

本文讨论由相互独立的成败型元件组成的串并联系统及并串联系统可靠性置信下限的近似解。本文利用系统诸元件的试验数据,在一、二阶矩拟合的原则下将其折合为原系统的伪试验数及伪成功数,然后利用单个成败型元件的可靠性的经典精确置信下限作为原系统可靠性置信下限的近似值。本文推导了伪试验数N及伪成功数S的计算公式,并给出了计算实例。     

Modeling and analysis of system reliability using phase‐type distribution closure properties

Phase‐type distribution closure properties are utilized to devise algorithms for generating reliability functions of systems with basic structures. These structures include series, parallel, K‐out‐of‐N, and standby structures with perfect/imperfect switch. The algorithms form a method for system reliability modeling and analysis based on the relationship between the system lifetime and component lifetimes for general structures. The proposed method is suitable for functional system reliability analysis, which can produce reliability functions of systems with independent components instead of only system reliability values. Once the system reliability function is obtained, other reliability measures such as the system's hazard function and mean time to failure can be obtained efficiently using only matrix algebra. Dimensional and numerical comparisons with computerized symbolic processing are also presented to show the superiority of the proposed method.     

Comparisons in the mean residual life order of coherent systems with identically distributed components

The comparisons of the performance of coherent systems (under different stochastic criteria) is an important task in the reliability theory. Several results have been obtained in the literature for the stochastic, hazard rate and likelihood ratio orders. In this paper, we obtain comparison results for the mean residual life order of coherent systems with identically distributed (ID) component lifetimes. These results can be applied not only to the usual case of systems with independent and identically distributed components but also to the case of systems with exchangeable components and to the more general case of just ID components. The results obtained are based on the representation of the system distribution as a distorted distribution of the common components' distribution. Some specific comparison results are given to illustrate the theoretical results. The comparison results for distorted distributions given here can also be applied to other statistical concepts such as order statistics, generalized order statistics or record values. Copyright © 2015 John Wiley & Sons, Ltd.