Inference on a future reliability parameter with the weibull process model

An inferential procedure is presented which provides confidence intervals for a future reliability parameter when reliability growth testing is only partially completed. Hypothesis tests based on this method are uniformly most powerful unbiased. These results are applicable if (1) the system failure rate can be modeled as the intensity function of a Weibull process and (2) efforts to improve reliability are assumed to continue at a steady rate throughout the intervening period of testing. The usefulness of this methodology is illustrated by evaluating the risk of not reaching some future reliability milestone. If such risk is unacceptably high, program management may have time to identify problem areas and take corrective action before testing has ended. As a consequence, a more reliable system may be developed without incurring overruns in the scheduling or cost of the development program.     

Model parameter estimation and residual life prediction for a partially observable failing system

We consider a partially observable degrading system subject to condition monitoring and random failure. The system's condition is categorized into one of three states: a healthy state, a warning state, and a failure state. Only the failure state is observable. While the system is operational, vector data that is stochastically related to the system state is obtained through condition monitoring at regular sampling epochs. The state process evolution follows a hidden semi‐Markov model (HSMM) and Erlang distribution is used for modeling the system's sojourn time in each of its operational states. The Expectation‐maximization (EM) algorithm is applied to estimate the state and observation parameters of the HSMM. Explicit formulas for several important quantities for the system residual life estimation such as the conditional reliability function and the mean residual life are derived in terms of the posterior probability that the system is in the warning state. Numerical examples are presented to demonstrate the applicability of the estimation procedure and failure prediction method. A comparison results with hidden Markov modeling are provided to illustrate the effectiveness of the proposed model. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 190–205, 2015     

基于年龄更换策略的威布尔分布备件需求计算方法

备件需求量预测在装备保障工作中发挥着重要作用。预防性维修可以消除装备潜在的故障或避免装备发生故障后所导致的严重后果,从而使装备始终处于期望状态。预防性维修策略下备件需求量建模能够以可预见的可靠性数据为基础进行,其关键问题是最佳更换间隔时间的确定。针对威布尔分布装备备件,采用年龄更换策略,确定最佳更换间隔时间,并在此基础上导出威布尔型备件需求计算模型,为备件需求量的预测提供了一种简单有效的方法。     

动态系统可靠性分析的新概念

传统可靠性分析的概念只能描述静态逻辑关系,不能满足现代复杂动态系统可靠性分析的需要。在给出动态系统状态空间结构和结构函数的基础上,提出失效序列和失效丛的概念描述动态系统的故障模式,这一概念扩展了传统可靠性分析的概念,将割集、蕴含集等作为其在静态情形的特例。给出动态系统部件的概率重要度、结构重要度以及关键重要度的概念,用实例对提出的有关概念进行了说明。     

小子样多失效模式系统可靠性竞争模型

为解决小子样多失效模式系统可靠性模型参数的估计问题,首先应用支持向量积建立小子样条件下各故障模式的规律模型,其次利用模型将各故障模式的故障数据由小子样扩充成大样本,再次采用常规的参数估算方法估算各故障模式的分布参数,最后建立多失效模式系统的可靠性竞争模型。利用所提方法,建立了小子样条件下具有两种失效模式的柴油机汽缸套可靠性竞争模型,计算结果与大样本条件下的故障预测数据吻合度较高,说明了方法的有效性。     

Reliability inference for field conditions from accelerated degradation testing

Accelerated degradation testing (ADT) is usually conducted under deterministic stresses such as constant‐stress, step‐stress, and cyclic‐stress. Based on ADT data, an ADT model is developed to predict reliability under normal (field) operating conditions. In engineering applications, the “standard” approach for reliability prediction assumes that the normal operating conditions are deterministic or simply uses the mean values of the stresses while ignoring their variability. Such an approach may lead to significant prediction errors. In this paper, we extend an ADT model obtained from constant‐stress ADT experiments to predict field reliability by considering the stress variations. A case study is provided to demonstrate the proposed statistical inference procedure. The accuracy of the procedure is verified by simulation using various distributions of field stresses. © 2006 Wiley Periodicals, Inc. Naval Research Logistics, 2006.     

A methodology for studying the dynamics of extended logistic systems

An extended logistic system is a well-defined configuration of equipment, modules, inventories, and repair and replacement facilities modeling a complex, repairable system with on-going repair. The design of such systems has been based largely on the static tools of inventory theory and reliability theory, i.e., on steady-state distributions and on associated means and variances. Such static tools suppress the scale of real lime and ignore system persistence time in up-states and persistence time in down-states. A reasonably simple dynamic methodology is presented, focusing on system failure time as a more meaningful objective function for system-design tradeoff studies. In the presence of good reliability, it is shown that different candidates for system failure time effectively merge to yield an unambiguous, single system failure time. Examples illustrating the importance of dynamic information for system design are given.     

复杂系统故障安全风险评价方法

复杂系统的安全风险涉及面广、影响因素多,因此需要系统的、可操作的方法来指导安全风险的评价过程。在系统的各类安全风险中,故障安全风险是由各种故障导致系统发生事故的风险,是最常见的系统安全问题,因此针对复杂系统的故障安全风险评价开展研究。复杂系统故障安全风险评价需要明确的评价参数和评价方法的支持,为此提出了复杂系统故障安全风险评价的流程、分层次的评价参数体系及评价方法,并通过示例来具体说明故障安全风险的评价过程,为解决复杂系统的故障安全风险评价问题提出了可行的思路。     

64mm催泪弹的空中运动特性研究

建立64mm催泪弹外弹道数学模型,分析64mm催泪弹的空中运动状态,找出影响64mm催泪弹飞行稳定性的主要因素,给出64mm催泪弹的改进方向和技术措施,以提高催泪弹的可靠性和作用有效性,并指导现装备的催泪弹的改进和新型催泪弹的设计。     

Compound availability measures

An availability measure is the probability that a two-state system modeled by an alternating renewal process is available at one or more points or intervals. The concept of availability measures is extended to formulae for the joint prediction of availability and numbers of breakdowns (or repairs) of the system during a fixed interval.     

高性能互连网络中端口阻塞故障预测方法

随着系统规模、芯片功耗和链路速率的提升,高性能互连网络的整体故障率也不断上升,传统运维方式将难以为继,给高性能计算系统整体可靠性和可用性带来了巨大挑战。针对网络端口阻塞这类严重网络故障,提出无监督算法的预测模型。该模型从历史信息中挖掘征兆性规律并形成新的特征向量,应用K-means聚类算法对特征向量进行学习归类。在预测时,结合端口当前状态,利用二次指数平滑算法对未来状态进行预测,将得到的新特征向量使用K-means算法预判是否会发生阻塞故障。利用拓扑结构信息,分别对叶交换机和根交换机构建预测子模型,进而提升预测的精确率。结果表明,该预测模型能保持在召回率为88.2%的前提下,达到65.2%的准确率,可为运维人员提供有效的辅助。     

舰艇作战指挥决策模型可信度评估流程分析

舰艇作战指挥决策模型的可信度是一项复杂的系统工程，而评估流程又是这项工程的基础性工作，直接影响到可信度评估的成败。运用了评估学的基本理论对舰艇作战指挥决策模型可信度评估流程进行分析，将可信度评估分为三个阶段，即评估准备阶段、评估实施阶段和评估总结阶段，研究和阐述了这三个阶段的具体工作、要求和标准等，最后，建立了专家评审流程图、可信度评估指标体系以及用于可信度评估指标的数据采集表，分析对比了数据处理方法的优缺点。     

Sequential determination of inspection epochs for reliability systems with general lifetime distributions

The problem of determining the optimal inspection epoch is studied for reliability systems in which N components operate in parallel. Lifetime distribution is arbitrary, but known. The optimization is carried with respect to two cost factors: the cost of inspecting a component and the cost of failure. The inspection epochs are determined so that the expected cost of the whole system per time unit per cycle will be minimized. The optimization process depends in the general case on the whole failure history of the system. This dependence is characterized. The cases of Weibull lifetime distributions are elaborated and illustrated numerically. The characteristics of the optimal inspection intervals are studied theoretically.     

装备维修中备件需求率的预计方法

通过研究装备维修过程中器件的固有可靠性和维修性,着重分析了影响维修器件需求率的主要因素.利用系统建模和仿真的方法,分别针对耗损类型器件和可修复类型器件建立了相应的需求数学模型,最后给出了维修备件需求率的预计方法.     

Dynamic signatures and their use in comparing the reliability of new and used systems

The signature of a system with independent and identically distributed (i.i.d.) component lifetimes is a vector whose ith element is the probability that the ith component failure is fatal to the system. System signatures have been found to be quite useful tools in the study and comparison of engineered systems. In this article, the theory of system signatures is extended to versions of signatures applicable in dynamic reliability settings. It is shown that, when a working used system is inspected at time t and it is noted that precisely k failures have occurred, the vector s [0,1]^n‐k whose jth element is the probability that the (k + j)th component failure is fatal to the system, for j = 1,2,2026;,n ‐ k, is a distribution‐free measure of the design of the residual system. Next, known representation and preservation theorems for system signatures are generalized to dynamic versions. Two additional applications of dynamic signatures are studied in detail. The well‐known “new better than used” (NBU) property of aging systems is extended to a uniform (UNBU) version, which compares systems when new and when used, conditional on the known number of failures. Sufficient conditions are given for a system to have the UNBU property. The application of dynamic signatures to the engineering practice of “burn‐in” is also treated. Specifically, we consider the comparison of new systems with working used systems burned‐in to a given ordered component failure time. In a reliability economics framework, we illustrate how one might compare a new system to one successfully burned‐in to the kth component failure, and we identify circumstances in which burn‐in is inferior (or is superior) to the fielding of a new system. © 2009 Wiley Periodicals, Inc. Naval Research Logistics, 2009     

Design and analysis of a scheme for the naval gun test shell entering the bore

The test shell without projectile belt is widely used in the teaching, inspection and maintenance of modern automatic naval guns. In order to ensure the normal work of each mechanism, it is very important to design the buffer and limit of the test shell during the process of entering the bore. Taking a certain type of medium caliber naval gun as the research object, the design of colloidal fluid damper and cartridge lock was proposed to ensure the reliability of entering the bore and closing the breechblock. By combining the simulation methods of computational fluid dynamics (CFD) and multibody system dy-namic (MBD), it was analyzed whether the structural design can meet the engineering requirements. The research results show that the colloidal fluid damper can dissipate a large amount of kinetic energy of the shell, and the cartridge lock can limit the rebound movement. The combination of the two ensures the smooth process of closing the breechblock. The research provides a design method for the process of the test shell entering the bore, and provides theoretical support for the feasibility of the method.     

具有节点失效的网络可靠度的信息交互算法

提出了一种用于计算具有节点失效的网络可靠度的新计算方法。该算法依据不交化代数及协同计算的思想,采用节点信息义互的方法直接获得网络的不交化最小路集。算法简便易行,具有分布计算的特点,为大型网络系统的可靠性度计算提供了一种新的途径。     

基于平均互信息熵的复杂系统可靠性评定方法

可靠性评定是定量评估系统可靠性水平的重要途径,是对其可靠性进行定量控制的必要手段.某些复杂系统由于研制时间和经费的限制,现场试验样本量极其有限,依赖传统的基于大样本的数理统计方法将难以获得客观结论,因此其可靠性评定一直是工程实践中的技术难题.针对复杂系统可靠性评估和寿命预测时现场样本量不足的问题,提出了一种基于多源信息融合的可靠性评定方法.该方法利用平均互信息熵来度量多源验前信息对可靠性评定不确定性减少所起的作用,以此为依据确定多源信息融合权重,并通过融合验前分布进行复杂系统的可靠性评定,从而减少了评定过程中的主观性,增强了评定结论的可信性.最后通过仿真实例验证了方法的有效性.     

Scheduling economic lot sizes in deteriorating production systems

The paper considers the economic lot scheduling problem (ELSP) where production facility is assumed to deteriorate, owing to aging, with an increasing failure rate. The time to shift from an “in‐control” state to an “out‐of‐control” state is assumed to be normally distributed. The system is scheduled to be inspected at the end of each production lot. If the process is found to be in an “out‐of‐control” state, then corrective maintenance is performed to restore it to an “in‐control” state before the start of the next production run. Otherwise, preventive maintenance is carried out to enhance system reliability. The ELSP is formulated under the capacity constraint taking into account the quality related cost due to possible production of non‐conforming items, process inspection, and maintenance costs. In order to find a feasible production schedule, both the common cycle and time‐varying lot sizes approaches are utilized. © 2003 Wiley Periodicals, Inc. Naval Research Logistics 50: 650–661, 2003     

Reliability growth of repairable systems

This paper considers the problem of modeling the reliability of a repairable system or device that is experiencing reliability improvement. Such a situation arises when system failure modes are gradually being corrected by a test-fix-test-fix procedure, which may include design changes. A dynamic reliability model for this process is discussed and statistical techniques are derived for estimating the model parameters and for testing the goodness-of-fit to observed data. The reliability model analyzed was first proposed as a graphical technique known as Duane plots, but can also be viewed as a nonhomogeneous Poisson process with a particular mean value function.