Reliability of repairable reserved systems with failure aftereffect

We propose new models for analyzing the reliability of repairable systems with failure aftereffect, when the probability distribution of an element’s time to failure changes only during the time when another element is being repaired. The key idea here is the so-called coupling principle for various probability distributions when the system’s operation conditions or the “residual lifetime preservation condition” change. We show a method for constructing a system of integral equations as a universal tool for modeling the reliability of systems under the assumption that time to failure of each element obeys the Weibull distribution.     

Availability optimisation of repairable system with preventive maintenance policy

This article investigates optimal steady availability of a repairable system with six states. Both preventive maintenance and corrective maintenance are considered in this article. By probability argument, the system is described as an abstract Cauchy problem. Using the method of strong continuous semi-group theory, we derive the steady availability of the system. Finally, the optimal time to carry out preventive maintenance is analysed theoretically and numerical examples are presented.     

Evolutionary neural network modeling for forecasting the field failure data of repairable systems

An accurate product reliability prediction model can not only learn and track the product’s reliability and operational performance, but also offer useful information for managers to take follow-up actions to improve the product’ quality and cost. This study proposes a new method for predicting the reliability for repairable systems. The novel method constructs a predictive model by employing evolutionary neural network modeling approach. Genetic algorithms are used to globally optimize the number of neurons in the hidden layer and learning parameters of the neural network architecture. Moreover, two case studies are presented to illustrate the proposed method. The prediction accuracy of the novel method is compared with that of other methods to illustrate the feasibility and effectiveness of the proposed method.     

Evolutionary neural network modeling for forecasting the field failure data of repairable systems

An accurate product reliability prediction model can not only learn and track the product’s reliability and operational performance, but also offer useful information for managers to take follow-up actions to improve the product’ quality and cost. This study proposes a new method for predicting the reliability for repairable systems. The novel method constructs a predictive model by employing evolutionary neural network modeling approach. Genetic algorithms are used to globally optimize the number of neurons in the hidden layer and learning parameters of the neural network architecture. Moreover, two case studies are presented to illustrate the proposed method. The prediction accuracy of the novel method is compared with that of other methods to illustrate the feasibility and effectiveness of the proposed method.     

Availability of a repairable retrial system with warm standby components

In this paper, we study a repairable K-out-of-(M+W) retrial system with M identical primary components, W standby components and one repair facility. The time-to-failure and time-to-repair of the primary and standby components are assumed to be exponential and general distributions, respectively. The failed components are immediately for repair if the server is idle, otherwise the failed machines would enter an orbit. It is assumed that the retrial times are exponentially distributed. We present a recursive method using the supplementary variable technique and treating the supplementary variable as the remaining repair time to obtain the steady-state probabilities of down components at arbitrary epoch. Then, a unified and efficient algorithm is developed to compute the steady-state availability. The method is illustrated analytically for the exponential repair time distribution. Sensitivity analysis of the steady-state availability with respect to system parameters for a variety of repair time distributions is also investigated.     

Change-point detection in failure intensity: A case study with repairable artillery systems

Repairable systems can experience unexpected environmental changes over long operational periods. Such changes affect the incidence of failures, causing different system failure patterns before and after the changes. In this article, we propose an informational change-point approach for the pattern of recurrent failures in repairable artillery systems. Unlike other trend tests, this approach provides additional information about the locations of change-points over rates of occurrence of failures (ROCOFs) as well as failure trends. We adopt the modified information criterion (MIC) proposed by Pan and Chen (2006) to detect the locations of the changes and propose sequential procedures for determining the number of change-points in independent exponential sequences. The change-point approach is applied to unscheduled maintenance data from eight artillery system exercises performed by the Republic of Korea Army. The change-point test along with a graphical presentation of estimated ROCOF lines can provide easy interpretation of changes in failure trends/intensities in a homogeneous Poisson process.     

Estimates of system failure probability during the renewal time for a group of repairable systems

Translated from Kibernetika i Sistemnyi Analiz, No. 6, pp. 170–173, November–December, 1995.     

Availability and reliability of teleprocessing systems

Computer communications network users notice a lack of network transparency in two main ways: service interruptions and excessive response times.A simplified analysis of the effects of service interruptions on terminal-user satisfaction and productivity, and on the lateness of session results is presented. A method of determining acceptable, or any other chosen level of, service as seen by the user in terms of the mean time between failures and the mean time to repair of interruptions is outlined. A hypothetical example is discussed to clarify the theoretical analysis.     

存储系统中的局部修复阵列码模型

对于单容错和双容错的存储系统,在磁盘修复过程中发生的任何故障都可能引起数据丢失,导致修复失败,保证数据的修复效率对于存储系统的可靠性至关重要。RDP码在进行单盘故障修复时使用混合恢复算法能减少25%的读取总量,但是在进行双盘故障修复时需读取所有的元素。针对目前难以同时提升单双盘故障修复效率的问题,对RDP码进行拓展,提出了一种具有局部修复性质的阵列码模型——DRDP码。DRDP码在RDP码的基础上将部分数据列按水平线进行异或计算生成局部水平校验列,并将其参与到全局校验列的编码计算中,从而缩短了修复链,使其拥有局部修复的功能。通过理论分析,DRDP码拥有良好的编译码复杂度和更新效率,大幅节省了单盘故障修复读取开销,并对双盘故障修复读取开销进行了优化,同时能修复75%三盘故障的情况。实验结果表明,与RDP码、LRRDP码和RDP(p,3)码相比,DRDP码的编码时间可节省8.23%～32.89%、单盘故障修复时间可节省7.08%～35.01%、双盘故障修复时间可节省5.07%～29.26%。     

RAM analysis of repairable industrial systems utilizing uncertain data

Industrial systems are mostly complex and considered as repairable. Also data, either collected or available (historical), reflecting their failure and repair patterns are limited, vague and imprecise due to various practical constraints. In such circumstances, their reliability, availability and maintainability (RAM) analysis may play an important role in any design modifications, if required, for achieving its optimum performance. However, it is difficult to estimate the RAM parameters of these systems up to a desired degree of accuracy by utilizing available information and uncertain data. This paper provides an idea, how can we estimate the RAM parameters of these systems by utilizing available information and uncertain data. For this purpose, Genetic Algorithms based Lambda–Tau (GABLT) technique is used. In this technique, expressions for the RAM parameters of the system are obtained by using traditional Lambda–Tau methodology and genetic algorithm is used to compute these parameters in the form of fuzzy membership functions utilizing quantified data in the form of triangular fuzzy numbers. A general RAM-Index is used for post RAM analysis to rank the subunits of the system on the basis of their performance. The approach has been applied to the press (series system) and washing (series–parallel system) units of a typical paper mill. The results may be helpful for the plant personnel for analyzing the systems’ behavior and to improve their performance by adopting suitable maintenance strategies.     

一种低单盘故障恢复开销的局部修复码

如今随着存储系统规模的扩大和廉价磁盘的大量使用,单一磁盘故障在存储系统中发生故障的概率也不断上升。而在基于RDP编码的阵列存储系统中,恢复单个故障磁盘,需要读取全部的剩余数据磁盘,读取开销大,故障恢复时间长。而故障时间长就会导致系统在恢复过程中出错的概率增大,影响系统整体的稳定性。为进一步降低单个磁盘故障恢复的读取开销,减少恢复时间,提升存储系统可靠性,提出一种局部修复RDP码,通过增加一个局部冗余列来减少故障恢复时需要读取的数据量。实验结果表明改进方法在降低读取开销和减少恢复时间方面相对于传统的RDP单盘故障恢复方法有明显提高,并且能够恢复75%的三盘故障情况。     

Availability evaluation of redundant computer systems

This paper investigates availability of two redundant computer systems, a duplex system and a load share system, under the assumptions that the failure time distribution is bivariate exponential and the repair time distribution is arbitrary. We derive the limiting availability for each system by applying a unique modification of regeneration point techniques in Markov renewal processes. In particular, the procedure for obtaining the limiting probability is presented thoroughly. This paper also gives numerical examples for comparison of the two systems from the viewpoint of the availability.     

装备系统可修部件闭环保障系统绩效研究

基于绩效的后勤保障（PBL）正成为军事装备系统一种主导型保障战略。构建一个由备件仓库和部件修理车间组成的装备系统可修部件闭环保障系统。推导出备件库存水平状态稳态概率分布,获得如可用度等几个重要的保障绩效度量指标。采用数值仿真技术考察系统参数在平时与战时环境下对保障绩效的影响。结果表明,初始备件库存水平对系统可用度影响较小且随着故障强度的增加影响程度减弱,而修复能力对系统可用度影响显著。     

A computationally efficient technique for transient analysis of repairable Markovian systems

A technique to design efficient methods using a combination of explicit (non-stiff) and implicit (stiff) ODE methods for numerical transient analysis of repairable Markovian systems is proposed. Repairable systems give rise to stiff Markov chains due to extreme disparity between failure rates and repair rates. Our approach is based on the observation that stiff Markov chains are non-stiff for an initial phase of the solution interval. A non-stiff ODE method is used to solve the model for this phase and a stiff ODE method is used to solve the model for the rest of the duration until the end of solution interval. A formal criterion to determine the length of the non-stiff phase is described. A significant outcome of this approach is that the accuracy requirement automatically becomes a part of model stiffness. Two specific methods based on this approach have been implemented. Both the methods use the Runge-Kutta-Fehlberg method as the non-stiff method. One uses the TR-BDF2 method as the stiff method while the other uses an implicit Runge-Kutta method as the stiff method. Numerical results obtained from solving dependability models of a multiprocessor system and an interconnection network are presented. These results show that the methods obtained using this approach are much more efficient than the corresponding stiff methods which have been proposed to solve stiff Markov models.     

State probability of a series-parallel repairable system with two-types of failure states

This paper presents a method for the analysis of a series-parallel safety-critical system where the system states can be distinguished into failure-safe and failure-dangerous. The method incorporates the Markov chain and universal generating function technique. In the model considered, both periodic inspection and repair (perfect and imperfect) of system elements are taken into account. The system state distributions and the overall system safety function are derived, based on the developed model. The proposed method is applicable to complex systems for analysing state distributions and it is also useful in decision-making such as determining the optimal proof-test interval or repair resource allocation. An illustrative example is given.     

Preventive maintenance and replacement scheduling for repairable and maintainable systems using dynamic programming

This paper presents mathematical models and a solution approach to determine the optimal preventive maintenance schedules for a repairable and maintainable series system of components with an increasing rate of occurrence of failure (ROCOF). The maintenance planning horizon has been divided into discrete and equally-sized periods and in each period, three possible actions for each component (maintain it, replace it, or do nothing) have been considered. The optimal decisions for each component in each period are investigated such that the objectives and the requirements of the system can be achieved. In particular, the cases of minimizing total cost subject to a constraint on system reliability, and maximizing system reliability subject to a budgetary constraint on overall cost have been modeled. As the optimization methodology, dynamic programming combined with branch-and-bound method is utilized and the effectiveness of the approach is presented through the use of a numerical example. Such a modeling approach should be useful for maintenance planners and engineers tasked with the problem of developing recommended maintenance plans for complex systems of components.