Proceedings of the Institution of Mechanical Engineers,Part O: Journal of Risk and Reliability

Preventive replacement is a well-known topic in the literature of operational research and reliability. The effects of a renewing free-replacement warranty (RFRW) on the age replacement policy for a repairable product with a general failure model are discussed. There are two types of failure when the product fails. One is type I failure, which can be removed by a minimal repair, and the other is type II failure, which can be removed only by a replacement. After a minimal repair, the product is operational but the failure rate of the product remains unchanged. For both warranted and non-warranted products, cost models are developed and the corresponding optimal replacement ages are derived based on the minimized long run expected cost rate. The impacts of the RFRW on the optimal replacement age are investigated analytically. Finally, numerical examples are given for the purposes of illustration.

For repairable items, the manufacturer is required to rectify all item failures through minimal repair, replacement, and imperfect repair should failures occur within the period specified in the warranty. In this paper, a new warranty servicing strategy is examined, considering imperfect repair with a two-dimensional warranty where the failed item is imperfectly repaired when it fails for the first time in a specified period of the warranty and all other failures are repaired minimally. The optimal servicing strategy is obtained to minimize the total expected warranty servicing cost. The proposed repair policy is compared numerically with existing strategies reported in the literature.

The reliability characteristics of automobile components depend on factors or covariates such as the automobile operating environment (e.g. temperature, rainfall, humidity, etc.), usage conditions, manufacturing periods, types of automobile that use the components, etc. In recent years, many automotive manufacturing companies utilize the warranty database as a very rich source of field reliability data that provides valuable information on such covariates for feedback to new product development systems on product performance in actual usage conditions. In the warranty database, the information on those covariates is known for the components that fail within the warranty period and are unknown for the censored components. This article considers covariates associated with some reliability-related factors and presents a Weibull regression model for the lifetime of the component as a function of such covariates. The expectation maximization (EM) algorithm is applied to obtain the ML estimates of the parameters of the model because of incomplete information on covariates. An example based on real field data of an automobile component is given and simulation studies are conducted to illustrate the use of the proposed method.

In this paper, a decision model is developed for an imperfect production system in which the demand for a product is assumed to be influenced by the warranty period offered to the customer. The production process may shift from an ‘in-control’ state to an ‘out-of-control’ state at any random time at which point non-conforming items are produced. To assess the state of the production process, periodic inspections are carried out during each production run. At the time of inspection, if the process is found to be in the ‘out-of-control’ state then restoration is done; otherwise, preventive maintenance is performed. The proposed model is formulated under a general process shift distribution and a rebate combination warranty. The expected cost per unit item is taken as the criterion for optimality. Some analytical results of the model are derived with restrictions. The optimal decisions (i.e. the optimal number of inspections, the optimal production time, and the optimal warranty period offered to the customer) are obtained numerically and the sensitivity of some model parameters is examined in a numerical example.

For repairable products, the warrantor has options in choosing the type of repair performed to an item that fails within the warranty period. The focus is on a particular warranty repair strategy, related to the degree of the warranty repair, under a non-renewing two-dimensional warranty policy that is free of charge to the consumer. A rectangular warranty region, as in the automotive industry, is considered and partitioned into disjoint subregions. Each of these subregions has a preassigned degree of repair for a faulty item. First, for a partition of size n, an expression is derived for the associated expected warranty servicing cost per item sold. Second, using an example, for a given discretization of the warranty period, the way in which the number of subregions and their shape can be determined, so that the expected warranty servicing cost per item sold is minimum, is demonstrated.

The issue of fault diagnostics is a dominant factor concerning current engineering systems. Information regarding possible failures is required in order to minimize disruption caused to functionality. A method proposed in this paper utilizes digraphs to model the information flow within an application system. Digraphs are composed from a set of nodes representing system process variables or component failure modes. The nodes are connected by signed edges thus illustrating the influence, be it positive or negative, one node has on another. System fault diagnostics is conducted through a procedure of back-tracing in the digraph from a known deviating variable. A computational method has been developed to conduct this process. Comparisons are made between retrieved transmitter readings and those expected while the system is in a known operating mode. Any noted deviations are assumed to indicate the presence of a failure. The current paper looks in detail at the application of the digraph diagnostic method to an industrially based test stand of an aircraft fuel system. This research includes transient system effects; the rate of change of a parameter is taken into consideration as a means of monitoring the system dynamically. The validity of the results achieved, through performing fault diagnostics based on the use of a digraph model, is evaluated. Finally, the effectiveness and scalability issues associated with the application of the method are addressed.

The theory of adaptive utility for sequential decision making offers a generalization of the classical Bayesian approach, permitting initial utility uncertainty. This paper examines how the possibility to learn preferences can be of interest for decisions in the area of reliability. The resulting differences in determining optimal strategies are explained and two examples are explored in which utility depends on the unknown cost of system failure. The paper concludes with a commentary on further research required.

The primary function of an electric power system is to satisfy the load requirement as economically as possible with an acceptable assurance of continuity and quality. A generating capacity adequacy evaluation involves the determination of the total system generation required to satisfy the load requirement. In these studies, a generating unit is usually represented by a two-state model in which the unit is either available or unavailable for service. These models are valid representations for base load units but do not adequately represent intermittent operating units used to meet peak load conditions. The two-state model for a base load unit has been extended to a four-state peaking unit model that is widely used in practice. The generating unit state residence time distributions in these models are assumed to be exponential in form in virtually all practical system studies. This may not be a valid assumption for the repair state in some situations. A sequential Monte Carlo simulation technique is utilized to incorporate Weibull distributed generating unit state residence times in the two-state and four-state models. The effects on the adequacy indices and the adequacy index distributions are illustrated by application to two practical test systems.

Ad hoc networking is used for the flexibility it provides. Its dynamic topology allows employment of the mobile ad hoc wireless network (MAWN) without groundwork because no infrastructure is required. However, these distinctive attributes of ad hoc networking do not conform to a key assumption under which most existing network reliability methods are founded; that network connectivity is known a priori. Therefore, ad hoc networking requires new network reliability assessment methods. Based on the unique characteristics of ad hoc networks, previous research has been focused on the development of methods that consider the probabilistic formation of the network topology and how to embed mobility models within a reliability approximation technique. This paper provides further advances in the area of MAWN reliability by removing the previous assumptions that link status is solely determined by node separation distance, resulting in a binary link behaviour. This paper proposes the use of a mathematical model for link capacity combined with a Monte Carlo simulation of the demand upon each link and each node's mobility. This new extension provides the ability to consider additional design parameters and their impact on reliability.

Suppose a technical unit is required to perform a particular task in the future, and that several different types of the unit are available. The unit could be a system or a component, the different types might be different designs or units made by different producers. Units of each type have been tested, and the result of each test of a unit is success or failure to perform the task required. It is assumed that the available test data consist of the number of tests of units per type together with the numbers of successes in these tests. In this paper comparison of different types of units on the basis of such success-failure data is considered, where it is explicitly assumed that interest is in the future performance of m ≥1 units per type. Both pairwise and multiple comparisons of such different types of units are presented, with the overall idea of selecting the particular type of unit that is likely to lead to fewest failures in the m future tasks. The use of upper and lower probabilities makes it possible to work in a non-parametric statistical framework which requires only few modelling assumptions. The influence of the value of m on the inferences is studied. In addition, special attention is given to cases where for some types of units few, or even zero, failures were observed during testing.