John S. Usher

Maximum likelihood analysis of component reliability using masked system life-test data

Life data from multicomponent systems are often analyzed to estimate the reliability of each system component. Due to the cost and diagnostic constraints, however, the exact cause of system failure might be unknown. Referring to such situations as being masked, the authors use a likelihood approach to exploit all the available information. They focus on a series system of three components, each with a constant failure rate, and propose a single numerical procedure for obtaining maximum-likelihood estimations (MLEs) in the general case. It is shown that, under certain assumptions, closed-form solutions for the MLEs can be obtained. The authors consider that the cause of system failure can be isolated to some subset of components, which allows them to consider the full range of possible information on the cause of system failure. The likelihood, while presented for complete data, can be extended to censoring. The general likelihood expressions can be used with various component life distributions, e.g., Weibull, lognormal. However, closed-form MLEs would most certainly be intractable and numerical methods would be required. >

Bayesian Inference for Masked System Lifetime Data

Estimating component and system reliabilities frequently requires using data from the system level. Because of cost and time constraints, however, the exact cause of system failure may be unknown. Instead, it may only be ascertained that the cause of system failure is due to a component in a subset of components. This paper develops methods for analysing such masked data from a Bayesian perspective. This work was motivated by a data set on a system unit of a particular type of IBM PS/2 computer. This data set is discussed and our methods are applied to it

Estimating system and component reliabilities under partial information on cause of failure

Estimating component reliabilities along with system reliability frequently requires using lifetimes from the system level. Due to cost and time constraints, however, the exact cause of system failure may be unknown. Instead it may only be ascertained that the cause of system failure is due to one component in a subset of components, e.g. the subset forms a subsystem. Confronted with such data, this article discusses how to fully exploit all of the available information using a maximum likelihood approach. We extend and clarify the useful work of Miyakawa (1984). A small Monte Carlo simulation study indicates the helpfulness of this approach.

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.

Cost optimal preventive maintenance and replacement scheduling

In this paper, we present a method for predicting a cost-optimal preventive maintenance policy for a repairable system with an increasing Rate of Occurrence Of Failure (ROCOF). We segment the maintenance planning horizon into n discrete and equally-sized periods. For each period, we predict which of three possible actions, (maintain the system, replace the system, or do nothing to the system) should be taken, such that the total net present worth of all future costs is minimized. Our model expands upon previous work by utilizing the concept that maintenance reduces the “effective age” of the system and hence the system ROCOF. We develop the model and evaluate three solution procedures, namely, a random search, a genetic algorithm, and a branch-and-bound approach. The entire approach is illustrated through the use of a numerical example.

Weibull component reliability-prediction in the presence of masked data

Analysts are often interested in obtaining component reliabilities by analyzing system-life data. This is generally done by making a series-system assumption and applying a competing-risks model. These estimates are useful because they reflect component reliabilities after assembly into an operational system under true operating conditions. The fact that most new systems under development contain a large proportion of old technology also supports the approach. In practice, however, this type of analysis is often confounded by the problem of masking (the exact cause of system failure is unknown). This paper derives a likelihood function for the masked-data case and presents an iterative procedure (IMLEP) for finding maximum likelihood estimates and confidence intervals of Weibull component life-distribution parameters. The approach is illustrated with a simple numerical example.

Exact maximum likelihood estimation using masked system data

This work estimates component reliability from masked series-system life data, viz, data where the exact component causing system failure might be unknown. The authors extend the results of Usher and Hodgson (1988) by deriving exact maximum likelihood estimators (MLE) for the general case of a series system of three exponential components with independent masking. Their previous work shows that closed-form MLE are intractable, and they propose an iterative method for the solution of a system of three nonlinear likelihood equations. >

Production planning for remanufactured products

This paper presents a methodology for production planning within facilities involved in the remanufacture of products. Remanufacturing refers to the process of accepting inoperable units, salvaging good and repairable components from those units, and then re-assembling good units to be re-issued into service. These types of facilities are common, yet many suffer from the unpredictability of good and repairable component yields, as well as processing time variation. These problems combine to make it extremely difficult to predict whether overall production output will be sufficient to meet demand. Low yields of key components can lead to shortages which require the facility to purchase new components for legacy systems, often with long lead times, thus causing overall delays. The approach developed here is a probabilistic form of standard material requirements planning (MRP), which considers variable yield rates of good, bad, and repairable components that are harvested from incoming units, and probabilistic processing times and yields at each stage of the remanufacturing process. The approach provides estimates of the expected number of remanufactured units to be completed in each future period. In addition, we propose a procedure for generating a component purchase schedule to avoid shortages in periods with a low probability of meeting demand. The proposed methodology is applied to an antenna remanufacturing process at the Naval Surface Warfare Center (NSWC). In this case study the proposed methodology identifies a potential shortage of a key component and suggests a corrective action to avoid significant delay in the delivery of remanufactured units.

Economic design of control charts using the Taguchi loss function

Abstract We embellish Duncans cost model with Taguchis loss function to incorporate losses that result from both inherent variability due to assignable causes. Whereas Duncan applies a penalty cost for operating out of control, he does not show how this cost can be obtained or quantified. We illustrate, analyze, and evaluate this model utilizing hypothetical cost figures and process parameters. We also suggest adjustments to control chart design parameters when there are process improvements over time.

The effect of process conditions on mechanical properties of laser‐sintered nylon

Purpose – The purpose of this paper is to measure the effect of process conditions on mechanical properties of laser‐sintered nylon 12 (Duraform®) and to determine the range of conditions that provide consistent mechanical performance for additive manufacturing.Design/methodology/approach – Tensile test specimens were fabricated over a range of well‐characterized process conditions including laser power, laser speed, scan spacing, layer thickness, build orientation, and build position. Tensile modulus, yield strength, ultimate tensile strength and elongation‐at‐fracture were measured and related to process parameters.Findings – Tensile properties are strongly related to the amount of energy deposited during scanning. Strength and modulus approach their maximum values as the energy deposited exceeds the amount needed to fully melt the applied powder. Elongation‐at‐fracture does not reach its maximum until higher energy‐melt ratio. Performance of blends with reused powder matches that of virgin powder when ...