International Journal of Reliability, Quality and Safety Engineering

In this paper, we study two sectional models, each involving two Weibull distributions. Characterization of the plot on Weibull plotting paper (WPP) for each model is carried out. We also study the shapes of the probability density and the failure rate functions. These are useful in determining if a given failure data set can be modeled by such a model. We discuss the estimation of model parameters based on the WPP plot and illustrate through two examples involving real data.

Bayesian reliability demonstration test plans are developed for binomial and exponential sampling distributions using mixtures of beta and inverse gamma prior distributions, respectively. Both types of plans consider a single specified target reliability and rectify an important drawback of an existing well-known classical single-level test planning procedure. The plans are developed in such a way that they attain a specified probability of passing the test when the target reliability has been met as well as provide desired confidence that the target reliability has been met given that the test has been passed.

Quantitatively assessing quality and using this assessment for competitive benchmarking and diagnostics of manufactured part failure are very important for continuous improvement in modern manufacturing industries. Process capability analysis often entails characterizing or assessing process specification or quality characteristics. When these quality characteristics are related, the analysis should be based on a multivariate statistical technique. A current problem in multivariate quality control is that there is no consensus about a methodology for assessing capability. Thus, the critical first step in instituting a multivariate control scheme is not well defined. While numerous authors have recently proposed alternative definitions of multivariate capability indices, those methods may not be practical in some cases. In this research, a new process control variable, geometric distance (GD), for assessing or evaluating the quality of manufactured product is developed and investigated for reducing dimensionality. The theoretical distribution of the geometric distance is investigated and a suitable performance metric of the multivariate process data is proposed. Finally, some real data are used to demonstrate the capability of the proposed method.

Production systems are generally subjected to failures, which are not self-announcing. These failures may not bring the system to a complete halt but may cause its malfunction, which would affect the quality of output. Inspections at intervals are required to detect such failures. After a failure, the system would continue to produce degraded output unless corrective action (minimal repair) is taken after detecting the failure during inspection. These minimal repairs do not bring the system to "as good as new" condition, but restore its condition to the level prior to the failure. A replacement/overhaul of the system after operation for a long time will make it "as good as new." The paper presents optimal inspection models for such a production system. The system is replaced or overhauled at predetermined times, marking the end of a cycle, while inspections are periodically done within a cycle. An entire output during an interval is scrapped, if inspection reveals a failure during the interval. Dynamic programming formulation has been used to optimize expected profit per cycle. The model is suitable when prior sales commitments exist and failure of the system is not self-announcing.

The paper describes the motivations, process and results of an activity defining the quality classification categories for a complicated system product. The underlying case project shares an objective to construct one of the largest scientific instrumentation ever built by mankind. This 10-year effort with significant technological, scientific, political and financial risks has reached manufacturing and partially the installation phase. It was realized that the key criteria to define the quality classification category for each equipment, item, part, subassembly and system must be done in relation to external world. A failure of an item or part must be assessed in respect of its anticipated hazard on environment, on expected performance of the system and on financial stability of the project. During the work, it was realized that each part should be evaluated separately, meaning that inheritance of quality categories cannot take place in the system. Once defined, quality categories dictate the level of detail used in engineering change, documentation and operational procedures of each part of the system. A more in-depth look on contact impact analysis between components of a complex system product is also provided. It is concluded that the approach provided in the paper can be applied to any system or artifact requiring design, production and assembly.

Tolerances in component values will affect a product manufacturing yield. The yield can be maximized by selecting component nominal values judiciously. Several yield optimization routines have been developed. A simple algorithm known as the center of gravity (CoG) method makes use of a simple Monte Carlo sampling to estimate the yield and to generate a search direction for the optimal nominal values. This technique is known to be able to identify the region of high yield in a small number of iterations. The use of the importance sampling technique is investigated. The objective is to reduce the number of samples needed to reach the optimal region. A uniform distribution centered at the mean is studied as the importance sampling density. The results show that a savings of about 40% as compared to Monte Carlo sampling can be achieved using importance sampling when the starting yield is low. The importance sampling density also helped the search process to identify the high yield region quickly and the region identified is generally better than that of Monte Carlo sampling.