Analysis of optimal accelerated life test plans for periodic inspection

Recent Advances in Robust Design for Accelerated Failure Time Models with Type I Censoring

Many fields including clinical and manufacturing areas usually perform life-testing experiments and accelerated failure time models (AFT) play an essential role in these investigations. In these models the covariate causes an accelerant effect on the course of the event through the term named acceleration factor (AF). Despite the influence of this factor on the model, recent studies state that the form of AF is weakly or partially known in most real applications. In these cases, the classical optimal design theory may produce low efficient designs since they are highly model dependent. This work explores planning and techniques that can provide the best robust designs for AFT models with type I censoring when the form of the AF is misspecified, which is an issue little explored in the literature. Main idea is focused on considering the AF to vary over a neighbourhood of perturbation functions and assuming the mean square error matrix as the basis for measuring the design quality. A key result of this research was obtaining the asymptotic MSE matrix for type I censoring under the assumption of known variance regardless the selected failure time distribution. In order to illustrate the applicability of previous result to a study case, analytical characterizations and numerical approaches were developed to construct optimal robust designs under different contaminating scenarios for a failure time following a log-logistic distribution.

Condition monitoring of aluminium electrolytic capacitors using accelerated life testing

Purpose

An electrolytic capacitor is extensively used as filtering devices in various power supplies and audio amplifiers. Low cost and higher value of capacitance make it more well known. As environmental stress and electrical parameters increase, capacitors degrade on accelerated pace. The paper aims to discuss these issues.

Design/methodology/approach

This paper focusses on the impact of thermal stress on electrolytic capacitors using accelerated life testing technique. The failure time was calculated based on the change in capacitance, equivalent series resistance and weight loss. The experimental results are compared with the outcome of already available life monitoring methods, and the accuracy level of these methods is accessed.

Findings

The results of all the three methods are having maximum 55 per cent accuracy. To enhance the accuracy level of theoretical methods, modifications have been suggested. A new method has been proposed, whose outcome is 92 per cent accurate with respect to experimentally obtained outcomes.

Practical implications

To assess the capacitor’s reliability using an experimental and modified theoretical method, failure prediction can be done before it actually fails.

Originality/value

A new method has been proposed to access the lifetime of capacitor.

Accelerated temperature and voltage life tests on aluminium electrolytic capacitors

Purpose

– The purpose of this paper is to focus on conducting accelerated life tests on aluminium electrolytic capacitors under accelerated temperature and voltage stress to study the effect of applied voltage and ambient temperature on the capacitor, its degradation over time, failure data collection, analysis and then modelling the failure times. Principles of DOE are used for studying the effect of temperature and voltage.

Design/methodology/approach

– Life tests are conducted at three levels of temperature and applied voltage and the life of capacitor is ascertained at each treatment level. Life variation with voltage and temperature is studied to gain an insight as to how these factors affect the lifetime of the capacitor. The interaction effect of temperature and voltage on capacitor life is also established.

Findings

– The life of the capacitor decreases exponentially with temperature and voltage at all the three factor levels. Ambient temperature, applied voltage and their interaction effect significantly affects the life of the capacitor. Applied voltage has the greatest effect followed by ambient temperature and then their interaction effect. Life of the capacitor has been estimated as 4,206 hrs when only voltage is taken as the accelerated stress using Inverse Power Law and as 4,003 hrs when both temperature and voltage are taken as accelerating stress using combination model.

Research limitations/implications

– This work consider only decrease in capacitance as the failure criterion. However, as a future scope, it is proposed that test may be conducted by taking into consideration not only the decrease in capacitance as the failure criteria but by monitoring all the performance parameters of the capacitor. This would give a more realistic assessment of life as it is possible that capacitor may have failed much before it reached the lower threshold capacitance value.

Practical implications

– This work has lots of practical implications. It shows how DOE approach can be used for ALT data analysis and identification and effect of critical stresses acting on capacitors in real practice. Most critical types of stresses affecting the reliability can thus be controlled to ensure better performance. Product manufactures as well as users will be benefited by such findings. The paper has also illustrated how failure data can generated by degradation analysis using life test data collection at discrete intervals.

Originality/value

– The methodology presents an alternative non traditional approach of accelerated life testing, which does not require continuous monitoring of test items. This only requires intermittent monitoring which reduces the need of test resources. Though the degradation study itself is not new but using degradation study for ALT data generation is new. This approach may considerably reduce the test duration and resources used for ALT. DOE approach gives more tangible result to study the effect of various variables on the dependent variable. As DOE approach uses a fractional factorial design, it can be very helpful to conduct life tests with minimum number of test units (only a fraction of full factorial test units). This will considerably reduce the test duration, resources requirement for testing, easier but accurate data analysis, and faster product development, especially when ALT is to be conducted at several stresses simultaneously.

Planning accelerated life tests under Exponentiated‐Weibull‐Arrhenius model

Purpose

The purpose of this paper is to present designs for an accelerated life test (ALT).

Design/methodology/approach

Bayesian methods and simulation Monte Carlo Markov Chain (MCMC) methods were used.

Findings

In the paper a Bayesian method based on MCMC for ALT under EW distribution (for life time) and Arrhenius models (relating the stress variable and parameters) was proposed. The paper can conclude that it is a reasonable alternative to the classical statistical methods since the implementation of the proposed method is simple, not requiring advanced computational understanding and inferences on the parameters can be made easily. By the predictive density of a future observation, a procedure was developed to plan ALT and also to verify if the conformance fraction of the manufactured process reaches some desired level of quality. This procedure is useful for statistical process control in many industrial applications.

Research limitations/implications

The results may be applied in a semiconductor manufacturer.

Originality/value

The Exponentiated‐Weibull‐Arrhenius model has never before been used to plan an ALT.

The exponentiated Weibull software reliability growth model with various testing‐efforts and optimal release policy

Purpose

The purpose of this research is to incorporate the exponentiated Weibull testing‐effort functions into software reliability modeling and to estimate the optimal software release time.

Design/methodology/approach

This paper suggests a software reliability growth model based on the non‐homogeneous Poisson process (NHPP) which incorporates the exponentiated Weibull (EW) testing‐efforts.

Findings

Experimental results on actual data from three software projects are compared with other existing models which reveal that the proposed software reliability growth model with EW testing‐effort is wider and effective SRGM.

Research limitations/implications

This paper presents a SRGM using a constant error detection rate per unit testing‐effort.

Practical implications

Software reliability growth model is one of the fundamental techniques to assess software reliability quantitatively. The results obtained in this paper will be useful during the software testing process.

Originality/value

The present scheme has a flexible structure and may cover many of the earlier results on software reliability growth modeling. In general, this paper also provides a framework in which many software reliability growth models can be described.