• Journal of Applied Reliability
• /
• v.14 no.3
• /
• pp.182-190
• /
• 2014

This paper presents new practical accelerated life test plans with different censoring times at three levels of stress for Weibull and lognormal lifetime distributions, respectively. The proposed plans are compared with the corresponding two-level statistically optimal plans and three-level compromise and practical plans. Computational results indicate that new practical plans have been more precise and effective than the existing three-level plans under a constraint of total testing time. In addition, a procedure to determine useful ALT plans is illustrated with a numerical example.

• Journal of Applied Reliability
• /
• v.15 no.3
• /
• pp.170-175
• /
• 2015

Reliability demonstration tests (RDT's) are widely employed in design verification and process validation stages of industry. New mixed attribute-variable RDT plans that compromise demerits of the corresponding zero and zero or one failure plans which are common in practice are developed for the exponential distribution. The proposed mixed plans are compared with the typical RDT plans in terms of probability of acceptance and expected test termination time. A numerical example is provided to illustrate the mixed plans and a procedure to extend these plans to the Weibull distribution with known shape parameter is also presented.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.47
• /
• pp.1-10
• /
• 1998

Testing high reliability devices under nomal operating condition is difficult, because the devices are not likely to fail in the relatively short time available for tests. For most applications it is necessary to accelerate the causes of failure by increasing a stress above its nomal value. Previous accelerated life test(ALT) plans have shown how to find optimum allocation, lowest stress and sample size subject to minimizing the variance of mean life estimator. In these ALT plans, the highest acceptable test-stress was assumed to be specified in advance by the experimenter but there is no guidance for selecting it. This assumption is, however, inappropriate for many applications. Testing devices at too-high stress levels can invalidate the extrapolation model, or introduce failure mechanisms that are not anticipated under nomal operating conditions. In this paper, we propose new 4:2:1 compromise plans using Min-Max method to minimize this risk and present minimized test-stress levels(max, middle, min), and find sample allocation based on Min-Max 4:2:1 compromise plans. In result, we compare previous 4:2:1 compromise plans specified maximum test-stress with Min-Max 4:2:1 compromise plans minimized maximum test-stress.

• Journal of Applied Reliability
• /
• v.3 no.2
• /
• pp.137-143
• /
• 2003

Sequential test plans are characterized by decision rules for accepting or rejecting compliance, or continuing the test at my test time. They are determined by selected values of risks and discrimination ratio. The sequential test plans in the international standard such as MIL-HDBK-781A are based on the assumption that the underlying distribution of times between failures is exponential. In this paper, sequential test plans are extended to the Weibull distribution case. Simulation studies are performed to examine the reasonability in this extension.

• Journal of Applied Reliability
• /
• v.17 no.2
• /
• pp.112-121
• /
• 2017

Purpose: The most previous works on designing accelerated life tests (ALTs) are focused on the application of a single stress. Because of the difficulty to obtain the sufficient information in a reasonable duration using single stress only, there is needed in practice to use multiple-stress ALTs frequently. This paper presents new practical plans with two stresses for Weibull distribution. Methods: The four-level practical plans based on rectangle test region are proposed and compared with the corresponding three-level statistically optimal plans. Sensitivity analyses for assumed design parameters and life-stress relationship are conducted. Results: A procedure to choose practical ALT plans is illustrated with a numerical example and guidelines for planning two-stress ALTs are provided. Conclusion: The proposed two-stress ALT plans on practical constraints to assess a quantile of Weibull lifetime distribution at the use condition are efficient and robust.

• Journal of Applied Reliability
• /
• v.17 no.2
• /
• pp.129-135
• /
• 2017

Purpose: This article provides step-stress accelerated degradation test (ADT) plans based on the Wiener process. Method: Step-stress levels and the stress change times are determined based on the D-optimality criteria to develop test plans. Further, a simple grid search method is provided for obtaining the optimal test plan. Results: Based on the solution procedure, ADT plans which include the stress levels and change times are developed for conducting the reliability test. Conclusion: Optimal step-stress ADT plans are provided for the case where the number of measurements is small.

• Journal of Korean Institute of Industrial Engineers
• /
• v.43 no.2
• /
• pp.147-153
• /
• 2017

In order to demonstrate a target reliability with a specified confidence level, a new two-stage Bayesian Reliability Demonstration Test (RDT) plans that is known to be more effective than a corresponding single-stage one is proposed and developed by Bayesian framework with beta prior distribution for Weibull life time distribution. A numerical example is provided to illustrate the proposed RDT plans and compared with other non-Bayesian and Bayesian plans. Comparative results show that the proposed Bayesian two-stage plans have some merits in terms of required and expected testing time and probability of acceptance.

• Journal of Korean Society for Quality Management
• /
• v.17 no.1
• /
• pp.89-106
• /
• 1989

For Weibull distributed lifetimes, this paper presents asymptotically optimal accelerated life test plans for practical applications under intermittent inspection and type-I censoring. Computational results show that the asymptotic variance of a low quantile at the design stress as optimal criterion is insensitive to the number of inspections at overstress levels. Sensitivity analyses indicate that optimal plans are robust enough to moderate departures of estimated failure probabilities at the design and high stresses as input parameters to plan accelerated life tests from their true values. Monte Carlo simulation for small sample study on optimal accelerated life test plans developed by the asymptotic maximum likelihood theory is conducted. Simulation results suggest that optimal plans are satisfactory for sample size in practice.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.945-952
• /
• 2006

Several accelerated life test plans use tests at only two levels of stress and thus, have practical limitations. They highly depend upon the assumption of a linear relationship between stress and time-to-failure and use only two extreme stresses that can cause irrelevant failure modes. Thus 3-level stress plans are preferable. When the lifetime distribution of test unit is exponential with mean lifetime $\theta_i$ at stress $x_i$, i=0, 1, 2, 3, we derive the optimum quadratic plan under the assumption that a quadratic relationship exists between stress and log(mean lifetime), and propose the compound linear plans, as an alternative to the optimum quadratic plan. The proposed compound linear plan is better than two other compromise plans for constant stress testing and nearly as good as the optimum quadratic plan, and has the advantage of simplicity.

• Journal of Applied Reliability
• /
• v.14 no.4
• /
• pp.262-266
• /
• 2014

In this paper, we consider the problem of determining the confidence level in zero-failure reliability sampling plans when the life distribution is Weibull distribution with a shape parameter m and a scale parameter ${\eta}$. We introduce zero-failure reliability sampling plans for Weibull distribution and investigate some characteristics of zero-failure reliability sampling plans. Finally, We propose new guideline for determining the confidence level in zero-failure reliability sampling plans for assuring $B_x-life$.