PROJECT TITLE :

Lifetime Inference for Highly Reliable Products Based on Skew-Normal Accelerated Destructive Degradation Test Model

ABSTRACT:

The accelerated damaging degradation test (ADDT) method provides an efficient way to assess the reliability information of highly reliable merchandise whose quality characteristics degrade over time, and can be taken only once on each tested unit throughout the measurement method. Conventionally, engineers assume that the measurement error follows the conventional distribution. However, degradation models based on this normality assumption typically don't apply in practical applications. To relax the normality assumption, the skew-traditional distribution is adopted in this study as a result of it preserves the benefits of the conventional distribution with the additional profit of flexibility regarding skewness and kurtosis. Here, motivated by polymer knowledge, we propose a skew-traditional nonlinear ADDT model, and derive the analytical expressions for the product's lifetime distribution together with its corresponding $100p$th percentile. Then, the polymer knowledge are used to illustrate the benefits gained by the proposed model. Finally, we addressed analytically the consequences of model mis-specification when the skewness of measurement error are mistakenly treated, and also the obtained results reveal that the impact from the skewness parameter on the accuracy and precision of the prediction of the lifetimes of products is quite important.