Abstract
At the research and development (R & D) stage, the manufacturers may wish to select the most reliable product (supplier) from among several competing products (suppliers). In this study, assuming the degradation paths of product’s quality characteristics come from an inverse Gaussian degradation process, we first apply locally optimal (LO) criterion to construct a suitable selection rule. Furthermore, with a minimum guarantee of probability of correct selection (CS) of the proposed rule, we deal with the optimal design of a degradation experiment (which includes the determinations of the sample size, sampling frequency and the termination time) in such a way that the total experimental cost can be minimized. Finally, we use an example to demonstrate the proposed procedure. From the results, it shows that our proposed procedure has the ability of substantially reducing the sample size and termination time, which are needed to conduct a degradation experiment.