Optimal progressively censored reliability sampling plans for log-location-scale distributions

Here, we introduce a variable neighborhood search algorithm-based approach to determine the minimum sample sizes required for progressively censored reliability sampling plans within the flexible family of log-location-scale family of distributions, which includes Weibull and log-logistic distributions. The proposed method significantly reduces sample sizes compared to previously developed approaches, demonstrating its feasibility, especially for small sample sizes, in contrast to complete search methods. Optimal censoring plans are identified using A- and D-optimality criteria, a variance-measure criterion, and a cost function-based criterion. The proposed approach consistently outperforms the methods discussed in the literature for the case of Weibull distribution. Furthermore, an additional optimization problem with a cost constraint is addressed to illustrate the practicality and efficiency of the proposed method, and a sensitivity analysis is also carried out.