Optimal Design Of Accelerated Life Test With Cost Constraint

This article considers the optimization problem of a constant-stress accelerated life test under cost constraint and Type I progressive censoring.In order to conduct an accelerated life test efficiently with cost constraint and obtain the precise estimate of the lifetime parameters,several decision variables such as the test stress levels,the sample allocation proportions,the number of test units,the number of inspections and the length of inspection intervals should be designed carefully under the constraint that the total cost of experiment does not exceed a pre-determined budget such that the asymptotic variance of the logarithm of the maximum likelihood estimator of the mean lifetime at the use condition is minimized.First of all,this paper derives the likelihood function and obtains the maximum likelihood estimation of the life parameter,then derives the Fisher information matrix and the expression of the maximum likelihood estimation of the asymptotic variance,and uses the Monte-Carlo method to get the optimal scheme of the given model parameter,then a sensitivity analysis is performed for the optimal scheme.The results of this paper provide valuable reference and guidance for the experimenter to carry out this type of accelerated life test.