Accelerated life test is an important experiment method to evaluate the high life product reliability, and the exponential distribution is one of the most common life distribution. Since the discontinuity of observing time and the constrain of total time cost, we can't observe the actual failure time exactly, and only get the failure number of production in certain interval. In this paper, we study the parametric estimation of the step-stress accelerated life test under the exponential distribution,and evaluate the mean life of the product at the normal stress level.The relevant content of accelerated life is introduced in first part of the paper.In second part, we provide the parametric estimation of the step-stress accelerated life test under the exponential distribution with grouped data. Finally, we provide explicit form of the parametric estimation of the step-stress accelerated life test under the exponential distribution with multiple grouped data when the interval is equal. The simulation example is given to illustrate the proposed methods in this paper, the results show that the method in this paper is feasible. |