Parameter Estimation For Double-Truncated Burr Type ? Distribution Under Accelerated Life Testing

Burr distribution has been concerned by many scholars and widely used in various fields since its birth.With the development of science and technology and the progress of society,the reliability of products is becoming higher and higher.It is difficult to get the relevant information of product life test in a short time.It is an effective method to save testing time and cost by using accelerated life test without changing the failure mechanism of products.In this paper,based on the three parameter burr ? model,a stress accelerated life model with two truncated three parameter burr ? distribution is constructed.Iterative Bayesian estimation method is used to solve the parameter estimation and confidence interval for the first time,and reliable estimation results are obtained.The main contents of this paper are as follows:Firstly,in three parameter burr on the basis of ? distribution model,a truncation function is constructed,which includes a wide range of model structures through the adjustment of parameters in the model,and can be applied to more application backgrounds.In addition,for the purpose of effectively saving test time,an acceleration factor is added to the model,so that the application of the new model is further extended.After the expansion,the new model is named double truncation three parameter burr ? acceleration model.Secondly,due to the complexity of the model,the calculation is heavy and the accuracy is reduced,so Bayesian iterative algorithm is proposed to solve the parameters of the model for the first time.The performance of the new method is evaluated by Monte Carlo simulation.The results show that the new method has smaller relative deviation and mean square error than the traditional Bayesian estimation,and can obtain more stable MLE estimation.Finally,the theory is applied to the failure analysis of oil well pump,which makes the theoretical results have certain engineering application value.