Scholarlink

<p>In this study, we introduce an accelerated life testing methodology under combined stress conditions, incorporating both thermal and non-thermal stress factors into the Eyring model framework. It is assumed that the lifetime of products follows an exponential distribution, which is well-suited for modeling time-to-failure data in reliability analysis. To estimate the model parameters, a Bayesian estimation strategy is used under three different loss functions: the squared error loss function, the general entropy loss function, the linear exponential loss function. The Bayesian framework enables flexible and robust inference by incorporating prior knowledge and adapting to diverse decision- making scenarios. The proposed methodology offers reliability engineers an effective tool for estimating product lifetime under complex stress conditions, enhancing predictive accuracy and supporting accelerated life testing applications. A simulation study was conducted to compare the performance of Bayesian estimates with maximum likelihood estimation. Finally, a real life application was considered for illustration purposes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bayesian Inference For Step-Stress Accelerated Life Testing Using Generalized Eyring Exponential Model Under Type II Censoring

  • 期刊论文

  • 发表日期：

    2026年6月29日

查看全文
  • Afaq Ahmad,
  • R. A. Rather

摘要

In this study, we introduce an accelerated life testing methodology under combined stress conditions, incorporating both thermal and non-thermal stress factors into the Eyring model framework. It is assumed that the lifetime of products follows an exponential distribution, which is well-suited for modeling time-to-failure data in reliability analysis. To estimate the model parameters, a Bayesian estimation strategy is used under three different loss functions: the squared error loss function, the general entropy loss function, the linear exponential loss function. The Bayesian framework enables flexible and robust inference by incorporating prior knowledge and adapting to diverse decision- making scenarios. The proposed methodology offers reliability engineers an effective tool for estimating product lifetime under complex stress conditions, enhancing predictive accuracy and supporting accelerated life testing applications. A simulation study was conducted to compare the performance of Bayesian estimates with maximum likelihood estimation. Finally, a real life application was considered for illustration purposes.