Reliability assessment of two production lines using joint progressively type-II censored XLindley samples

Area of Science:

• Engineering
• Statistics
• Manufacturing

Background:

• Assessing production line reliability is crucial for manufacturing efficiency and product quality.
• Joint progressively Type-II censored samples offer a robust method for reliability analysis.

Purpose of the Study:

• To evaluate the reliability of two production lines using joint progressively Type-II censored data from the XLindley distribution.
• To estimate unknown parameters and reliability functions for individual and combined production lines.
• To compare classical likelihood-based and Bayesian estimation techniques.

Main Methods:

• Utilized joint progressively Type-II censored samples from the XLindley distribution.
• Employed Maximum Likelihood Estimation (MLE) for point estimates.
• Applied Bayesian inference with Markov Chain Monte Carlo (MCMC) under a squared error loss function.
• Investigated approximate confidence intervals, percentile bootstrap intervals, and highest posterior density credible intervals.
• Considered A-optimality, D-optimality, and F-optimality for optimal censoring plan selection.

Main Results:

• Both MLE and Bayesian methods provided reliable estimates for parameters and reliability functions.
• Simulation studies demonstrated the accuracy and efficiency of the proposed methods across various censoring schemes.
• The methodology was validated using two real-world manufacturing datasets.

Conclusions:

• The proposed reliability assessment framework using joint progressively Type-II censored samples is effective for dual production lines.
• The study provides practical insights for optimizing manufacturing processes and enhancing product quality through robust reliability analysis.