摘要
Product reliability is a critical concern for both producers and consumers, as it directly impacts user satisfaction and brand reputation. In practice, professionals use life testing in conjunction with acceptance sampling plans to verify product reliability efficiently. However, much of the existing research emphasizes mean life, which may not be suitable for products with skewed lifetime distributions, such as many electronic devices. To address this gap, this paper introduces two widely used acceptance sampling schemes-single and double sampling plans-within the framework of time-truncated life testing, using percentile life as a measure of reliability. We derive operating characteristic functions for both single and double sampling plans and establish optimization models to minimize the required sample size for testing, simultaneously accounting for Type I and Type II errors. We also present an algorithm for solving these optimization models and conduct an in-depth analysis of the proposed methods, outlining their respective strengths and limitations for real-world applications. Finally, we demonstrate the practicality and applicability of our approach through a case study, showcasing the effectiveness of the proposed methods.