Reliability evaluation of hard disk drive failures based on counting processes

• Published in: Reliability engineering & system safety 2013-01, Vol.109, p.110-118
• Main Authors: Ye, Zhi-Sheng, Xie, Min, Tang, Loon-Ching
• Format: Article
• Language: English
• Subjects: Accelerated life test (ALT); Applied sciences; Electronics; Exact sciences and technology; Hard disk drive (HDD); Magnetic and optical mass memories; Nelson-Aalen plot; Non-homogeneous poisson process (NHPP); Operational research and scientific management; Operational research. Management science; Poisson distribution; Reliability theory. Replacement problems; Storage and reproduction of information
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2012.07.003

Reliability assessment for hard disk drives (HDDs) is important yet difficult for manufacturers. Motivated by the fact that the particle accumulation in the HDDs, which accounts for most HDD catastrophic failures, is contributed from the internal and external sources, a counting process with two arrival sources is proposed to model the particle cumulative process in HDDs. This model successfully explains the collapse of traditional ALT approaches for accelerated life test data. Parameter estimation and hypothesis tests for the model are developed and illustrated with real data from a HDD test. A simulation study is conducted to examine the accuracy of large sample normal approximations that are used to test existence of the internal and external sources. ► Develop a reliability evaluation framework for HDD based on NHPPs. ► Use the framework to explain why traditional ALT methods fail to analyze the data. ► Develop statistical inference and hypothesis testing approaches. ► Apply the framework to a real HDD problem. ► Conduct a simulation to examine the normal approximation used for hypothesis testing.