Automation of FMEA for computer servers using log data with grey relational analysis

Failure modes and effects analysis (FMEA) is a powerful and proactive quality tool for defining, detecting, and identifying potential failure modes and their effects. However, conventional FMEA process is sometimes difficult to implement due to workload required and subjectivity of the evaluations performed. Hence, automation of this tool can be useful for some application domains to objectively evaluate failures and faster implementations, which is the aim of this study. To automate the process and eliminate the subjectivity, data-based algorithms such as grey relational analysis and association analysis are implemented in the following with an application to computer servers.