Survey of FMEA methods with improvement on performance inconsistency

Abstract Failure mode and effects analysis (FMEA) is an effective risk assessment tool for detecting and reducing possible risks during a manufacturing process. However, traditional FMEA has some shortcomings when used in the real world. In recent years, improved FMEA approaches have been proposed to eliminate the inherent shortcomings of FMEA, but the risk ranking result obtained from those FMEA approaches may be inconsistent. Therefore, this paper integrates six FMEA approaches by using an ensemble learning technique to obtain comprehensive and reliable rankings for failure modes. Data from the assembly process of spark plugs are used to check the performance of the proposed method. Meanwhile, a comparation is designed to illustrate that the proposed FMEA method can not only obtain reliable results, but also provide meaningful management insights for practitioners.