Fuzzy Logic based Failure Modes and Effects Analysis on Medical Ventilators

Failure mode and effects analysis (FMEA) is a widely used tool in engineering applications for the identification and assessment of possible failures. Traditionally, risk assessment of the failure modes is performed using risk priority numbers that are calculated based on the occurrence, severity and detection of the failure modes. The failure modes with the highest-ranking after these analyses are considered as the most commonly occurring, severe and detectable by the device, in general. But these priority numbers may not accurately reflect the failures due to the varied and complex nature of the evaluating processes. To overcome this limitation fuzzy string matching with a knowledge-based fuzzy inference system is used. This introduces a similarity indexing that accounts for these complex service data with huge uncertainty. This work is a case study, aimed towards applying FMEA and fuzzy FMEA for risk management on a medical ventilator used in hospitals. Nine potential failure modes have been identified out of which five major modes and four minor modes that are more probable to occur in a ventilator are prioritized based on fuzzy inference logic. Eventually, this risk prioritization of the failure modes can be considered for developing suitable prevention steps to mitigate those future failures.