Principles of Prioritization for Failure Mode and Effects Analysis with Missing Risk Ratings

Failure mode and effects analysis (FMEA) is a reliability engineering methodology used to define, identify, and eliminate known and /or potential failure modes, problems, errors, for a system, design, process, and /or service. FMEA adopts a risk priority number (RPN) model which considers three risk...

Full description

Saved in:
Bibliographic Details
Main Author: Ngian, Seng Kai
Format: Thesis
Language:English
Published: 2019
Subjects:
Online Access:http://ir.unimas.my/id/eprint/27501/2/Ngian%20Seng%20Kai.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Failure mode and effects analysis (FMEA) is a reliability engineering methodology used to define, identify, and eliminate known and /or potential failure modes, problems, errors, for a system, design, process, and /or service. FMEA adopts a risk priority number (RPN) model which considers three risk factors, i.e., Severity (S), Occurrence (O), and Detection (D), for prioritization of potential failure modes and corrective actions. However, most of the studies do not focus on the rationality of the prioritization outcomes, and assume that all risk ratings (i.e., S, O, and D ratings) are known a priori. In this thesis, three basic principles, i.e., transitivity, pareto optimality, and independence of irrelevant alternatives, are formulated to ensure rationality of prioritization of failure modes or corrective actions in FMEA, are analysed together with the rational properties of an RPN model. It is deduced that the monotonicity property is important for fulfilling the pareto optimality principle. Besides, a new tree model and a vector representation for potential failure modes and corrective actions are proposed. Moreover, an interval-valued RPN model to solve the problem with missing S, O, and/or D ratings by imputing the corresponding rational interval value(s) is further proposed. The proposed solution is evaluated analytically with respect to the aforementioned three principles. Empirical evaluations using benchmark information ascertain the usefulness of the proposed solution.