Comparative Study of the use of Arithmetic Mean and Geometric Mean for Data Aggregation in FMEA Analysis

Ikuobase Emovon, Modestus Okechukwu Okwu

Abstract


Failure Mode and Effects Analysis (FMEA) is a commonly use approach for ranking risk of failure modes of most marine machinery system. However, the Risk Priority Number (RPN) use for evaluating risk within FMEA framework have several limitations and as such most researchers focus had been in the area of improvement of the tool without considering the effect of the aggregated data from multiple experts use as input  into the decision making process. The purpose of this paper therefore, is to perform a comparative analysis of the aggregation techniques for combining multiple experts’ ratings of failure modes in order to establish their degree of similarity and their effect on the output of the ranking tools. The commonly used aggregation techniques in the literature considered are; Arithmetic Mean (AM) and Geometric Mean (GM). The index for comparison of the AM and GM was based on the effect of their respective aggregated data on the rank produced by four well known ranking tools; RPN of FMEA, Compromise Programming (CP), Vlsekriterijumska Optimizacija Ikompromisno Resenje, meaning: Multicriteria Optimization and Compromise Solution (VIKOR), Weighted Sum Model (WSM) and Weighted Product Model (WPM). A case study of fuel oil system of marine diesel engine of ship system was utilised to demonstrate the effectiveness of the two techniques.


Full Text:

PDF

Refbacks

  • There are currently no refbacks.