A Fuzzy Data-Driven framework for Enhanced risk management Decision-Making in Manufacturing: A Case study

Document Type

Article

Publication Date

8-1-2025

Abstract

In today's fast-paced and competitive business world, companies are constantly looking for ways to increase their profits by reducing disruptions and failures. This research examines risks within a manufacturing company to facilitate sustainable growth. To achieve this, possible failures were identified using a combination of Risk Priority Number (RPN) criteria, improved by Fuzzy Shannon's Entropy, through group decision-making. Then, a framework based on Multi-Criteria Decision Making (MCDM) and Failure Mode and Effects Analysis (FMEA) was developed to assess and prioritize potential failures. The study highlights the necessity of analyzing the interplay between various risk assessment indicators, including the costs associated with failures, all while considering uncertainties through fuzzy modeling. These factors significantly influence how failures are ranked for risk management strategies. The methodology demonstrated effectiveness, particularly in prioritizing costly failures. Additionally, this research introduces an innovative aspect of risk assessment by integrating the confusion matrix concept from Machine Learning (ML) for data classification and exploring statistical correlations. The results revealed that the aggregated data ranking was most effectively matched and influenced by the Weighted Aggregated Sum Product Assessment (WASPAS) method, reaching significant recall and precision metrics rates.

Publication Source (Journal or Book title)

Manufacturing Letters

First Page

1681

Last Page

1688

This document is currently not available here.

Share

COinS