Multi-attribute approach for enhancing maintenance processes in maintenance depots under a type-2 fuzzy environment

Abstract

Introduction/purpose: The purpose of this research is to determine the priority of Key Performance Indicators (KPIs) in a precise and structured manner. By applying the fuzzy multi-attribute decision-making model, operational management can identify and prioritize activities that will enhance maintenance process reliability in the shortest possible time while simultaneously reducing costs. Methods: The relative importance of sub-processes and KPI values is represented using predefined linguistic terms modelled by interval type-2 fuzzy numbers (IT2FNs). These assessments are formulated as a fuzzy group decision-making framework. The weight vector is determined using the fuzzy geometric mean, while the ranking of KPIs is obtained through the Taxonomy method combined with IT2FNs, which represents the main scientific contribution of this research. Results: Real-world data gathered from a maintenance depot were used to test the proposed model. The study effectively modelled uncertainty in KPI evaluations using seven predefined linguistic expressions mapped onto IT2FNs. A consistent weight vector was obtained using the fuzzy group decision-making approach. Effective KPI ranking was achieved through a combination of the Taxonomy method and IT2FNs, which helped pinpoint the most important areas for operational improvement. The method's ability to provide clear priorities to support reliability improvements while cutting costs was validated through its application. Conclusion: The key contributions of this study are: (i) fuzzy algebra rules with IT2FNs are used to determine the group utility value, and (ii) the integration of the Taxonomy method with IT2FNs for an improved decision-making procedure.