•  
  •  
 

Keywords

conventional reliability, fuzzy reliability, data scarcity, aleatory uncertainty, epistemic uncertainty, triangle fuzzy number, fuzzy logic

Document Type

Research Article

Abstract

Effective spare part management relies heavily on accurate reliability assessment. However, in new or complex systems, historical failure data are often limited, making traditional probabilistic reliability models inadequate. This paper proposes a hybrid reliability framework that integrates conventional reliability theory with fuzzy logic to address both aleatory (random)and epistemic (lack of knowledge) uncertainties. The approach combines crisp failure rate estimation using exponential distributions with fuzzy reliability modelling using the triangular fuzzy number (TFN) methodology and fuzzy logic to support dynamic decision-making for a maintenance plan. The degree of membership functions is derived from the TFN and provides the operator with a decision-making tool, enabling robust reliability estimation even in data-scarce environments. The model is applied to ten marine vessels, analysing systems in the engine room. Results show that the hybrid approach provides a more realistic and flexible reliability assessment compared to conventional methods alone, particularly for components with sparse failure records. The integration of fuzzy logic enables sensitivity analysis and enhances decision-making in maintenance planning. This work lays the foundation for a more comprehensive spare-part prioritisation framework, especially when uncertainty dominates operational decisions.

html

Publication Date

31-12-2025

First Page

35

Last Page

46

Download

Share

COinS