Fuzzy Inference System-Based Prognostics for Remaining Useful Life Estimation

Prognostics and health management (PHM) plays a critical role in ensuring the reliability and safety of complex engineering systems such as aircraft engines. In this field, estimating the Remaining Life (RUL) of systems is vital for optimizing maintenance strategies and preventing unexpected failures. This study proposes a Fuzzy Inference System (FIS)-based approach for RUL estimation. The proposed model uses expert-defined fuzzy rules and membership functions to effectively address uncertainties and nonlinear degradation patterns in sensor data. The industry-standard NASA C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset was used for model development and validation. Multiple features extracted from the dataset were input to the developed Fuzzy Inference System, and the system’s performance was comprehensively evaluated under different operating conditions. Experimental results demonstrate that the FIS model performs competitively compared to traditional machine learning methods and produces interpretable and robust RUL estimates. This study demonstrates the potential of fuzzy logic in data-driven prognostics and makes a significant contribution to the literature by laying a solid groundwork for future hybrid approaches that integrate expert knowledge and learning algorithms.