Expert System for Autoclave Damage Detection Using the Fuzzy Logic Method

The reliability of sterilization equipment, such as autoclaves, is essential to ensure patient safety, infection control, and operational continuity in healthcare facilities. Damage or malfunction of autoclaves may disrupt sterilization processes and pose significant risks to medical services. This study aims to develop an expert system for autoclave damage detection using the fuzzy logic method to support faster and more accurate diagnostic decision-making. The proposed system applies fuzzy inference to evaluate the level of damage based on input symptoms provided by users. By handling uncertainty and varying symptom intensities, the fuzzy logic approach enables proportional assessment rather than rigid rule-based classification. The system was designed through knowledge acquisition from technical experts and implemented using fuzzy membership functions and inference rules to determine damage severity levels. Experimental testing was conducted to evaluate system performance and diagnostic accuracy. The results indicate that the expert system successfully generated diagnosis outputs for all tested scenarios, achieving functional diagnostic accuracy within the defined test cases. The system was also able to calculate a quantified damage severity value of 11.6235981% based on the given symptoms, demonstrating its capability to assess damage levels numerically and objectively. Furthermore, the developed system significantly reduces the time required for damage detection compared to manual diagnostic procedures. Automating the evaluation process, it assists electromedical technicians in identifying faults more efficiently and taking preventive or corrective actions promptly. Overall, the implementation of a fuzzy logic-based expert system provides an effective, accurate, and practical solution for improving autoclave maintenance management and supporting healthcare service reliability.